# Ava Advisor (remote · mcp.ava.fund)

Your AI watches the markets so you can live your life. Financial intelligence for everybody.

- Trust score: 85/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.ava.fund`: 85/100 (this document), [markdown](https://verifymcp.io/servers/fund-ava-ava-advisor/mcp.md), [page](https://verifymcp.io/servers/fund-ava-ava-advisor/mcp)

## Channel facts

- Endpoint: `https://mcp.ava.fund/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 95/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 24514 tokens (~570/item across 43 items; 37 tools + 6 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (5% of tools); any adoption earns full credit.
- **Tool Safety**: 88/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "screen_unified" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 39 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Ava Advisor MCP server?

Ava Advisor is a hosted endpoint at https://mcp.ava.fund/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http fund-ava-ava-advisor 'https://mcp.ava.fund/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fund-ava-ava-advisor": {
      "url": "https://mcp.ava.fund/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fund-ava-ava-advisor": {
      "type": "http",
      "url": "https://mcp.ava.fund/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fund-ava-ava-advisor]
url = "https://mcp.ava.fund/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fund-ava-ava-advisor": {
      "type": "remote",
      "url": "https://mcp.ava.fund/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fund-ava-ava-advisor --url 'https://mcp.ava.fund/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fund-ava-ava-advisor:
    url: "https://mcp.ava.fund/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fund-ava-ava-advisor": {
      "Transport": "http",
      "Url": "https://mcp.ava.fund/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fund-ava-ava-advisor -t streamable-http -u 'https://mcp.ava.fund/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fund-ava-ava-advisor": {
      "type": "http",
      "url": "https://mcp.ava.fund/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 85, +1)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-20 (score 84, 0)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-19 (score 84, 0)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-18 (score 84, +1)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-17 (score 83, 0)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-16 (score 83, +1)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-15 (score 82, 0)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

### 2026-11-14 (score 82, +1)

- [security] Resource “capabilities” now points somewhere else: marketdx://capabilities → avaadvisor://capabilities
- [security] Resource “capabilities” now points somewhere else: marketiv://capabilities → avaadvisor://capabilities
- [security] Resource “gate_policy” now points somewhere else: marketdx://policy → avaadvisor://policy
- [security] Resource “gate_policy” now points somewhere else: marketiv://policy → avaadvisor://policy

## MCP tools (37)

### `theme_summary` (~178 tokens)

Theme Summary

Pre-composed analyst brief for a megatrend theme: pulse, winners/losers, top entities, aspect
    heatmap, ripple. `theme` = a theme name or id/slug; `window` = 7d/30d/90d/1y/mtd/qtd/ytd.

Input parameters:

- `country`: Optional market ISO-2 filter.
- `theme` (string, required): A megatrend theme — name/slug (resolved for you) or node id.
- `window` (string): News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

### `brief` (~866 tokens)

Brief

The generalized ANALYST BRIEF — one composed "how is <scope> doing right now?" picture (pulse + net direction,
    top_stories, winners/losers, aspect_heatmap, top_entities, top_assets) for any AND-combination of scopes. ⭐ Use to
    SUMMARIZE a scope (theme / news category / country / sector / aspect) — NOT a raw article list (that's
    search_news/news_feed). ⛔ NOT for a single COMPANY or market INDEX ("how is AAPL / the S&P doing?" →
    options_sentiment + stock_impact/news_feed; an index maps to an ETF, not a brief scope). For a sector×region the
    quickest path is pulse(kind='theme', target='banks', country=…); use brief for one precise GICS cohort or an AND-combo.
    Scope by ≥1 of (CSV for several) — REQUIRED (never whole-market):
      • `news_type` — a category; use ONLY these EXACT names: product_tech, ma_partnership, industry_thematic,
        earnings_results, corporate_action, management_governance, analyst_rating, macro_economic, geopolitics,
        commodity_supply, regulatory_legal, cybersecurity_digital_trust, digital_finance_tokenization,
        price_action_technical, crypto_related, forex_related, analyst_forecast. (commodity→commodity_supply;
        central-bank/rates→macro_economic — there is NO 'monetary_policy'.)
      • `country` (ISO-2) · `aspect` (impact channel) · `gics` (code or plain English) · `megatrend` (theme name/id).
    ⚠️ News coverage starts 2026-01-01. `node`+`ripple` appear only when a SINGLE megatrend anchors the brief.

Input parameters:

- `aspect`: Impact CHANNEL filter (e.g. `demand`, `competition`, `tariff`, `monetary`). Omit → all channels.
- `country`: Market filter — CSV of ISO-2 codes (e.g. `US` or `CN,TW,HK`). 🌍 If the question names a NATIONALITY or REGION ('European','Thai','Chinese','ASEAN'), put it HERE — never leave it inside a concept/`q`…
- `from_`: Lower time bound, ISO date `YYYY-MM-DD`. ⚠️ Ava Advisor NEWS coverage starts 2026-01-01 (nothing before).
- `gics`: A GICS sector/industry — a CODE PREFIX (sector `25` / group `2550` / industry `255010` / sub `25501010`, CSV for several) OR plain English ('banks', 'semiconductors', 'biotech'); the server resolves…
- `interval`: Time-bucketing of the pulse series: `day`|`week`|`month`.
- `lang`: Translate title/brief_text: `en`|`th`|`ja`.
- `megatrend`: A megatrend node — a name/slug (resolved for you, e.g. `foundry`) or an int node id. CSV for several.
- `news_type`: News CATEGORY (exact names only, e.g. `macro_economic`, `commodity_supply`, `earnings_results`).
- `to`: Upper time bound, ISO date `YYYY-MM-DD`.
- `window` (string): News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

### `search_news` (~663 tokens)

Search News

SEMANTIC news search across ALL covered asset classes — stocks, FX, crypto, COMMODITIES (metals
    like copper/gold, energy like oil), and private companies. Articles matched by MEANING, impact-labeled
    (title, publisher, entities, direction, why). USE THIS for 'copper news', 'metals', 'gold', etc.
    instead of a web search. `entity_type` keeps only stock/forex/crypto/commodity/private hits. For a
    FILTERED feed by aspect/direction/country use `news_feed`. `limit` = how many (default 20, max 50).
    TIME-SCOPE with `from_`/`to` (ISO dates, e.g. '2026-04-01') or a `window` ('90d','qtd','ytd','1y').
    ⚠️ News coverage starts 2026-01-01 — older ranges return nothing (that's no COVERAGE, not 'no news').
    Returns {match_quality, top_similarity, note, results}. If match_quality is 'weak'/'none', the corpus
    has no strongly relevant news — do NOT present these results as evidence; say so and use another route.

Input parameters:

- `collapse`: Merge near-duplicate stories (same article from many outlets) into one row + `dup_count`. Default ON; pass `false` for the raw un-deduped feed.
- `detail`: `compact` (default): per story title, date, publisher, types, impact_score, a short brief and the TOP-3 impacted entities (direction + relevance + one-line why) — fits the client's tool-output limit.…
- `entity_type`: Keep only hits of one kind: `stock`|`forex`|`crypto`|`commodity`|`private`. Omit → all.
- `format`: `json` (default): structured rows. `text`: the same stories as plain readable lines (no JSON keys / quotes / nesting) — about half the size; prefer it when you only need to READ the news to answer.
- `from_`: Lower time bound, ISO date `YYYY-MM-DD`. ⚠️ Ava Advisor NEWS coverage starts 2026-01-01 (nothing before).
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `q` (string, required): Free-text SEMANTIC news query — a topic/event/asset in any language ('copper', 'oil shock', 'Fed rate hike', 'ข่าวทองคำ').
- `to`: Upper time bound, ISO date `YYYY-MM-DD`.
- `window`: News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

Output parameters:

- `result`

### `news_feed` (~835 tokens)

News Feed

The filtered impact feed — news by megatrend/country/aspect/direction/news_type, across stocks,
    FX, crypto, COMMODITIES (metals/energy) and private cos. Use for 'negative tariff news on
    Semiconductors', 'macro news moving European stocks', 'copper / metals news', etc. Near-duplicate
    stories are MERGED by default (+`dup_count`); `collapse=false` for the raw feed. `limit` = how many
    (default 20, max 50); narrow the filters rather than paging deep. TIME-SCOPE with `from_`/`to` (ISO)
    or a `window` ('90d','qtd','ytd','1y'). To COMPARE periods, call once per period and compare the
    results. ⚠️ News starts 2026-01-01 — older ranges return nothing (no coverage, not 'no news').
    `megatrend` accepts a plain name/slug/concept ('foundry', 'AI chips') — resolved server-side to node id(s).

Input parameters:

- `aspect`: Impact CHANNEL filter (e.g. `demand`, `competition`, `tariff`, `monetary`). Omit → all channels.
- `collapse`: Merge near-duplicate stories (same article from many outlets) into one row + `dup_count`. Default ON; pass `false` for the raw un-deduped feed.
- `country`: Market filter — CSV of ISO-2 codes (e.g. `US` or `CN,TW,HK`). 🌍 If the question names a NATIONALITY or REGION ('European','Thai','Chinese','ASEAN'), put it HERE — never leave it inside a concept/`q`…
- `detail`: `compact` (default): per story title, date, publisher, types, impact_score, a short brief and the TOP-3 impacted entities (direction + relevance + one-line why) — fits the client's tool-output limit.…
- `direction`: Filter by impact direction: `pos` | `neg` | `ambiguous`. Omit → all.
- `format`: `json` (default): structured rows. `text`: the same stories as plain readable lines (no JSON keys / quotes / nesting) — about half the size; prefer it when you only need to READ the news to answer.
- `from_`: Lower time bound, ISO date `YYYY-MM-DD`. ⚠️ Ava Advisor NEWS coverage starts 2026-01-01 (nothing before).
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `megatrend`: A megatrend node — a name/slug (resolved for you, e.g. `foundry`) or an int node id. CSV for several.
- `min_relevance`: Minimum impact relevance, 0–1.
- `news_type`: News CATEGORY (exact names only, e.g. `macro_economic`, `commodity_supply`, `earnings_results`).
- `only_scored`: Keep only articles carrying a judged per-entity impact. Omit → all gated articles.
- `to`: Upper time bound, ISO date `YYYY-MM-DD`.
- `window`: News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

Output parameters:

- `result`

### `stock_impact` (~972 tokens)

Stock Impact

How news moved a specific company/asset (incl commodities like GOLD.COMM) — per-article impact
    (direction + aspect + why), most recent first. Near-duplicate stories are MERGED by default (each row
    = one story + `dup_count`); `collapse=false` for the raw feed. `limit` = how many (default 20, max 50). Ordered by how hard each story hits this entity (`relevance`, 1.0 = directly about it; a market wrap that touches it ranks lower), then recency; `companies_in_story` says when it is one of several
    — heavily-covered assets have HUNDREDS, so keep it small + narrow. TIME-SCOPE with `from_`/`to` (ISO)
    or `window` ('90d','qtd','1y'); to COMPARE periods, call once per period. ⚠️ News starts 2026-01-01 —
    older ranges return nothing (no coverage, not 'no news'; price/volatility history goes back decades).
    🔵 BONDS/RATES: a specific tenor/rate (`US-2Y.GB`, `SOFR.MM`) with no news of its own returns the
    country's benchmark-10Y macro news tagged `scope:'curve_macro'` + `macro_source` — narrate those as
    curve-wide central-bank context, not tenor-specific. 📏 MAGNITUDE: for a listed, priced asset each story has
    `price_move` = close-to-close % of the session it landed in (`day_pct`) and of the next one (`next_day_pct`) —
    the market's reaction next to the direction. It is the WHOLE day's move (other news counts too), not the story's
    isolated effect; say so. End-of-day prices: a story from today has no session close yet.

Input parameters:

- `collapse`: Merge near-duplicate stories (same article from many outlets) into one row + `dup_count`. Default ON; pass `false` for the raw un-deduped feed.
- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `country`: OPTIONAL market disambiguator — pass ONLY when `ticker` is a plain NAME that collides across markets (the Thai vs Korean 'KBANK'); omit for a distinctive name or an exact ticker (an unneeded country…
- `direction`: Filter by impact direction: `pos` | `neg` | `ambiguous`. Omit → all.
- `from_`: Lower time bound, ISO date `YYYY-MM-DD`. ⚠️ Ava Advisor NEWS coverage starts 2026-01-01 (nothing before).
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `ticker` (string, required): A Ava Advisor ticker OR a company/asset NAME — the SERVER resolves it (no lookup step). A COMPANY/proper NAME passes AS-IS in any language (茅台/トヨタ/삼성 resolve natively — never translate a name); a gen…
- `to`: Upper time bound, ISO date `YYYY-MM-DD`.
- `window`: News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

### `options_sentiment` (~867 tokens)

Options Sentiment

What the US OPTIONS MARKET is saying — the POSITIONING lens (~547 popular US optionable names,
    stocks + ETFs). Pairs with the news→impact read: for "how is <X> doing?" fetch THIS *and*
    `stock_impact`/`news_feed` and fuse them (news = what's happening + WHY; options = how the market is
    positioned — direction lean via put/call, fear/greed via skew, IV level, dealer-gamma stability,
    max-pain pinning, notable expiries). For a name the user HOLDS it shows how the market is hedging that
    position. Broad-INDEX question → pass the liquid ETF proxy: S&P 500→`SPY`, Nasdaq 100→`QQQ`, Dow→
    `DIA`, Russell 2000→`IWM`, 20y Treasuries→`TLT`, Gold→`GLD`. Tickers = bare US symbol or `SYMBOL.US`
    (`NVDA`/`NVDA.US`); US-only. `style` = `plain` (everyday language, default) | `technical`.

    TWO MODES:
    • SINGLE deep read — pass `ticker=<one>` (+ optional `as_of`). Returns the FULL narrative payload
      (horizons, buckets, per-signal `read`+`because`, `_guide`). Use for a focused "how is NVDA doing".
    • BATCH / COMPARE — pass `tickers=[...]` and/or `dates=[...]` → ONE call returns a COMPACT grid, one
      small row per (ticker × date) cell: `spot`, `positioning_score` ([-1,+1], + bullish), per-horizon
      positioning, and medium-term signal `reads`. THIS is how you answer "NVDA vs AAPL, last week vs
      this week" — do NOT fire the single tool N×M times. `dates=[]` (omit) → a single "latest" column.

    📅 HISTORICAL: `as_of`/`dates` = ISO date/timestamp; the snapshot AT-OR-BEFORE that instant. A bare
    date (`2026-07-15`) is read as END of that day. Every response carries `available_from`/`available_to`
    (the stored window); a cell whose date predates it comes back `covered:false` with the range — relay
    THAT honestly (say history only goes back to `available_from`), never invent an older reading.
    ⚠️ Narrate from `read`+`because` (or the batch `reads`); DON'T recompute, DON'T compare raw O/S or IV
    across assets, `baseline_pendin…

Input parameters:

- `as_of`: As-of date YYYY-MM-DD (point-in-time positioning).
- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `dates`: Specific expiry dates YYYY-MM-DD to focus the read on.
- `style` (string): Narration style: `plain` (layperson, default) | `technical`.
- `ticker`: A US-listed OPTIONABLE ticker OR a plain company name (resolved server-side) — ~547 names — or an index-ETF proxy (S&P→SPY, Nasdaq→QQQ). Non-US / uncovered → `covered:false` (not an error).
- `tickers`: Batch form — several tickers at once (instead of `ticker`).

### `options_scan` (~359 tokens)

Options Scan

Find STOCKS by an options-behaviour pattern (opana lens) across the ~557 US optionable names — returns
    ranked UNDERLYINGS each with a plain-language `because` + `metrics` (value, and prev→delta for a trend/flip).
    STOCK scanner only: it does NOT pick option contracts/strikes/expiries (for one named stock's detail use
    `options_sentiment`). The `pattern` is a key OR plain English (the server resolves it) — its `temporal_mode`
    decides the read (level = now, rising/falling = ~2-week trend, flip = reversal). A `supported:'no'`/`'future'` pattern returns an empty
    list + an honest note (say so, don't substitute). US-capped — state that in the answer.

Input parameters:

- `horizon` (string): `short` | `long` — which options horizon to read (default long = the positioning/conviction lens; short = the gamma/near-term lens).
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `min_strength`: Optional cutoff on the ranked axis / Δ — omit to let the scanner return the top-ranked names.
- `pattern` (string, required): An options-behaviour pattern — an exact key OR plain English ('cheap implied vol', 'crowd getting fearful', 'smart money piling in'); the server resolves it. CSV = AND-combine (intersect), e.g. 'iv_c…

### `theme_players` (~390 tokens)

Theme Players

THE roster tool: investable MEMBER companies of a theme (curated membership). Rolls up sub-themes
    (a parent node returns its children's members too). Use this — not screen_stocks — for 'who are the
    players / real names in <theme>' (screen_stocks is a NEWS-ranked subset gated to news-epicenter members).
    `country='all'` (default) gives the complete cross-market list; an ISO-2 scopes to one trading venue.
    Different from top_entities (news-derived). `limit` = how many (default 20, max 50; big themes have many).
    Returns {stocks, count, total, note?} — if `total` > `count` it's a TOP SLICE: say so, don't present it
    as the full roster (raise `limit`).

Input parameters:

- `country`: `all` (DEFAULT) = the whole cross-market roster — use this for 'who are the players in <theme>'. Or an ISO-2 market to scope to ONE venue. ⚠️ keyed by LISTING VENUE, not domicile: a foreign name list…
- `exposure`: Filter by exposure tier (e.g. `core`). Omit → all members.
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `theme` (string, required): A megatrend theme — name/slug (resolved for you) or node id.

### `private_movers` (~261 tokens)

Private Movers

Off-coverage / private companies the news moved within a theme — the 'beyond tickers' surface.
    `limit` = how many (default 20, max 50). Returns {companies, count, total, note?} — honor `note` when
    `total` > `count` (it's a top slice, not the whole set).

Input parameters:

- `country`: Market filter — CSV of ISO-2 codes (e.g. `US` or `CN,TW,HK`). 🌍 If the question names a NATIONALITY or REGION ('European','Thai','Chinese','ASEAN'), put it HERE — never leave it inside a concept/`q`…
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `theme` (string, required): A megatrend theme — name/slug (resolved for you) or node id.

### `relationships` (~449 tokens)

Company Relationships

Competitors + peers of a company (news-derived relationship graph). `limit` caps EACH list
    (default 15, max 50). Each side carries `total`/`count`/`note` — a big `total` (peers often run to
    hundreds) means you're seeing a TOP slice; say so rather than implying it's the complete set.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `country`: OPTIONAL market disambiguator — pass ONLY when `ticker` is a plain NAME that collides across markets (the Thai vs Korean 'KBANK'); omit for a distinctive name or an exact ticker (an unneeded country…
- `limit`: Max competitors + peers each (default/cap per _lim).
- `ticker` (string, required): A Ava Advisor ticker OR a company/asset NAME — the SERVER resolves it (no lookup step). A COMPANY/proper NAME passes AS-IS in any language (茅台/トヨタ/삼성 resolve natively — never translate a name); a gen…

### `list_themes` (~56 tokens)

List Megatrends

Browse / discover the megatrend taxonomy (25 tier-1 families + sub-nodes) — resolve a theme id.

Input parameters:

- `query`: Optional free-text filter over the megatrend taxonomy; omit → the browsable tree.

### `list_portfolios` (~144 tokens)

List Portfolios

List the user's OWN portfolios (id, name, base_currency, account_type, nav, total_return_pct,
    unrealized_pnl, position_count, …) so you can pick one to analyze. Call this FIRST whenever the user
    says 'my portfolio' without a number — show the names, then pass the chosen `id` to
    `portfolio_context`. Owner-scoped: only ever the user's own portfolios.
    If `count` is 0 (they own none), the response carries a `note` with a create link — relay THAT
    (invite them to create a portfolio) instead of saying an empty 'you have no portfolios'.

### `portfolio_context` (~915 tokens)

Portfolio Context

An LLM-ready snapshot of ONE of the user's OWN portfolios (owner-scoped) — analyze it directly.
    NO window → default: `meta` · `summary` · a `lifetime`(all-time) + `recent`(~12mo) block, EACH with
    `performance` (return/cagr/sharpe/sortino/calmar/drawdown/vol/win_rate) + `attribution` · `positions`
    · `closed_positions` (realized_pnl) · `composition` (point-in-time holdings) · `allocation` ·
    `concentration` (HHI) · `inferred_behavior` · `flags`. `portfolio_id` from `list_portfolios`; 404 if
    not the user's.

    TIME WINDOW — `from_`/`to` (ISO) or `window` (`7d|30d|90d|180d|1y|mtd|qtd|ytd`): REPLACES lifetime+
    recent with ONE `window` block (that span's `performance` + `attribution` + `nav_trend`) and scopes
    `composition` to match. So ANY period's return + drivers is answerable. `snapshots` = composition
    granularity only (`year|quarter|month|week|day|off`).
    🔴 MANDATORY for period questions: the default / `lifetime` / `recent` blocks DO NOT contain the
    performance or attribution of an arbitrary period (e.g. Q1-2025, "H1 2024"). To answer ANY specific
    period — or to COMPARE periods (Q1/25 vs Q1/26, 2023 vs 2025) — you MUST call this tool AGAIN with
    `from_`/`to` (or `window`) for EACH period, then compare the returned `window` blocks. NEVER derive a
    period's return/sharpe/drawdown/attribution from the default view — those numbers aren't in it; making
    them up is a hard error. If you haven't fetched a period's window, say you need to fetch it, don't guess.

    HOW TO ANALYZE (research-analyst framing — see avaadvisor://policy):
    • Lead with the sharpest thing: a non-empty `flag`, or the biggest concentration / drawdown / tilt.
    • "What drove the return / drawdown / strengths & weaknesses" (for the default OR a window) → read
      `attribution.contributors[]` (per-holding `pnl_contribution` + `pct_of_nav_change` + `held` window;
      reconciles to `nav_change` to the cent, INCLUDES since-sold names). Don't est…

Input parameters:

- `from_`: Window start YYYY-MM-DD — re-scopes performance/attribution/composition together.
- `portfolio_id` (integer, required): The portfolio's id (call list_portfolios first if the user says 'my portfolio' without a number).
- `snapshots`: Point-in-time composition cadence: `year|quarter|month|week|day|off` (default quarter); auto-coarsens over long spans.
- `to`: Window end YYYY-MM-DD.
- `window`: Re-scope perf+attribution+composition to a period: `7d`/…/`ytd`. Omit → lifetime + recent(12mo).

### `write_note` (~1350 tokens)

Save Note

🔴 WRITE — save a NOTE to the user's account (this PERSISTS data; it is NOT a read/lookup). Typical
    flow: FIRST give the user your complete answer as usual, THEN — as the final step of the turn — call
    `write_note` once to keep it.

    🔴 IF YOUR ANSWER CONTAINED A TABLE / NUMERIC COMPARISON, keep it as a MARKDOWN table in `body` — lead with
    the table, do NOT re-narrate the numbers into prose. Saving a figures answer as a wall of prose is the #1
    note-quality failure; preserving structure OUTRANKS "distilling into a paragraph". (The figures are extracted
    from these markdown tables later for charts — so a clean table with clear headers is what makes that possible.)

    CONTENT: `subject` (short title), `body` (MARKDOWN — keep tables as tables, absolute headers like `FY2025`),
    `summary` (1–2 sentences), `note_type` (reference/tracking/thesis/decision), `category`, `tags` — see each field.

    ENTITY LINKS make the note findable + joinable to the graph — fill whenever the note touches specific things;
    the server RESOLVES plain names for you. `stocks` (the subjects) · `mentioned_stocks` (referenced) · `gics`
    (sector/theme, code or plain English) · `megatrend_ids` (advanced raw id) · `portfolio_id`.

    🧭 LINK THE NOTE'S HOME — the theme/sector, not just the stocks. If the note is about a TREND/tech/mechanism
    ("what is HBM", "solid-state batteries") or an established INDUSTRY/SECTOR ("retail", "airlines", "pharma"),
    put the word(s) straight in `gics` (plain English — the server resolves each and routes a theme→megatrend).
    A note whose subject is a trend or a sector, saved with EMPTY `gics`, means you SKIPPED this. The only correct
    empties: a single-stock note (stocks only) or a general concept with no home (P/E, EBITDA — don't force it;
    tags/body still make it findable by semantic search).

    WHEN TO SAVE — this is the investor's knowledge base; CAPTURE substantive investment content generously
    (reference/unde…

Input parameters:

- `agent`: Which app is writing the note — EXACTLY one of: `Claude` | `Claude Code` | `Claude Coworks` | `ChatGPT` | `Codex` | `Gemini` | `Other` (case-sensitive); the server falls back to the connection's clie…
- `body` (string, required): The note's full text in MARKDOWN — the distilled answer/observation/thesis to persist. PRESERVE the structure of your answer: any numeric / tabular data goes in a markdown TABLE (pipe syntax `| col |…
- `category`: Optional free-text category.
- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `gics`: The note's INDUSTRY/SECTOR or THEME — a GICS code OR plain English ('banks', 'semiconductors', 'AI'); the server resolves each and routes a curated theme to a megatrend link. (Derived free if the not…
- `megatrend_ids`: ADVANCED — raw megatrend node id(s) if you already hold one (e.g. a theme tool's `megatrend.id`). Normally just name the theme in `gics` and the server routes it to a megatrend.
- `mentioned_stocks`: Secondary tickers merely referenced (a peer named in passing).
- `note_type`: `reference` (concept/understanding) | `tracking` (dated market read) | `thesis` | `decision`.
- `portfolio_id`: Link the note to one of the user's portfolios, if relevant.
- `stocks`: PRIMARY stocks/assets the note is ABOUT — an exact Ava Advisor ticker OR a plain NAME the SERVER resolves (any asset class; an ambiguous name → reconfirm). ⚠️ A COMMODITY discussed via the trade tool…
- `subject` (string, required): Short title / subject line of the note.
- `summary`: One-line summary (shown when the note is collapsed).
- `tags`: Free-text tags for retrieval.

### `query_notes` (~686 tokens)

My Notes

Recall the USER'S OWN saved notes — their personal investment knowledge base (owner-scoped, only
    ever their notes). Two combinable ways:
      • SEMANTIC recall via `q` — natural language ("what did I say about foundry manufacturing?"); results
        are ranked by MEANING with a `similarity` score (cross-language OK).
      • Structured filters: `stock` (a ticker → their notes about it), `theme` (a sector/trend NAME →
        resolved to the megatrend, subtree included), `gics` (6-digit code), `tag`, `note_type`
        (reference/tracking/thesis/decision), `since` (e.g. '30d').
    📌 `stock` + `relation` (direct|indirect|any, default any) splits how a note relates to that ticker —
    same idea as newsfeed direct/indirect: `direct` = the note is ABOUT it (a subject); `indirect` = it's
    only REFERENCED (e.g. a peer named in a note about ANOTHER stock — a "NVDA vs peers" note surfaces
    under AMD as indirect). Every returned note carries a `relation` label when you filter by `stock`, so
    you can say "1 note about AMD + 1 that only mentions it". Use `relation="direct"` for "notes really
    about X".
    Returns note SUMMARIES + linked entities + `similarity` — NOT the full body (call `get_note(id)` for
    that). `limit` default 10 (max 50).
    🔴 FUSE personal + live: when the user asks about something they've likely noted, pair this with the
    live read — e.g. `pulse(kind='asset', target=NVDA)` AND "your NVDA thesis from last week said …". That personal-
    knowledge + live-graph combination is the whole point of the notes layer.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `gics`: GICS code filter.
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `note_type`: Filter by type (reference/tracking/thesis/decision).
- `q`: Semantic query text — recall notes by MEANING (cross-language).
- `relation`: With `stock=`: `direct` (note ABOUT it) | `indirect` (merely referenced) | `any` (default).
- `since`: Only notes since this date/window (e.g. `30d` or YYYY-MM-DD).
- `stock`: Filter to notes about a ticker (name/ticker → resolved).
- `tag`: Tag filter.
- `theme`: Filter to a theme (name → megatrend, incl. subtree rollup).

### `get_note` (~72 tokens)

Read Note

The FULL saved note (including its `body`) by id — owner-scoped. Use after `query_notes` when you
    need the complete content, not just the summary.

Input parameters:

- `note_id` (integer, required): The note's id (from query_notes results). Owner-scoped → 404 if not yours.

### `list_playlists` (~132 tokens)

List Playlists

List the user's OWN feed playlists (id, name, emoji, item_count, items[{kind,ref_id,label}]).
    🔴 Call this FIRST whenever the user refers to a playlist BY NAME ("add X to My Tech List") — you
    match the (possibly mistyped / mis-spaced) name against the REAL names yourself. If the user didn't
    say WHICH and they own more than one, ASK which one (show the names). If they own NONE, offer to
    create one. Owner-scoped — only ever the user's own playlists. A playlist drives their news Feed.

### `create_playlist` (~94 tokens)

Create Playlist

🔴 WRITE — create a new feed playlist (owner-scoped). Do NOT auto-create from a possible typo:
    call `list_playlists` FIRST and only create when the name genuinely doesn't exist, or the user
    confirms a new one. Returns the created playlist {id, name, …}.

Input parameters:

- `emoji`: Optional emoji icon for the playlist.
- `name` (string, required): The new playlist's display name.

### `add_to_playlist` (~327 tokens)

Add to Playlist

🔴 WRITE — add one or more STOCKS/assets to a playlist (batch, idempotent). Each entry may be an exact
    Ava Advisor ticker OR a name/symbol the server resolves (any asset class: stock/ETF/commodity/crypto/FX). An
    ambiguous name (e.g. same name across markets) returns a `needs_confirmation` reconfirm — pick the exact ticker
    and re-call. `playlist_id` from `list_playlists`. Re-adding an existing ticker is a harmless no-op. Returns
    `{added, skipped, item_count}` — ⚠️ RELAY any `skipped` to the user; never drop it silently.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `playlist_id` (integer, required): The playlist's id (from list_playlists).
- `tickers` (array, required): Stocks to add — an EXACT Ava Advisor ticker (`AAPL.US`, `BTC-USD.CC`) OR a plain NAME/symbol ('Apple', 'ซัมซุง', 'btcusd') which the SERVER resolves for you (any asset class). An ambiguous/same-name-…

### `remove_from_playlist` (~100 tokens)

Remove from Playlist

🔴 WRITE — remove one or more stocks (by ticker) from a playlist (batch). `playlist_id` from
    `list_playlists`. Returns `{removed, not_found, item_count}` — relay `not_found` (a ticker that
    wasn't in the playlist) to the user.

Input parameters:

- `playlist_id` (integer, required): The playlist's id.
- `tickers` (array, required): Ava Advisor tickers to remove from the playlist.

### `stock_prices` (~926 tokens)

Stock Prices

Price context for a tradable ticker (stock / ETF / index-ETF / forex / crypto / commodity), split &
    dividend-ADJUSTED — a DIGESTED read, NOT a raw bar series: windowed changes (1w/1mo/3mo/ytd/1y), 52-week
    range + `drawdown_from_52w_high_pct` (how far below the peak), realized vol + `realized_vol_percentile_1y`
    (is today's vol high vs its OWN year), trend vs SMA50/200, volume conviction (`up_down_volume_ratio_1mo`,
    rvol). `*_read` fields are ready plain-language labels — quote them, don't re-derive. Reach for this on
    "is it cheap/extended / how has it moved / why is it dropping" — the LEVEL that makes a news+options read
    actionable (or use `pulse(kind='asset')` to get price + news + options in one). `to` = as-of date (point-in-time,
    YYYY-MM-DD, features as of that day); `from_` bounds history (narrowing below ~1y nulls the long windows).
    For a SECTOR/theme (not one ticker) use `pulse(kind='theme')`, not this. 🔵 BONDS/RATES: if `metric_kind` ==
    "yield" (a `.GB` govt-bond yield like US-10Y.GB or a `.MM` rate like SOFR.MM) the stored value is a
    LEVEL, not a price — narrate each window's `change_bps` in BASIS POINTS, NOT `change_pct` (a % of a
    yield is sign-inverted + the wrong unit; e.g. US-10Y 1y = "+52 bps", not "+12%"). Bonds also carry
    per-window `price_proxy_pct` + top-level `mod_duration` = an L1 bond-PRICE estimate (≈ −ModDur×Δy) for
    "the bond fell ~4%" narration (label it an ESTIMATE; for an exact bond return point to a bond ETF like
    TLT/IEF). Volume fields (`rvol`, `up_down_volume_ratio_1mo`, …) are `null` for a yield — don't present
    volume conviction; and yield↑ ⇒ bond price↓.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `country`: OPTIONAL market disambiguator — pass ONLY when `ticker` is a plain NAME that collides across markets (the Thai vs Korean 'KBANK'); omit for a distinctive name or an exact ticker (an unneeded country…
- `from_`: Lower bound of price history `YYYY-MM-DD`. Narrowing below ~1y nulls the long windows. Price history goes back DECADES (unlike news, 2026+).
- `ticker` (string, required): A Ava Advisor ticker OR a company/asset NAME — the SERVER resolves it (no lookup step). A COMPANY/proper NAME passes AS-IS in any language (茅台/トヨタ/삼성 resolve natively — never translate a name); a gen…
- `to`: As-of date `YYYY-MM-DD` — features computed as of that day (point-in-time). Omit → latest.

### `latest_quote` (~262 tokens)

Latest Quote (US, delayed)

The LATEST TRADED PRICE today for US stocks / ETFs — a DELAYED intraday quote (typically ~15 minutes behind),
    with today's change vs the previous close. Use it when the user asks about TODAY during the US session ("why is
    UBER down today", "where is NVDA trading"): every other price tool is END-OF-DAY (last close). US listings only —
    any other market returns `not_covered` (use stock_prices). Pair the move with today's news (stock_impact /
    search_news) for the why. State the quote time and that it is delayed; it is not a live tick.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `tickers` (required): 1–10 US tickers or company NAMES (e.g. `UBER.US`, `Uber`, `AAPL`) — names are resolved for you.

### `etf_profile` (~430 tokens)

ETF Profile

What a US ETF / fund HOLDS: top holdings with % of NAV, sector (GICS) and country weights, plus the fund facts
    — AUM, expense ratio, benchmark / index or active, holdings count, top-10 concentration, tracking difference
    (SEC N-PORT / N-CEN filings; `as_of` dates say how fresh). Use it for "what does SCHD hold", "how concentrated is
    QQQ", "SPY vs VOO fees", "sector mix of XLE". ETFs rarely have news of their own — for "why is it moving" pair
    this with stock_impact / pulse on the top holdings. Non-fund tickers → `not_a_fund`.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `ticker` (string, required): A Ava Advisor ticker OR a company/asset NAME — the SERVER resolves it (no lookup step). A COMPANY/proper NAME passes AS-IS in any language (茅台/トヨタ/삼성 resolve natively — never translate a name); a gen…
- `top`: How many top holdings to list (default 15, max 50).

### `price_series` (~719 tokens)

Price Series

A SMALL, bounded price SERIES for drawing a chart (a device screen, a sparkline) plus headline numbers —
    the counterpart of `stock_prices`, which is a digested read with no series. Returns ticker, name, metric_kind
    (`yield` = a bond yield / rate: levels in %, moves in bps via period_change_bps / change_bps_by_period), currency,
    range, interval (`day`|`week`|`month`), period_start_date / period_end_date, last_close, period_change_pct,
    period_high / period_low (+ their dates), last_volume, average_daily_volume, change_pct_by_period
    {1w, 1mo, 3mo, ytd, 1y}, and `series` {dates, closes[, volumes]} as parallel arrays (≤ 65 points). EOD daily
    data, split/dividend-adjusted closes — the last point is the LAST CLOSE, not an intraday quote. Weekly/monthly
    points are each period's last close. Use this when a chart or a few chart numbers are needed; for "is it
    cheap / extended / why is it moving" use `stock_prices` or `pulse(kind='asset')`.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `country`: OPTIONAL market disambiguator — pass ONLY when `ticker` is a plain NAME that collides across markets (the Thai vs Korean 'KBANK'); omit for a distinctive name or an exact ticker (an unneeded country…
- `include_volume`: Add `series.volumes` (summed per week/month). Default false — closes only.
- `range`: Chart window. `1w`|`1mo`|`3mo` → daily points; `6mo`|`1y` → weekly; `3y`|`5y` → monthly; `10y` → 2-month; `max` = full history (1–12-month points). Default `1mo`. Never more than 65 points.
- `ticker` (string, required): A Ava Advisor ticker OR a company/asset NAME — the SERVER resolves it (no lookup step). A COMPANY/proper NAME passes AS-IS in any language (茅台/トヨタ/삼성 resolve natively — never translate a name); a gen…

### `stock_prices_batch` (~307 tokens)

Batch Stock Prices

The same digested price context for UP TO 50 tickers in ONE call — a watchlist / cohort snapshot
    ("which of these names are most extended, or deepest in drawdown"). Returns `results` (in input order)
    + `unresolved` (unknown / no-price-history tickers). `to`/`from_` as in `stock_prices`.

Input parameters:

- `chart_range`: Leave unset. For apps/devices that draw charts themselves: adds `chart` (≤ 65 points) to the first 5 results.
- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `from_`: Lower bound of price history `YYYY-MM-DD` (below ~1y nulls the long windows).
- `tickers` (array, required): UP TO 50 items, EACH a Ava Advisor ticker OR a plain company/asset NAME — the SERVER resolves names (pass `context` to disambiguate); a watchlist/cohort. Returns `results` in input order + `unresolve…
- `to`: As-of date `YYYY-MM-DD` (point-in-time). Omit → latest.

### `positioning` (~444 tokens)

Futures Positioning (COT)

⭐ How the FUTURES market is POSITIONED — the CFTC Commitment of Traders lens for commodities, FX,
    rates and equity indices (the non-equity TWIN of options_sentiment; the two together cover positioning
    for every asset class). Answers 'is this trade crowded?', 'is the smart money leaning the other way?',
    'is the good news already priced into positioning?'. Returns: `crowding` (the speculative crowd at a
    3-year extreme = a contrarian RISK, NOT a timing call), `smart_vs_crowd` (are commercial hedgers — who
    know the physical/fundamental side — leaning against the crowd), `momentum` (building or unwinding; a
    flip = regime change), `fragility` (a few big traders holding it = reverses fast), and ⭐
    `news_vs_positioning` (does recent news CONFIRM the crowd → priced-in, or CONTRADICT a crowded position →
    unwind risk). Weekly, as of the prior TUESDAY. For a RATE/YIELD asset (`.GB`/`.MM`) a long futures =
    positioned for LOWER yields (the reads already say it that way). 🗣 Every feature carries a PLAIN `read`
    — narrate it in EVERYDAY language for a beginner (no 'net'/'percentile'/'basis' jargon); say what it
    MEANS for risk. Facts, not advice — the verdict is yours. A stock / uncovered asset → `__notfound`: say
    futures positioning doesn't apply and use options_sentiment / the news read instead.

Input parameters:

- `q` (string, required): A COMMODITY / FX / RATES / INDEX to read FUTURES positioning for — a concept IN ENGLISH (oil, gold, copper, natural gas, US 10Y treasury, euro, S&P 500; translate first) or a Ava Advisor ticker (WTI.…

### `cot_extremes` (~280 tokens)

CFTC / COT Futures Extremes

⭐ FUTURES / CFTC-COT speculative positioning extremes — which commodity / FX / rate / equity-INDEX
    FUTURES have the CROWD at a 3-year extreme right now (NOT single-stock equity options → for 'stretched
    put/call' or crowded STOCK names use options_scan). The discovery scan across every tracked
    futures market at once. COT / FUTURES lens ONLY. Surfaces stretched positioning (≥90th or ≤10th
    percentile of its own 3y history) that could unwind hard on a shock — a contrarian-RISK map, NOT buy/sell
    calls (an extreme can persist). Use for 'where is FUTURES positioning most crowded / stretched right now?'.
    🔴 WRONG TOOL for single-STOCK options crowding — 'stretched put/call', 'one-sided / crowded equity names',
    'most extreme options positioning across stocks': for those use options_scan (pattern='crowded / one-sided' —
    the equity-options opana lens across ~557 US optionable names). Narrate each `read` plainly.

Input parameters:

- `asset_class`: Filter: `commodity` | `fx` | `rates` | `equity_index`. Omit = all.
- `limit`: Max markets (default 15, max 50).

### `financials` (~1198 tokens)

Financials

⭐ Company FINANCIAL STATEMENTS — income / balance / cash-flow + auto-detected abnormality signals. Read ONE
    company or COMPARE up to 8 (revenue, growth, margins, ROE, FCF…), on a clean normalized feed uniform across every
    industry (banks, insurers, REITs).
    🔴 To compare SEVERAL, pass them ALL in ONE call (tickers='TSLA.US,MSFT.US') — a single call aligns them on a
    common basis+currency and costs a fraction of N calls. Pick ONE `period` (quarterly already carries YoY).
    🎚 `fields`: leave EMPTY for the DIGEST (small default — headline + ratios + capital-return + signals; covers most
    compares); set it for specific line items, a whole statement ('income'|'balance'|'cashflow'), or 'all'.
    ⏱ `period` = the window (5y / 2022 / 2022-2023 / 5q / 2024Q2), mapped to each fiscal year. 🌐 currency=USD (auto for
    multi-company) converts totals at each period's date. 🗣 The digest carries a plain `read` (facts, not advice) and may
    carry `_notes` (per-period comparability flags — the warning is FACT, each `likely_causes` is an inferred lead to VERIFY).
    📏 LIMITS: ≤8 companies · ≤20 fields · ~4–5y history. A non-equity/unlisted entry → `ok:false`.
    🔴 pulse(kind='asset') on a stock ALREADY embeds this digest — call financials only for a dedicated read/compare or a
    specific fields/statement pull, not right after pulse(kind='asset').

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candidate each `ti…
- `currency`: Convert ABSOLUTE totals to this currency (e.g. USD) at each period's date so cross-currency companies compare — margins/growth are currency-neutral anyway. A multi-company compare defaults to USD.
- `fields`: OPTIONAL — the granularity dial. LEAVE EMPTY for the DIGEST (headline + ratios ROE/ROA/margins/debt/current/quick + capital-return dividends/buybacks + abnormality signals) — the safe default that al…
- `period`: OPTIONAL time selector, mapped to each company's FISCAL year. Forms: '5' or '5y' = last 5 years (default 5) · '2022' = that fiscal year · '2022-2023' = a range · '2020,2022' = specific years · '5q' =…
- `tickers` (required): 1–8 comma-separated COMMON-STOCK companies to read/compare financial statements for. EACH entry can be EITHER an exact Ava Advisor ticker ('AAPL.US', '2330.TW') — used directly — OR a bare symbol / c…

### `screen_unified` (~2129 tokens)

Unified Screener (Universe × Fundamental × Technical)

EXECUTE a unified screen = universe ∩ fundamental ∩ technical ∩ options (any leg optional; each grammar resolved
    server-side — key or plain English). Returns {universe, count, sort, executed_criteria (the resolved request that ran — save/re-run it verbatim), results:[{head_listing_id, ticker, name, score,
    matched_legs, matched:{ta, fundamental:{<metric>:{value, basis, window?, series?, periods?}}}, context}], notes}.
    Evidence keys == the leg name you sent (TA→matched.ta, fundamentals→matched.fundamental, NOT technical/financial);
    `matched_legs` lists which leg(s) a row passed. A thin intersection adds partial:true + per-leg near-misses — never
    present a partial/one-leg row as a full match; read `notes` (names the tighter leg + how to broaden).
    Time windows are PER-LEG: TA 'within last N bars' = top-level `window_bars`; a fundamental trend's span = that
    condition's `N`. Options leg is US-optionable only (~557 → US-capped); sort='options' ranks by it; an
    options-vs-price divergence = just send the phrase in `options`. FAILS LOUD: an unsupported pattern/operand/concept
    returns a 400, so count:0 with NO error = a VALID query that matched zero now (loosen / widen window_bars, don't say
    'can't do X'); `notes` may say 'insufficient history' (not a no-match) or which basis was screened. Over-fetches a
    ~4× buffer (cap 100) so 'show me more' is served from these rows — don't re-call.

Input parameters:

- `asset_type`: OPTIONAL asset type(s), OR'd: 'Common Stock','ETF','Crypto','Currency','Commodity','Bond','Index','Fund','ADR','REIT'. Crypto≠Currency (forex); gold/silver=Commodity. Omit = all (a company screen usu…
- `count_total`: Set true ONLY when the user asks HOW MANY match ('how many stocks…', 'is it more than 500?'): returns the exact `total` up to 500, else `total_over: 500`. Slower (runs every leg in full) — omit for a…
- `country`: OPTIONAL operating-country scope — one or MORE ISO-2 codes, OR'd (a stock matches if in ANY of them). e.g. ['US'] · ['CN','US'] for China+US · ['TH','SG','MY']. Omit = all countries.
- `criteria`: A WHOLE formula in the saved shape — the `executed_criteria` a screen_unified call returned, or the user's saved formula ({universe:{include:[{country,gics,size,theme,asset_type,mcap_min,mcap_max}],…
- `dividend_min_cagr`: OPTIONAL dividend gate — 5-year dividend CAGR ≥ this % (5 = ≥5%/yr). Needs a fundamental/ta/options base leg too.
- `dividend_min_streak_years`: OPTIONAL dividend gate — keep stocks with a no-cut dividend streak ≥ N years (reliability streak in a 10-year window, capped at 10; NOT the full age). A membership gate — combine with a fundamental/t…
- `exclude_country`: OPTIONAL — EXCLUDE operating-country(ies), ISO-2. 'global ex-US' = exclude_country=['US']. Universe-level, applies to every leg.
- `exclude_gics`: OPTIONAL — EXCLUDE industry/theme CONCEPT(s), CSV, codes or plain English ('banks','AI'); server-resolved & routed same as `gics`. Applies to EVERY leg ('high-yield but NOT banks' = fundamental divid…
- `exclude_theme`: ADVANCED raw-passthrough — EXCLUDE megatrend THEME node_id(s). Normally just name the theme to exclude in `exclude_gics` ('not AI'); the server routes it. Universe-level negation across every leg.
- `fundamental`: The FUNDAMENTAL leg — AND-ed conditions (each = a METRIC `concept` + a SHAPE `pattern` + its value; key or plain English, server-resolved). e.g. roe>20% & 3y revenue growth → [{concept:'roe',pattern:…
- `gics`: OPTIONAL universe SCOPE — industry/theme concept(s), CSV of ATOMIC concepts (decompose 'banks and insurance' → 'banks,insurance'). Each = English ('banks','semiconductors','AI') or a GICS code prefix…
- `limit`: How many stocks to SHOW (default 10). Over-fetches a ~4× buffer (capped 100) so 'show me a few more' is served from THIS result — don't re-screen; re-screen only to exceed the buffer.
- `max_market_cap_usd`: OPTIONAL ABSOLUTE max market cap USD (2000000000 = under $2bn). Pair with min for a band.
- `min_market_cap_usd`: OPTIONAL ABSOLUTE min market cap USD (50000000000 = $50bn). Use this (not `size`) for a USD floor / 'under $X' band.
- `mode`: What to do with the formula. 'run' (default) = screen and return the stocks. 'check' = NO scan, no market data: resolve every field exactly as a run does and validate the formula (rules only, fast) →…
- `options`: The OPTIONS leg — an options-behaviour term, key or plain English ('fear_building','iv_cheap','the crowd getting brave'), server-resolved. Intersects the ~557 US-optionable names showing it; an optio…
- `options_horizon`: Options horizon: 'long' (default, positioning/conviction) or 'short' (gamma/near-term). Only meaningful with `options`.
- `size`: OPTIONAL market-cap size tier(s), OR'd — 'large'|'mid'|'small'|'micro'. RELATIVE per-market MSCI tiers ('small' = small FOR ITS market, not in USD; no separate 'mega'). For an ABSOLUTE USD size / 'un…
- `sort`: Rank key: 'ta' (default, TA chain score) · 'options' (use when `options` present) · 'mcap' · a TA-context oscillator ('rsi'/'adx' — 'most overbought'→'rsi') · or any fundamental metric key in the res…
- `ta`: The TECHNICAL leg — a THEN chain of steps (usually ONE). Each signal = `pattern` (SHAPE) + operands `a`/`b` (LINES), key or plain English, server-resolved. e.g. golden cross + volume spike → [{anchor…
- `theme`: ADVANCED raw-passthrough — megatrend THEME node_id(s), OR'd (core member of ANY). Normally OMIT: name the theme in `gics` ('AI') and the server routes it. Use only with a known node_id.
- `timeframe`: Chart for the TA leg: 1=daily (default) · 2=weekly · 3=monthly. TA operand periods & for_bars are counted in BARS of this timeframe.
- `window_bars`: TA-leg LOOKBACK in bars of `timeframe` — how far back a signal may have fired / the span a THEN-chain completes within ('…within the last N days'; 'divergence within 50 days' → 50). Whole `ta` leg; o…

### `screen_stocks` (~969 tokens)

Screen Stocks

⭐ The cohort SCREENER: "which stocks in <a group> are interesting / winning / losing / most-talked-about,
    and how cheap or expensive do they trade?" Ranks the companies in a scope by how news is hitting them (lead with
    the winners-vs-losers split), and EVERY row carries its VALUATION (P/E, P/B, dividend yield, 52w) — so this is
    also the tool for "which in <group> are cheap / worth investing" (pulse(kind='theme')/brief are news-only, no valuation —
    pull P/E from here; P/B leads for banks/insurers).
    ⚠️ Rows are a NEWS-RANKED, CAPPED SUBSET, not the full cohort — do NOT compute a sector/peer AVERAGE from them
    (biased sample). For "cheaper/richer than the sector average / below-above the group / undervalued vs peers" use
    screen_unified with a `below_average`/`above_average` pattern (proper cap-weighted, outlier-cleaned benchmark).
    Scope ≥1 REQUIRED (never whole-universe): megatrend / gics / country — combine freely.
    Each row = {symbol, name, country, gic_code, market_cap_usd, impact:{news_count, pos, neg, ambiguous,
    net_direction, top_relevance, aspects, top_reason}, fundamentals:{pe_ratio, pb_ratio, dividend_yield_pct,
    week52_high, week52_low}}; `direction_split` pre-tallies winners/losers. ⚠️ per-stock impact scoring exists only
    from ~2026-07-03 — an earlier window returns empty (say so, not "nothing happened"). One ticker → pulse(kind='asset');
    a group's overall pulse → pulse(kind='theme'); a sector-average benchmark → screen_unified.

Input parameters:

- `aspect`: Impact CHANNEL filter (e.g. `demand`, `competition`, `tariff`, `monetary`). Omit → all channels.
- `country`: Market filter — CSV of ISO-2 codes (e.g. `US` or `CN,TW,HK`). 🌍 If the question names a NATIONALITY or REGION ('European','Thai','Chinese','ASEAN'), put it HERE — never leave it inside a concept/`q`…
- `direction`: `pos` → winners only · `neg` → losers/at-risk only · omit → all.
- `from_`: Start date YYYY-MM-DD. ⚠️ per-stock impact scoring only exists from ~2026-07-03 (earlier → empty).
- `gate`: megatrend scope only: `both` (default, strict member AND epicenter) | `membership` (looser).
- `gics`: A GICS sector/industry — a CODE PREFIX (sector `25` / group `2550` / industry `255010` / sub `25501010`, CSV for several) OR plain English ('banks', 'semiconductors', 'biotech'); the server resolves…
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `megatrend`: A megatrend node — a name/slug (resolved for you, e.g. `foundry`) or an int node id. CSV for several.
- `min_impact`: Min article importance, 1–5.
- `min_market_cap_usd`: Min market cap, USD.
- `min_relevance`: Min centrality to its news, 0–1.
- `order_by`: `news_count` (default, most attention) | `relevance` | `market_cap`.
- `to`: Upper time bound, ISO date `YYYY-MM-DD`.
- `window`: News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

### `screen_dividends` (~988 tokens)

Screen Dividends

💰 THE income screener — "which stocks pay a high / reliable / growing DIVIDEND?" Ranks the DIVIDEND-PAYING
    universe (all payers, not just news-covered) and hands you the raw pieces to tell a real income name from a YIELD
    TRAP (don't trust a headline yield).
    🔴 A multi-metric ask that also needs P/E / financial-health (dividend AND low P/E AND healthy) belongs in
    screen_unified (a `fundamental` leg + `dividend_min_streak_years`/`dividend_min_cagr` gate). THIS tool is the
    dividend specialist (no P/E filter) but it both INCLUDES (`gics`) and EXCLUDES (`exclude_gics`) a sector.
    Scope (country/gics) is OPTIONAL — omit both for a fast whole-market rank.
    🔴 `no_cut_streak_yrs` is a bounded RELIABILITY signal, capped at 10 (clean across the tracked decade incl. 2020/
    2022 stress) — NOT the dividend's full age; never state a multi-decade "aristocrat/king" streak, say "clean 10y+".
    Each row's `dividend` block decomposes the yield: `yield_pct` (forward/sustainable — quote this), `yield_trailing_pct`
    (>> yield_pct ⇒ a special inflated it), `payout_ratio` (>1 = unsustainable), `ttm_div_yoy_pct`, `no_cut_streak_yrs`,
    `last_cut_year`, `cagr_5y_pct`, plus `week52_high/low` + `pe_ratio`/`pb_ratio`/`eps` + a `news` block. 🔴 Never rank on
    yield alone: high yield + recent `last_cut_year` + negative yoy + high payout + bad news = TRAP; high yield from a
    price drop + intact/growing dividend + long streak = possible VALUE. Read the payload's `_guide`. limit default 15 (max 50).

Input parameters:

- `country`: Market filter — CSV of ISO-2 codes (e.g. `US` or `CN,TW,HK`). 🌍 If the question names a NATIONALITY or REGION ('European','Thai','Chinese','ASEAN'), put it HERE — never leave it inside a concept/`q`…
- `exclude_gics`: OPTIONAL — EXCLUDE a sector/industry from the screen (GICS code prefix e.g. '4010', OR plain English 'banks' — the server resolves the name). 'high-yield stocks but NOT banks' = exclude_gics='banks'.…
- `gics`: A GICS sector/industry — a CODE PREFIX (sector `25` / group `2550` / industry `255010` / sub `25501010`, CSV for several) OR plain English ('banks', 'semiconductors', 'biotech'); the server resolves…
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
- `max_market_cap_usd`: Max market cap, USD.
- `max_payout`: Max payout ratio — 'high yield but payout NOT stretched'. Fraction (0.7) or percent (70).
- `max_yield`: Max yield % — guards against trap-tier yields.
- `min_cagr`: Min 5-year dividend CAGR, %.
- `min_market_cap_usd`: Min market cap, USD.
- `min_streak_years`: Min no-cut streak years (0–10; caps at 10 = clean across the whole tracked decade). HIGHER = more reliable. A low bar lets a name that CUT recently through — it may have only rebuilt a short streak s…
- `min_yield`: Min dividend yield in PERCENT (3 = 3%).
- `order_by`: `yield` (default) | `streak` | `cagr`.

### `trade` (~539 tokens)

Trade Flows & Rankings

International TRADE STATISTICS — countries' import/export flows, partners, rankings and balances from UN Comtrade
    (official customs data). NOT securities trading: it never places, routes or executes an order. Pick `mode`; each mode reads a subset of the params (see each param's note).

Input parameters:

- `codes`: Product: HS code(s) OR a plain-English product ('copper','cars'), server-resolved. REQUIRED for flows/top_partners/top_traders; omit for balance → TOTAL (all goods).
- `context`: OPTIONAL but RECOMMENDED — the user's FULL request VERBATIM (any language). Used to pick the right code + SUPPLY STAGE (ore vs concentrate vs refined) and leaf-vs-family granularity for a `codes` con…
- `flow`: export/import/both. Defaults: flows/top_partners=export, top_traders=import.
- `freq`: annual (default) | monthly (YYYYMM, goods only). flows only.
- `limit`: top_partners/top_traders: top-N (default 10, max 50).
- `min_value_usd`: top_traders only: floor to drop tiny-base noise.
- `mirror`: Also return the partner-reported figure + discrepancy (China esp.). flows only, goods.
- `mode` (string, required): flows = one country's trade of a product over time · top_partners = a country's biggest trading partners for a product · top_traders = rank COUNTRIES by trade of a product (world/region) · balance =…
- `order`: top_traders only: desc (default) / asc; for streak = run direction.
- `partner`: Partner country, or 'World' (default). flows/balance only.
- `period`: Year '2023' / list '2020,2021' / range '2015:2024' / 'lastN' / 'latest'. DYNAMIC — never hardcode. Defaults vary by mode.
- `rank_by`: top_traders only: value (default) / growth (CAGR) / streak.
- `reporter`: Reporting country — name/ISO/M49 ('Thailand'/'THA'/'764'), server-resolved. REQUIRED for flows/top_partners/balance.
- `scope`: top_traders only: world (default) / continent / subregion / econ group (asean/eu/g7) / CSV ISO-2.
- `type`: goods (default, HS) | services (EBOPS, value-only). flows/top_partners.

### `fred_series` (~682 tokens)

Macro Series + Analysis (FRED)

"What is <macro indicator> / is it high vs history / how has it moved" — ONE FRED series, feature-extracted.
    Pass a macro CONCEPT (the server resolves it to the canonical series_id + the right transform) or an exact id.
    Returns `series` (transformed points) + an `analysis` block: `latest` (+date — always say as-of-when), `trend`,
    `change` (vs prior/YoY/window), `peak`/`trough`, and 🔑 `percentile`+`z_score` vs the window's own history (the
    money-shot for "high or low?" — e.g. unemployment 8th pct = historically very low), `volatility`, a one-line
    `read`. 🔵 `transform` matters and is auto-picked from the resolved series ("inflation" = pc1 YoY % of a price
    index, a rate = lin) — override only deliberately. QUOTE the `read`; narrate the percentile. Compare two = call
    once per concept and diff. A concept that isn't a FRED series (ISM/PMI, a commodity SPOT price → pulse(kind='commodity'))
    → honest no_match, not a fabrication. US-govt series are public domain (`_license_note`).

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — the user's FULL request VERBATIM (any language). Used to pick the right series VARIANT (headline vs core, SA vs NSA). e.g. 'is US core inflation still sticky?'
- `country`: OPTIONAL ISO-2 to bias a CONCEPT to a country's series (JP, DE) — the nationality from the question goes HERE, not in `series_id`. FRED intl coverage is uneven; omit for US (default).
- `from_`: Start — ISO date or relative window `10y`/`5y`/`qtd` (dynamic, anchored to today).
- `q` (string, required): A macro CONCEPT (any language — 'inflation', 'core PCE', 'unemployment rate', '10y yield', 'อัตราว่างงาน') OR an exact FRED series_id you already hold (CPIAUCSL). The SERVER resolves a concept → the…
- `to`: End — ISO date. Omit → latest.
- `transform`: FRED units transform — `lin` (level: a rate/ratio) · `pc1` (YoY %: inflation/price index) · `pca` (annualized %: real GDP) · `pch` (period %) · `chg`/`ch1` (abs Δ). Omit → the resolved series' sugges…

### `wb_series` (~609 tokens)

World Bank Data + Analysis

"<structural indicator> for <country>, over time / vs other countries" — World Bank annual data,
    feature-extracted (open data, 3 credits). Pass a structural CONCEPT (the server resolves it to the canonical
    indicator + variant) or an exact indicator id. Returns `results:[{country, series:[{year,value}], analysis}]`
    (one per country); `analysis` = `latest`(+year), `trend`, `cagr_pct`, `change`, `peak`/`trough`. ⭐ For a
    MULTI-COUNTRY call (comma-sep `country`) a top-level `ranking` orders them by the latest value — the
    cross-country compare FRED can't do. Annual STRUCTURAL data → read levels + CAGR, not high-frequency moves.
    A country/year with no data is omitted (never interpolated). The right VARIANT (%GDP vs US$ vs per-capita) is
    picked from your `context`. A concept that isn't World-Bank structural (CPI/unemployment → fred_series) → honest
    no_match. Surface `_license_note` when showing data.

Input parameters:

- `context`: OPTIONAL but RECOMMENDED — the user's FULL request VERBATIM (any language). Used to pick the right unit VARIANT (% of GDP vs US$ vs per-capita vs real). e.g. 'compare household spending as a share of…
- `country` (string, required): Country as ISO3 or a name (`Thailand`/`THA`); COMMA-SEP for a cross-country compare (`THA,JPN,USA`); or an aggregate (`WLD` world · `EMU` euro area · `HIC`/`MIC`/`LIC` income groups).
- `database`: ADVANCED — the indicator's source database (WB_WDI, IMF_FSIC). Auto-derived from the resolved concept; override only for a non-WDI id you pass directly.
- `from_`: Start year (default ≈ last 15y, dynamic).
- `q` (string, required): A cross-country STRUCTURAL concept (any language — 'household consumption', 'GDP per capita', 'poverty rate', 'life expectancy', 'government debt', 'การบริโภค') OR an exact World Bank indicator id yo…
- `to`: End year (default latest).

### `suggest_cta` (~192 tokens)

Suggest Explorations

After answering, propose 1-2 data-backed 'explore further' hooks that pull the user into the
    graph's moat (ripple/relations/commodity/off-coverage). Server-side: theme_summary(has ripple/
    entities/aspects) + a semantic news search, then deepseek curates ONLY data-backed hooks.
    Validated in /tmp/mcp-gate/cta_tool.js (there via direct probes; here via the summary composite).

Input parameters:

- `theme` (string, required): A theme/scope to suggest a next-step call-to-action for.
- `window` (string): News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

### `edit_screen` (~381 tokens)

Edit Screen (change a formula you have)

CHANGE a screener formula you already have — add, remove or replace conditions as ops; the server places,
    resolves and merges them and checks the result (no engine JSON to write). Use it for EVERY change while building a
    screen with the user; use screen_unified (mode 'run') when the user wants to SEE the stocks of a formula.
    Returns {ok, criteria (the new formula, saved shape — screen_unified takes it verbatim in `criteria`), changes
    (what each op became: status resolved|snapped, value, snaps / dropped / assumed = what the engine read differently),
    issues (what did not go in: code, and `nearest` / `candidates` = alternatives ready to send back as an op's value),
    keep (the user-set paths after the change), reset, charts (when conditions were split across charts), count?}.
    Nothing is saved — the client decides what to apply.

Input parameters:

- `criteria`: The formula to change, in the saved shape — the user's current formula or an `executed_criteria` / `criteria` a screen tool returned. Omit (or {}) to build from empty.
- `keep`: Paths of values the USER set by hand ('ta.0.anchor.0.b', 'universe.include.0.country') — never overwritten or removed unless an op says user_asked.
- `mode` (string): 'check' = place, resolve and validate (fast, no market data) · 'count' = also how many stocks match the new formula (exact up to 500).
- `ops` (array, required): The changes, in order (1–8): ONE condition per op, written exactly as screen_unified takes it (same fields), plus WHERE it goes (op / target / step / rel).

### `pulse` (~577 tokens)

Market Pulse

ONE market-pulse read across every subject type — a news + market lens on an asset, a theme/sector, a
    commodity, a bond/rate/curve, a macro dashboard, or your portfolio. Pick `kind`, put the subject in `target`.
    Replaces the per-type asset/theme/commodity/bond/macro/portfolio pulse tools.

Input parameters:

- `context`: asset only — OPTIONAL but RECOMMENDED — paste the user's FULL request VERBATIM (any language: 'ขอราคาผลไม้ apple', 'compare Apple and Microsoft stock'). The server uses it to disambiguate which candi…
- `country`: ISO-2 CSV. theme: nationality scope ('European'→'GB,DE,FR,IT,ES,NL,CH,SE'; 'Thai'→'TH'). asset/macro: optional. Ignored by commodity/bond/portfolio.
- `kind` (string, required): WHICH pulse: `asset` (company/ETF/index-ETF/crypto) · `theme` (sector/industry/megatrend) · `commodity` (metal/energy/agri) · `bond` (govt-yield/rate/curve) · `macro` (FRED dashboard) · `portfolio` (…
- `limit`: Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles. (asset only)
- `target` (string, required): The SUBJECT for `kind`. asset: a ticker/company NAME ('NVDA','Apple'; the server resolves it). theme: a sector/industry/theme in ENGLISH ('semiconductors','banks','AI') — put nationality in `country`…
- `top_n`: portfolio only: how many top holdings to analyze (default 3, cap 5).
- `window`: News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fund-ava-ava-advisor/mcp#diagnostics

## Score history

- 2026-11-21: 85
- 2026-11-20: 84
- 2026-11-19: 84
- 2026-11-18: 84
- 2026-11-17: 83
- 2026-11-16: 83
- 2026-11-15: 82
- 2026-11-14: 82
- 2026-11-13: 81
- 2026-11-12: 81
- 2026-11-11: 80
- 2026-11-10: 80
- 2026-11-09: 79
- 2026-11-08: 79
- 2026-11-07: 78
- 2026-11-06: 38
- 2026-11-05: 38

## Common questions

### What is the Ava Advisor MCP server?

Ava Advisor is an MCP server listed in the public MCP registry as fund.ava/ava-advisor. Your AI watches the markets so you can live your life. Financial intelligence for everybody. This page covers its hosted endpoint (https://mcp.ava.fund/mcp).

### Is the Ava Advisor MCP server safe to use?

Ava Advisor scores 85 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Ava Advisor MCP server expose?

Ava Advisor exposes 37 tools: theme_summary, brief, search_news, news_feed, stock_impact, and 32 more. Their descriptions and schemas cost roughly 21,348 tokens of context every time the server is loaded.

### Does the Ava Advisor MCP server require authentication?

Yes. Ava Advisor asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Ava Advisor MCP server still maintained?

Ava Advisor is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Ava Advisor MCP server?

VerifyMCP ran 13 checks on Ava Advisor, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.ava.fund/mcp
- Repository: https://github.com/ava-fund/ava-advisor-mcp
- Website: https://ava.fund/
- Changelog RSS feed: https://verifymcp.io/servers/fund-ava-ava-advisor/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/fund-ava-ava-advisor/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/fund-ava-ava-advisor/mcp.json
- HTML version of this page: https://verifymcp.io/servers/fund-ava-ava-advisor/mcp
