# QuantApe Markets (remote · mcp.quantape.com)

Stock screens; per-stock earnings, guidance, signal and sector insights; rotation and market mood.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-05

## Components

- remote · `mcp.quantape.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-quantape-markets/mcp.md), [page](https://verifymcp.io/servers/com-quantape-markets/mcp)

## Channel facts

- Endpoint: `https://mcp.quantape.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.1.0`

## 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 2026-10-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2853 tokens (~237/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 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 (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the QuantApe Markets MCP server?

QuantApe Markets is a hosted endpoint at https://mcp.quantape.com/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 com-quantape-markets 'https://mcp.quantape.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-quantape-markets": {
      "url": "https://mcp.quantape.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-quantape-markets": {
      "type": "http",
      "url": "https://mcp.quantape.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-quantape-markets]
url = "https://mcp.quantape.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-quantape-markets": {
      "type": "remote",
      "url": "https://mcp.quantape.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-quantape-markets --url 'https://mcp.quantape.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-quantape-markets:
    url: "https://mcp.quantape.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-quantape-markets": {
      "Transport": "http",
      "Url": "https://mcp.quantape.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-quantape-markets -t streamable-http -u 'https://mcp.quantape.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-quantape-markets": {
      "type": "http",
      "url": "https://mcp.quantape.com/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.

### 2026-10-05 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-03 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-02 (score 75, 0)

- [security] Tool “cluster_context” rewrote its description, which is the text the model reads
- [cosmetic] “cluster_context” added an optional parameter “mode”

### 2026-10-01 (score 75, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 2285 → 2703
- [functional] Server version: 2.2.0 → 2.3.1
- [functional] New tool “cluster_context”

### 2026-09-30 (score 75, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 175 → 207
- [functional] Server version: 2.1.0 → 2.2.0
- [functional] New tool “graph_neighbors”
- [functional] New tool “portfolio_analyze”

### 2026-09-29 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 74, +7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (12)

### `list_smart_lists` (~104 tokens)

Browse stock screens by category — momentum, technical signals, fundamentals, earnings events, social sentiment, themes, curated baskets, investment theses — with display names, descriptions, member counts, and the per-tool pricing/allowance for the metered tools below. Always free. Start here to find a screen id.

Input parameters:

- `category_id` (string): Restrict the catalog to one category id (e.g. momentum, technical, events, thematic); omit for every category.

Output parameters:

- `allowance` (object)
- `as_of` (string|null): Newest rebuild across the returned screens, ISO 8601 UTC
- `categories` (array)
- `pricing` (object): USD per call of each metered tool beyond the daily allowance

### `get_list_criteria` (~63 tokens)

Metadata for one stock screen (smart list): display name, short description, icon, category ids and parent screen. Always free.

Input parameters:

- `list_id` (string, required): Screen id from list_smart_lists (e.g. day_gainers, todays_earnings).

Output parameters:

- `category_ids` (array)
- `display_name` (string|null)
- `icon` (string|null)
- `list_id` (string)
- `parent_list` (string|null): Id of the screen this one refines
- `short_description` (string|null)
- `updated_at` (string|null): Screen last rebuilt, ISO 8601 UTC

### `get_smart_list` (~152 tokens)

Symbols currently in a stock screen — e.g. today's earnings, golden-cross buy signals, AI beneficiaries (paged, max 200 per call). Descriptive, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.01 per call via x402 (USDC).

Input parameters:

- `limit` (integer): Symbols per page, 1-200 (default 200).
- `list_id` (string, required): Screen id from list_smart_lists (e.g. day_gainers, golden_cross, ai_beneficiaries).
- `offset` (integer): Zero-based offset into the screen for paging.

Output parameters:

- `as_of` (string|null): Screen last rebuilt, ISO 8601 UTC
- `limit` (number)
- `list_id` (string)
- `offset` (number)
- `symbols` (array)
- `total` (number): Symbols across all pages.

### `get_smart_list_metrics` (~203 tokens)

QuantApe's own per-symbol analytics for a stock screen — last earnings reaction and the drift since it, next earnings date with how much of that report is already priced in (expectations score) and the options-implied move, and recent technical signals (paged, max 200 per call). It returns no live quotes, market cap or valuation ratios; use a quote API for those. Descriptive, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.05 per call via x402 (USDC).

Input parameters:

- `limit` (integer): Symbols per page, 1-200 (default 200).
- `list_id` (string, required): Screen id from list_smart_lists (e.g. day_gainers, golden_cross, ai_beneficiaries).
- `offset` (integer): Zero-based offset into the screen for paging.

Output parameters:

- `as_of` (string|null): Reserved; currently always null
- `has_more` (boolean)
- `limit` (number)
- `list_id` (string)
- `offset` (number)
- `rows` (array)
- `total` (number): Symbols across all pages.

### `get_my_watchlist` (~182 tokens)

The same per-symbol analytics as get_smart_list_metrics (earnings reaction and drift, expectations score, implied move, technical signals), plus the latest headlines, for your own watchlist — the tool behind "What's going on with my watchlist today?". Requires your session token (Authorization: Bearer). Descriptive, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.05 per call via x402 (USDC).

Input parameters:

- `limit` (integer): Watchlist symbols per page, 1-100 (default 50).
- `news_days` (integer): How many days of headlines to attach per symbol, 1-7 (default 2).
- `offset` (integer): Zero-based offset into the watchlist for paging.

Output parameters:

- `as_of` (string|null): Reserved; currently always null
- `has_more` (boolean)
- `limit` (number)
- `news_days` (number)
- `news_error` (string): Only when headlines could not be fetched (every row then has news: [])
- `offset` (number)
- `rows` (array)
- `total` (number): Symbols across all pages.

### `get_market_overview` (~140 tokens)

Today's market conditions: the daily overview narrative, the fear & greed index and per-sector scores, sector rotation and market-cycle phase, and categorized market news. Pick sections to keep the answer small. Pairs with get_my_watchlist for "how is my watchlist doing against the market?". Descriptive, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.02 per call via x402 (USDC).

Input parameters:

- `sections` (array): Which sections to return; omit for all five. Pick fewer to keep the answer small.

Output parameters:

- `as_of` (string|null): Newest section date, YYYY-MM-DD
- `disclaimer` (string)
- `sections` (object): Only the requested sections are present

### `get_stock_insights` (~272 tokens)

Everything QuantApe derives about ONE stock that a quote API can't tell you — the tool behind "what do you know about NVDA?": last earnings reaction and the drift since, how much of the next report is already priced in (expectations score) and the options-implied move, what the latest earnings call said about guidance, recent technical signals, why it moved today if it was a notable mover, its sector's fear & greed score and rotation quadrant, and which stock screens hold it with how those screens are doing. Each section carries its own as_of. It returns no live quotes, market cap or valuation ratios; use a quote API for those. Pick sections to keep the answer small; inside_sentiment (how the business reads from the inside) is opt-in. Descriptive, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.10 per call via x402 (USDC).

Input parameters:

- `sections` (array): Which sections to return; omit for the default set (earnings, guidance, signals, movers, sector, screens). Add inside_sentiment explicitly.
- `symbol` (string, required): Ticker symbol, e.g. NVDA or BRK-B.

Output parameters:

- `company` (object)
- `disclaimer` (string)
- `sections` (object): Only the requested sections are present
- `symbol` (string)

### `get_smart_list_changes` (~113 tokens)

Which symbols entered or left a stock screen since its last recorded baseline (which can span several rebuilds) — e.g. new golden crosses, or names that dropped out of the momentum leaders. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.02 per call via x402 (USDC).

Input parameters:

- `list_id` (string, required): Screen id from list_smart_lists whose additions and removals you want.

Output parameters:

- `added` (array)
- `added_count` (number)
- `as_of` (string|null): Screen last rebuilt, ISO 8601 UTC
- `baseline_as_of` (string|null): When the baseline was recorded; null = no baseline yet, so added/removed are empty
- `list_id` (string)
- `removed` (array)
- `removed_count` (number)

### `find_symbol_lists` (~98 tokens)

Every stock screen a given ticker is currently in — its momentum, technical-signal, earnings, theme and thesis memberships, in one call. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.01 per call via x402 (USDC).

Input parameters:

- `symbol` (string, required): Ticker symbol, e.g. NVDA or BRK-B.

Output parameters:

- `lists` (array)
- `symbol` (string)

### `graph_neighbors` (~326 tokens)

The stocks that move most with a given ticker, ranked by strength, each with its cluster (a stable id and a label naming its biggest members) — peers, co-movers and offsetting names. Residual correlation is how much two stocks move together after the market and sector effects are removed from each, so it shows peers and true co-movement rather than shared market beta. type=lead_lag instead lists directed lagged relationships (one stock's move followed by another's a few sessions later; direction is from the symbol's point of view), which are weak and largely noise out of sample. Share classes are one company (GOOG is answered as GOOGL). Everything returned is descriptive statistics of past returns, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.01 per call via x402 (USDC).

Input parameters:

- `k` (integer): Neighbours to return, 1-50 (default 20).
- `regime` (string): all (default) | highvol | lowvol: volatility regime the correlation was measured in (VIX above / below its trailing median).
- `symbol` (string, required): Ticker symbol, e.g. RGTI or BRK-B.
- `type` (string): resid_corr (default): same-day residual correlation. lead_lag: directed lagged correlation.
- `window` (integer): Sessions behind resid_corr: 250 (default) or 60. Leave unset for lead_lag.

Output parameters:

- `cluster`: The symbol's cluster (stable id + label) or null
- `neighbors` (array)
- `peers_kind` (string): 'neighbors' when the symbol is in no cluster (cluster_context then returns its closest peers)
- `regime` (string)
- `run_date` (string|null): Date of the nightly run the edges come from, YYYY-MM-DD
- `symbol` (string)
- `type` (string)
- `window` (number|null): Sessions behind resid_corr (60 or 250); for lead_lag the sample size

### `portfolio_analyze` (~333 tokens)

A diversification read on a list of holdings: how concentrated they are across clusters of co-moving stocks (shares, Herfindahl index), the portfolio's residual volatility, which names most and least move with the portfolio as a whole, and which clusters are least correlated to it — per volatility regime (high-vol is the conservative one, since correlations rise when volatility does). Residual correlation is how much two stocks move together after the market and sector effects are removed from each, so it shows peers and true co-movement rather than shared market beta. `diversifiers` are the names with the lowest correlation to the portfolio, not recommendations to buy them. hedge=true marks TLT, GLD and UUP, market ballast rather than residual offsets. Holdings are tickers (equal weight) or {symbol, weight} objects; share classes collapse to one company; tickers outside the graph universe are listed under unknown. Everything returned is descriptive statistics of past returns, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.05 per call via x402 (USDC).

Input parameters:

- `holdings` (array, required): 1-200 tickers (equal weight) or {symbol, weight} objects (weights positive, given for all holdings or none), e.g. ["NVDA","XOM"].
- `regimes` (array): Regimes to analyse; default ["all","highvol"].
- `top` (integer): Diversifiers to list per regime, 1-50 (default 10).

Output parameters:

- `cluster_run_date` (string|null)
- `equal_weight` (boolean)
- `holdings` (array): Canonical symbols analysed (GOOG is GOOGL)
- `regimes` (array)
- `unavailable` (array): Requested regimes without a matrix yet

### `cluster_context` (~555 tokens)

What happened recently to a ticker's peers: the cluster's move over the last 5 or 20 days (raw, market and residual), plus the news, earnings reactions, earnings-call guidance, price-mover explanations and themes that name its members. Give a symbol (its cluster; share classes are one company) or a cluster_id from graph_neighbors. Mega-caps and other names without a tight cluster get their closest residual-correlation peers instead (peers.kind = 'neighbors'). Peers are the ticker's residual-correlation cluster: stocks that move together once the market is removed. move is the cluster's equal-weight average in percent over the last 5 or 20 sessions: raw_* is the plain price move, market_* is SPY's, and residual_* is the move left after removing the market (the cluster-specific part); move.members has each member's own figures. Every news, earnings, transcript, mover and theme item cites a member symbol and a date. The optional digest (include_digest) is an LLM summary constrained to the cluster's members, each bullet citing members and a date; it may add latency, not cost. With mode 'peers' (symbol input only) the peers are instead the stocks whose residual moves track the ticker most closely (positive residual correlation over the past year, listed in peers.corr, with the ticker's leaf cluster as peers.theme): move is then the peers-only mean, move.symbol the ticker's own move and move.divergence_5d / _20d the ticker minus its peers, in percentage points. All of it is descriptive, not a recommendation. Free within your daily allowance (anonymous 5/day by IP, signed-in users 10/day, power users 50/day); beyond that $0.03 per call via x402 (USDC), with or without the digest.

Input parameters:

- `cluster_id` (integer): Cluster id from graph_neighbors. Give this or symbol, not both.
- `days` (number): Look-back window in days: 5 (default) or 20.
- `include_digest` (boolean): Also attach the LLM digest (default false). Slower; a failed digest comes back as digest: null with digest_status, never as an error.
- `mode` (string): Symbol input only. 'cluster' (default): the ticker's residual-correlation cluster. 'peers': the ticker plus the stocks whose residual moves track it most closely (with peers.corr), the peers' mean mo…
- `symbol` (string): Ticker symbol, e.g. RGTI. Give this or cluster_id, not both.

Output parameters:

- `as_of` (string|null): YYYY-MM-DD the window ends on
- `cluster`: The symbol's cluster, or null when it is in no tight cluster (then see peers)
- `counts` (object)
- `days` (number): 5 or 20 calendar days behind news, earnings, transcripts, movers and themes
- `digest`: include_digest only: LLM summary constrained to the member symbols of the peers; null when it could not be produced
- `digest_model` (string|null): include_digest only
- `digest_status` (string): include_digest only
- `earnings` (array)
- `move` (object)
- `movers` (array)
- `news` (array)
- `peers` (object): symbol input only: the peers the payload covers (absent for cluster_id input)
- `symbol` (string): The ticker asked about (symbol input only)
- `themes` (array)
- `transcripts` (array)

## Diagnostics

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

## Score history

- 2026-10-05: 77
- 2026-10-04: 76
- 2026-10-03: 76
- 2026-10-02: 75
- 2026-10-01: 75
- 2026-09-30: 75
- 2026-09-29: 75
- 2026-09-28: 74
- 2026-09-27: 67
- 2026-09-26: 66
- 2026-09-25: 66
- 2026-09-24: 66
- 2026-09-23: 65
- 2026-09-22: 65
- 2026-09-21: 65
- 2026-09-20: 64
- 2026-09-19: 64
- 2026-09-18: 63
- 2026-09-17: 63
- 2026-09-16: 62
- 2026-09-15: 62
- 2026-09-14: 61
- 2026-09-13: 61
- 2026-09-12: 60
- 2026-09-11: 60
- 2026-09-10: 59

## Common questions

### What is the QuantApe Markets MCP server?

QuantApe Markets is an MCP server listed in the public MCP registry as com.quantape/markets. Stock screens; per-stock earnings, guidance, signal and sector insights; rotation and market mood. This page covers its hosted endpoint (https://mcp.quantape.com/mcp).

### Is the QuantApe Markets MCP server safe to use?

QuantApe Markets scores 77 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 QuantApe Markets MCP server expose?

QuantApe Markets exposes 12 tools: list_smart_lists, get_list_criteria, get_smart_list, get_smart_list_metrics, get_my_watchlist, and 7 more. Their descriptions and schemas cost roughly 2,541 tokens of context every time the server is loaded.

### Does the QuantApe Markets MCP server require authentication?

No. We connected to QuantApe Markets without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the QuantApe Markets MCP server still maintained?

QuantApe Markets is still listed as active in the MCP registry. We last reached this channel on 5 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.quantape.com/mcp
- Website: https://quantape.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-quantape-markets/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-quantape-markets/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-quantape-markets/mcp