# FinChiefs research (remote · finchiefs.com)

Research views from 200+ sources, plus official rates, positioning and macro data, with sources.

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `finchiefs.com`: 82/100 (this document), [markdown](https://verifymcp.io/servers/com-finchiefs-research/api-mcp.md), [page](https://verifymcp.io/servers/com-finchiefs-research/api-mcp)

## Channel facts

- Endpoint: `https://finchiefs.com/api/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.1`

## 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 2026-11-06.

- **Endpoint Security**: 94/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3184 tokens (~244/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 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 FinChiefs research MCP server?

FinChiefs research is a hosted endpoint at https://finchiefs.com/api/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-finchiefs-research 'https://finchiefs.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-finchiefs-research": {
      "url": "https://finchiefs.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-finchiefs-research": {
      "type": "http",
      "url": "https://finchiefs.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-finchiefs-research]
url = "https://finchiefs.com/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-finchiefs-research --url 'https://finchiefs.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-finchiefs-research:
    url: "https://finchiefs.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-finchiefs-research": {
      "Transport": "http",
      "Url": "https://finchiefs.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-finchiefs-research -t streamable-http -u 'https://finchiefs.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-finchiefs-research": {
      "type": "http",
      "url": "https://finchiefs.com/api/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.

### 2026-11-06 (score 82, 0)

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

### 2026-11-04 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 81, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_central_bank_meetings” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 2025 → 3184
- [functional regression] Schema quality: 2025 → 3152
- [functional] Server version: 1.1.0 → 1.1.1
- [functional] Server version: 1.0.1 → 1.1.0
- [functional] New tool “get_central_bank_meetings”
- [functional] New tool “get_economic_indicators”
- [functional] New tool “get_policy_rates”
- [functional] New tool “get_positioning”
- [functional] New tool “get_yield_curves”
- [cosmetic] “get_central_bank_meetings” reworded the description of “houses”

### 2026-10-31 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 77, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-24 (score 76, +38)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: 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.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 91
- [functional] First check of Schema quality: good

## MCP tools (13)

### `list_providers` (~81 tokens)

List research providers

Research providers FinChiefs follows (banks, asset managers, central banks, multilaterals, independent researchers). Use the id to limit other tools to one provider.

Input parameters:

- `limit` (integer): Default 100.
- `query` (string): Part of the provider name, e.g. "ECB" or "Federal Reserve". Omit to list all.

### `list_categories` (~64 tokens)

List categories

Asset digest categories (gold, oil, us_bonds, eurusd, …) and macro categories (monetary_policy, geopolitics, …). Keys with has_daily_digest work with get_daily_digests; macro keys also filter search_macro_views and summarize_views.

### `summarize_views` (~291 tokens)

Summarize views

The overall picture from EVERY matching view in one small response: totals, up/down counts (asset views), how many providers lean each way, the busiest providers, a week-by-week trend, and the most-discussed assets or macro categories. Start here for "what is the consensus / how has it changed" questions, then read individual views with search_asset_views or search_macro_views.

Input parameters:

- `asset_class` (string): Asset views only.
- `category` (string): Macro views only: a macro category key from list_categories, e.g. "monetary_policy".
- `kind` (string, required): Asset (directional) views or macro theme views.
- `provider_id` (string): Limit to one research provider (id from list_providers).
- `since` (string): Start date YYYY-MM-DD. Default: 30 days ago. The free plan reaches back 30 days for summaries.
- `terms` (array): Subject words to match (assets, tickers, countries, central banks, companies, themes). Whole-word, case-insensitive; any term may match. Include synonyms and tickers, e.g. ["gold", "xau", "bullion"].…
- `until` (string): End date YYYY-MM-DD, inclusive. Default: today.

### `search_asset_views` (~334 tokens)

Search asset views

Individual directional views (up/down) on assets, with provider, date, horizon, rationale and a link to the source publication. Up/down tallies cover every match; items come in pages (offset / next_offset), spread across providers by default. For the overall picture, call summarize_views first.

Input parameters:

- `asset_class` (string)
- `direction` (string)
- `limit` (integer): Items per page, at most 100. Default 100.
- `offset` (integer): Skip this many items; pass the previous response's next_offset to read the next page.
- `order` (string): "spread" (default) interleaves providers so each page covers as many sources as possible; "newest" is strictly newest first.
- `provider_id` (string): Limit to one research provider (id from list_providers).
- `search_rationale` (boolean): Also match terms in the rationale text (for themes like "tariffs" that are not asset names). Default false.
- `since` (string): Start date YYYY-MM-DD. Default: 30 days ago. The free plan reaches back 7 days for individual items.
- `terms` (array): Subject words to match (assets, tickers, countries, central banks, companies, themes). Whole-word, case-insensitive; any term may match. Include synonyms and tickers, e.g. ["gold", "xau", "bullion"].…
- `until` (string): End date YYYY-MM-DD, inclusive. Default: today.

### `search_macro_views` (~313 tokens)

Search macro views

Individual macro themes and drivers from provider research (growth, inflation, policy, fiscal, geopolitics, …), each with a description and a link to the source publication. Items come in pages (offset / next_offset), spread across providers by default. For counts and trends, call summarize_views first.

Input parameters:

- `category` (string): A macro category key from list_categories, e.g. "monetary_policy".
- `limit` (integer): Items per page, at most 100. Default 100.
- `offset` (integer): Skip this many items; pass the previous response's next_offset to read the next page.
- `order` (string): "spread" (default) interleaves providers so each page covers as many sources as possible; "newest" is strictly newest first.
- `provider_id` (string): Limit to one research provider (id from list_providers).
- `since` (string): Start date YYYY-MM-DD. Default: 30 days ago. The free plan reaches back 7 days for individual items.
- `terms` (array): Subject words to match (assets, tickers, countries, central banks, companies, themes). Whole-word, case-insensitive; any term may match. Include synonyms and tickers, e.g. ["gold", "xau", "bullion"].…
- `until` (string): End date YYYY-MM-DD, inclusive. Default: today.

### `search_research` (~261 tokens)

Search research publications

Research publications (articles, reports, podcasts) with title, provider, date, a short description and the link to the original. Ranked by how well the terms match (title matches count most), then newest; pages via offset / next_offset. Follow the link for the full text where the publisher allows it.

Input parameters:

- `limit` (integer): Items per page, at most 100. Default 25.
- `offset` (integer): Skip this many items; pass the previous response's next_offset to read the next page.
- `provider_id` (string): Limit to one research provider (id from list_providers).
- `since` (string): Start date YYYY-MM-DD. Default: 30 days ago. The free plan reaches back 7 days for individual items.
- `terms` (array): Subject words to match (assets, tickers, countries, central banks, companies, themes). Whole-word, case-insensitive; any term may match. Include synonyms and tickers, e.g. ["gold", "xau", "bullion"].…
- `type` (string)
- `until` (string): End date YYYY-MM-DD, inclusive. Default: today.

### `get_daily_digests` (~196 tokens)

Get daily digest summaries

Daily summaries written from all providers' views for a category (e.g. gold, oil, us_bonds, top macro themes, policy makers), with the day's up/down tallies. Good for how a view changed day by day. Category keys (has_daily_digest) come from list_categories.

Input parameters:

- `categories` (array, required): Category keys, e.g. ["gold"] or ["top", "policy_makers"]. "__overall__" is the cross-asset summary.
- `limit` (integer): Digests per page, at most 100. Default 30.
- `offset` (integer): Skip this many items; pass the previous response's next_offset to read the next page.
- `since` (string): Start date YYYY-MM-DD. Default: 14 days ago. The free plan reaches back 7 days.
- `until` (string): End date YYYY-MM-DD, inclusive. Default: today.

### `get_policy_signals` (~191 tokens)

Get central bank and policy-maker signals

Structured reads of central-bank and multilateral publications: decisions, stance (-2 dovish to +2 hawkish), guidance, conditions, speaker and forecasts, each with a link to the original. Newest first; pages via offset / next_offset.

Input parameters:

- `doc_type` (string)
- `limit` (integer): Items per page, at most 100. Default 40.
- `offset` (integer): Skip this many items; pass the previous response's next_offset to read the next page.
- `provider_id` (string): A central bank or multilateral (id from list_providers). Matches the publisher or the institution whose view it is.
- `since` (string): Start date YYYY-MM-DD. Default: 30 days ago. The free plan reaches back 7 days for individual items.
- `until` (string): End date YYYY-MM-DD, inclusive. Default: today.

### `get_yield_curves` (~173 tokens)

Get government bond yield curves

Government bond yield curves for the US (Treasury), euro area (ECB AAA curve), UK (Bank of England) and Japan (Ministry of Finance): yields per tenor now, a day, a month and a year ago, the 2s10s and 3m10y spreads, and optionally weekly 2y / 10y / 2s10s history. Official data with its source.

Input parameters:

- `history` (boolean): Add weekly 2y, 10y and 2s10s history (default false).
- `regions` (array): US, EA (euro area), UK, JP. Omit for all four.
- `since` (string): History start YYYY-MM-DD. Default: 5 years ago. Data reaches back to 1990.

### `get_policy_rates` (~198 tokens)

Get central bank policy rates

Policy rates of the Fed, ECB, BoE, BoJ, Bank of Canada, RBA, SNB and PBoC: current rate, last change, moves in the past 12 months and the rate path since a date; plus the FOMC dot-plot medians (latest and previous release) when the Fed is included. Official data (BIS, ECB, Federal Reserve). Market-implied rate odds are not included.

Input parameters:

- `banks` (array): Central banks by code or short name: fed, ecb, boe, boj, boc, rba, snb, pboc (meetings also cover Riksbank, Norges Bank, RBNZ, RBI). Omit for all.
- `dot_plot` (boolean): Include the Fed dot plot (default: when the Fed is included).
- `since` (string): Rate path start YYYY-MM-DD. Default: 5 years ago.

### `get_central_bank_meetings` (~185 tokens)

Get upcoming central bank meetings and the research tally

Each central bank's next rate decision (and decisions of the past week): date, FinChiefs' preview, the research tally (one hike/hold/cut vote per research house — banks, asset managers, independent research firms and podcasts — counted from published notes) with its mix by house type, and the outcome once decided. Pass banks to also list each house with its call and latest note. Covers the G10 banks and India.

Input parameters:

- `banks` (array): Central banks by code or short name: fed, ecb, boe, boj, boc, rba, snb, pboc (meetings also cover Riksbank, Norges Bank, RBNZ, RBI). Omit for all.
- `houses` (boolean): List each research house's call and note (default: true when banks are given, false otherwise).

### `get_positioning` (~193 tokens)

Get futures positioning (CFTC COT, ESMA)

Weekly speculative positioning in futures: CFTC Commitments of Traders for US-listed FX, rates, equity-index, energy, metals, agricultural and bitcoin futures, and ESMA's MiFID II reports for Dutch TTF gas. Net position, % of open interest, week change, 52/156-week COT index, crowding, other trader groups, optional weekly history. Plain data, not a signal. No arguments lists every market's latest reading.

Input parameters:

- `markets` (array): Market keys, e.g. ["gold", "ust10", "eur", "wti", "ttf", "btc", "spx"]. Call without arguments for the full list.
- `terms` (array): Whole-word match on market name or group, e.g. ["gold"], ["metals"], ["yen"].
- `weeks` (integer): Weekly history rows to add per market (default 0).

### `get_economic_indicators` (~226 tokens)

Get economic indicators

Economic indicators for the US, euro area, UK and Japan from official sources (statistics offices, central banks, OECD, FRED): inflation, growth, labour market, financial conditions, money and credit, housing, public finances, currencies, expectations surveys. Latest print with its period, change, source, optional history. Without keys or terms it returns the headline readings; catalog: true lists every key.

Input parameters:

- `all` (boolean): Every indicator, not only the headline ones (default false).
- `catalog` (boolean): Only list the available indicator keys per region.
- `history` (boolean): Add each indicator's history (default false).
- `keys` (array): Indicator keys from catalog: true.
- `regions` (array): US, EA (euro area), UK, JP. Omit for all four.
- `since` (string): History start YYYY-MM-DD. Default: 5 years ago.
- `terms` (array): Whole-word match on indicator name or group, e.g. ["inflation"], ["unemployment"], ["housing"].

## Diagnostics

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

## Score history

- 2026-11-06: 82
- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 80
- 2026-10-31: 80
- 2026-10-30: 79
- 2026-10-29: 79
- 2026-10-28: 78
- 2026-10-27: 78
- 2026-10-26: 77
- 2026-10-25: 77
- 2026-10-24: 76
- 2026-10-23: 38
- 2026-10-22: 38
- 2026-10-21: 38

## Common questions

### What is the FinChiefs research MCP server?

FinChiefs research is an MCP server listed in the public MCP registry as com.finchiefs/research. Research views from 200+ sources, plus official rates, positioning and macro data, with sources. This page covers its hosted endpoint (https://finchiefs.com/api/mcp).

### Is the FinChiefs research MCP server safe to use?

FinChiefs research scores 82 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 FinChiefs research MCP server expose?

FinChiefs research exposes 13 tools: list_providers, list_categories, summarize_views, search_asset_views, search_macro_views, and 8 more. Their descriptions and schemas cost roughly 2,706 tokens of context every time the server is loaded.

### Does the FinChiefs research MCP server require authentication?

Yes. FinChiefs research 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 FinChiefs research MCP server still maintained?

FinChiefs research is still listed as active in the MCP registry. We last reached this channel on 6 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 FinChiefs research MCP server?

VerifyMCP ran 13 checks on FinChiefs research, 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://finchiefs.com/api/mcp
- Website: https://finchiefs.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-finchiefs-research/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-finchiefs-research/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-finchiefs-research/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-finchiefs-research/api-mcp