# io.github.FinzData/finzdata-mcp (remote · api.finzdata.com)

US market data, PIT fundamentals, macro vintages, COT, 13F and backtester exports for AI agents.

- Trust score: 52/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `api.finzdata.com`: 52/100 (this document), [markdown](https://verifymcp.io/servers/finzdata-finzdata-mcp/api.md), [page](https://verifymcp.io/servers/finzdata-finzdata-mcp/api)
- pypi · `finzdata-mcp`: 63/100, [markdown](https://verifymcp.io/servers/finzdata-finzdata-mcp/finzdata-mcp.md), [page](https://verifymcp.io/servers/finzdata-finzdata-mcp/finzdata-mcp)

## Channel facts

- Endpoint: `https://api.finzdata.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.2`

## 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 2026-10-18.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2801 tokens (~100/item across 28 items; 28 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 79/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 36% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_strategy" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 29 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.

**Unverified: 1 category.** A category scored 0 because we couldn't verify past authentication. We only credit what we can confirm, so an authenticated endpoint we can't read counts against the score.

## Install

### How do I install the io.github.FinzData/finzdata-mcp server?

io.github.FinzData/finzdata-mcp is a hosted endpoint at https://api.finzdata.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 finzdata-finzdata-mcp 'https://api.finzdata.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "finzdata-finzdata-mcp": {
      "type": "http",
      "url": "https://api.finzdata.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.

### 2026-10-18 (score 52, −19)

- [security regression] Authorization: pass → unverified
- [security regression] Transport: pass → unverified
- [security improvement] HTTPS: unverified → pass
- [functional regression] Schema quality: 2264 → 2801
- [functional] New tool “backtest_export”
- [functional] New tool “claim_mcp_server”
- [functional] New tool “get_gex”
- [functional] New tool “get_mcp_server”
- [functional] New tool “search_mcp_servers”

### 2026-10-17 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 70, +1)

- [security] Tool “retire_strategy” rewrote its description, which is the text the model reads

### 2026-10-14 (score 69, −2)

- [security] Tool “run_backtest” rewrote its description, which is the text the model reads
- [security] Tool “get_universe” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1065 → 2240
- [functional regression] Tool coverage: 52% → 40%
- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: pass → 0
- [functional] New tool “get_verified_record”
- [functional] New tool “get_strategy”
- [functional] New tool “fork_strategy”
- [functional] New tool “comment_strategy”
- [functional] New tool “publish_strategy”
- [functional] New tool “list_strategies”
- [functional] New tool “verify_chain”
- [functional] New tool “verified_board”
- [functional] New tool “survivorship_audit”
- [functional] New tool “star_strategy”
- [functional] New tool “retire_strategy”
- [functional] New tool “register_strategy”
- [cosmetic] “get_universe” added an optional parameter “prefix”
- [cosmetic] “get_universe” added an optional parameter “offset”
- [cosmetic] “get_universe” reworded the description of “index”

### 2026-10-13 (score 71)

First indexed and scored.

## MCP tools (28)

### `search_datasets` (~45 tokens)

Search datasets

Full-text search over the dataset catalog. Returns matching dataset ids and descriptions. Free of look-ahead concerns; no as_of needed.

Input parameters:

- `query` (string, required): Search text.

### `describe_dataset` (~38 tokens)

Describe dataset

Returns the schema, coverage and field definitions of one dataset. Raises not_found for an unknown dataset id.

Input parameters:

- `dataset` (string, required): Dataset id.

### `get_universe` (~171 tokens)

Get universe

Returns every US symbol that was trading on as_of, including companies that later delisted (survivorship-free). index='top500'|'top1000'|'top3000' instead returns the most-traded names priced at least $5 that day, ranked by 63-day dollar volume (a point-in-time large-cap proxy, not official S&P or Russell membership). Pages of 500; pass offset. as_of defaults to today.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `index` (string): Optional liquidity-ranked subset.
- `offset` (integer): Paging offset (default 0).
- `prefix` (string): Only symbols starting with this.

### `get_bars` (~120 tokens)

Get OHLCV bars

Returns daily OHLCV bars for symbols between start and end, clipped to as_of (default today) so no future data leaks. Max 5000 rows per page; use next_cursor for more.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `bar` (string): Bar size, default '1d'.
- `end` (string)
- `start` (string, required)
- `symbols` (array, required)

### `backtest_export` (~175 tokens)

Export bars for a backtester

Daily OHLCV bars for one symbol packaged as ready-to-load files for an open-source backtester or trading framework: backtrader, backtesting_py, vectorbt, zipline (csvdir bundle), lean (QuantConnect LEAN, base64 zip), nautilus, freqtrade or qlib. Returns files (path, encoding, content) and load_code. Write each file at its path, then run load_code. Clipped to as_of; start defaults to 365 days before end.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `end` (string)
- `framework` (string)
- `start` (string)
- `symbol` (string, required)

### `get_fundamentals_pit` (~80 tokens)

Get fundamentals (point-in-time)

Returns fundamentals for one symbol as known on as_of (no restatements from the future). as_of defaults to today.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `symbol` (string, required)

### `get_macro_vintage` (~88 tokens)

Get macro vintage

Returns a macro series as it was actually published by as_of (vintage data, no revisions from the future). Optional start.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `series` (string, required)
- `start` (string): Optional start date.

### `get_cot` (~94 tokens)

Get COT

Returns CFTC Commitments of Traders rows for a market between start and end, clipped to as_of. Max 5000 rows per page.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `end` (string)
- `market` (string, required)
- `start` (string, required)

### `get_gex` (~212 tokens)

Get point-in-time GEX (dealer gamma)

Point-in-time dealer gamma exposure for US stocks and ETFs, one row per ticker per session, each stamped with knowledge_time (17:00 New York on the session date). Columns: spot, net_gex_bn (dealer net gamma, $bn per 1% move; >0 dealers long gamma, <0 short), call_gex_bn, put_gex_bn, flip (gamma-flip level), call_wall, put_wall, pcr_oi, atm_iv_pct. Give ticker (+ start/end) for a time series, or date alone for every name that session ranked by |net_gex_bn|. Rows after as_of are hidden.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `date` (string): YYYY-MM-DD, cross-section mode
- `end` (string)
- `start` (string)
- `ticker` (string)

### `get_13f` (~76 tokens)

Get 13F filings

Returns 13F holdings matching a query as known on as_of (default today); filings after as_of are hidden.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `query` (string, required)

### `get_events` (~90 tokens)

Get events

Returns corporate/market events of a kind between start and end, clipped to as_of. Max 5000 rows per page.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `end` (string)
- `kind` (string, required)
- `start` (string, required)

### `run_backtest` (~482 tokens)

Run backtest

Runs a deterministic backtest from a JSON spec (universe, start, end, signal, rebalance, top_n, costs_bps, side='long'|'long_short', blind=true to hide tickers). universe: a list of symbols, or 'top500'|'top1000'|'top3000'|'all' for the liquid US market (each month the N most-traded names priced >= min_price, default $5, by 63-day dollar volume; 'all' = liquid_top names, default 1000, max 3000; delisted names included while they traded; membership is set on each month's last trading day and used from the next). rebalance: D|W|M|Q (or daily/weekly/monthly/quarterly). signal.type: momentum (lookback, skip days), ma_cross, factor, or expr with signal.expr a formula over close prices, e.g. 'rank(ret(252)) - rank(vol(60))' (functions: ret, logret, sma, ema, vol, rsi, high, low, dist_high, lag, rank, zscore, demean, abs, log, sign, clip, min, max, where). Point-in-time fundamentals for US stocks (from 2011) work as expr variables and as signal.type factor fields (set ascending false to buy the highest): earnings_yield, book_to_market, sales_yield, ebitda_ev, dividend_yield, roe, leverage, log_mcap, e.g. 'rank(book_to_market) + rank(ret(252) - ret(21))'; such results carry a 'fundamentals' coverage and survivorship report. Every result includes 'overfitting': trials counted per API key and the deflated Sharpe ratio. Prices are fetched point-in-time with a 400-trading-day lookback buffer and clipped to as_of, so results have no look-ahead. Identical specs on the same snapshot are cached and free. Returns stats, benchmark stats, equity curve, warnings, snapshot id and a disclaimer.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `spec` (object, required): Backtest spec.

### `compare_runs` (~55 tokens)

Compare runs

Returns a table (run_id, cagr, sharpe, max_drawdown, turnover, final_equity) for previously run backtests in this session. Unknown run_id -> not_found.

Input parameters:

- `run_ids` (array, required)

### `publish_strategy` (~178 tokens)

Publish strategy

Runs a backtest spec (same format as run_backtest) on the server and publishes it to the FinzData Hub as a public, reproducible strategy page at data.finzdata.com/s/<slug>, forward-tracked daily from today. Only server-computed results are stored. Costs one backtest; free accounts may publish 3 a day. visibility='private' keeps it unlisted.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `description` (string): Hypothesis: why it should work and what would falsify it.
- `spec` (object, required): Backtest spec (see run_backtest).
- `title` (string, required): 1-120 characters.
- `visibility` (string)

### `fork_strategy` (~114 tokens)

Fork strategy

Copies a published Hub strategy, applies `changes` (nested fields merged, e.g. {"signal": {"lookback": 126}}), re-runs it on the server and publishes the fork linked to its parent. Costs one backtest.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `changes` (object, required)
- `slug` (string, required)
- `title` (string)

### `list_strategies` (~82 tokens)

List hub strategies

Lists public FinzData Hub strategies. sort: robust (deflated Sharpe), forward (forward Sharpe, 63+ days of out-of-sample record), new, forks. Optional family (momentum, expr, ma_cross, factor).

Input parameters:

- `family` (string)
- `limit` (integer)
- `sort` (string)

### `get_strategy` (~38 tokens)

Get hub strategy

Returns one public Hub strategy: spec, server-computed backtest result, forward-tracking record and fork lineage.

Input parameters:

- `slug` (string, required)

### `star_strategy` (~57 tokens)

Star a hub strategy

Stars (or with unstar=true removes your star from) a public Hub strategy. Stars feed the Trending list; rankings stay on deflated Sharpe and forward record.

Input parameters:

- `slug` (string, required)
- `unstar` (boolean)

### `comment_strategy` (~61 tokens)

Comment on a hub strategy

Posts a public comment (1-2000 characters) on a Hub strategy, e.g. a question, a result from a fork or a suggested change. Comments are shown under your handle.

Input parameters:

- `body` (string, required)
- `slug` (string, required)

### `survivorship_audit` (~152 tokens)

Survivorship-bias audit

Runs your backtest spec twice: once on the point-in-time universe (delisted companies included while they traded, the honest result) and once on only the names still trading today (what a backtest on a current ticker list does). Returns both stats and the inflation in CAGR and Sharpe that survivorship bias adds. Use universe 'top500'|'top1000'|'top3000' or a symbol list. Costs one backtest.

Input parameters:

- `as_of` (string): Point-in-time cutoff (YYYY-MM-DD). Nothing dated after this is returned, preventing look-ahead bias. Defaults to today (UTC).
- `spec` (object, required): Backtest spec, same as run_backtest.

### `register_strategy` (~96 tokens)

Register Strategy

Register a new strategy signal. The strategy is scored ONLY on data after registration, the record can never be edited or deleted, ranking starts at 63 trading sessions, and FinzData never trades on submitted signals.

Input parameters:

- `agent_name` (string, required)
- `rebalance` (string, required)
- `side` (string, required)
- `signal` (string, required)
- `top_frac` (number, required)
- `universe` (string, required)

### `get_verified_record` (~26 tokens)

Get Verified Record

Retrieve a verified strategy record by its ID.

Input parameters:

- `record_id` (string, required)

### `verified_board` (~22 tokens)

Verified Board

Get the leaderboard of verified strategies.

Input parameters:

- `limit` (integer)

### `verify_chain` (~20 tokens)

Verify Chain

Anyone can check no record was edited or back-dated.

### `retire_strategy` (~47 tokens)

Retire Strategy

Retire one of your verified strategy records: it stops accruing new forward results, keeps its full history and stays public on the Verified board marked retired.

Input parameters:

- `record_id` (string, required)

### `search_mcp_servers` (~66 tokens)

Search MCP Servers

finds financial MCP servers graded nightly by FinzData for health, protocol conformance and prompt-injection risk; results include install URLs.

Input parameters:

- `category` (string)
- `limit` (integer)
- `min_grade` (string)
- `q` (string)

### `get_mcp_server` (~35 tokens)

Get MCP Server

retrieves a financial MCP server listing with tools, probe history, issues and verified-data status.

Input parameters:

- `slug` (string, required)

### `claim_mcp_server` (~49 tokens)

Claim MCP Server

claims a listing for the calling API key so its owner can enable price-accuracy checks; first claimant wins; contact info@finzdata.com to dispute.

Input parameters:

- `slug` (string, required)

## Diagnostics

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

## Score history

- 2026-10-18: 52
- 2026-10-17: 71
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 69
- 2026-10-13: 71

## Common questions

### What is the io.github.FinzData/finzdata-mcp server?

io.github.FinzData/finzdata-mcp is listed in the public MCP registry as io.github.FinzData/finzdata-mcp. US market data, PIT fundamentals, macro vintages, COT, 13F and backtester exports for AI agents. This page covers its hosted endpoint (https://api.finzdata.com/mcp).

### Is the io.github.FinzData/finzdata-mcp server safe to use?

io.github.FinzData/finzdata-mcp scores 52 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 io.github.FinzData/finzdata-mcp server expose?

io.github.FinzData/finzdata-mcp exposes 28 tools: search_datasets, describe_dataset, get_universe, get_bars, backtest_export, and 23 more. Their descriptions and schemas cost roughly 2,769 tokens of context every time the server is loaded.

### Does the io.github.FinzData/finzdata-mcp server require authentication?

No. We connected to io.github.FinzData/finzdata-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.FinzData/finzdata-mcp server still maintained?

io.github.FinzData/finzdata-mcp is still listed as active in the MCP registry. We last reached this channel on 18 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://api.finzdata.com/mcp
- Authorisation metadata: https://api.finzdata.com/.well-known/oauth-protected-resource/mcp
- Changelog RSS feed: https://verifymcp.io/servers/finzdata-finzdata-mcp/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/finzdata-finzdata-mcp/api.json
- HTML version of this page: https://verifymcp.io/servers/finzdata-finzdata-mcp/api