# io.github.FinzData/finzdata-mcp (pypi · finzdata-mcp)

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

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

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

## Channel facts

- Registry: `pypi`
- Package: `finzdata-mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1643 tokens (~109/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 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 io.github.FinzData/finzdata-mcp server?

io.github.FinzData/finzdata-mcp runs locally as a PyPI package, launched with uvx finzdata-mcp. 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 finzdata-finzdata-mcp -- uvx finzdata-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "finzdata-finzdata-mcp": {
      "command": "uvx",
      "args": [
        "finzdata-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "finzdata-finzdata-mcp": {
      "command": "uvx",
      "args": [
        "finzdata-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add finzdata-finzdata-mcp -- uvx finzdata-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "finzdata-finzdata-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "finzdata-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add finzdata-finzdata-mcp --command uvx --arg finzdata-mcp
```

### Hermes

```yaml
mcp_servers:
  finzdata-finzdata-mcp:
    command: "uvx"
    args: ["finzdata-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "finzdata-finzdata-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "finzdata-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add finzdata-finzdata-mcp -t stdio -c uvx -a finzdata-mcp
```

### Other

```json
{
  "mcpServers": {
    "finzdata-finzdata-mcp": {
      "command": "uvx",
      "args": [
        "finzdata-mcp"
      ]
    }
  }
}
```

## 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 63, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-17 (score 47, +28)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.10
- [functional improvement] MCP protocol: unverified → pass
- [functional] Package version: 0.1.0 → 0.1.3

### 2026-10-15 (score 19, −42)

- [security regression] Tool safety: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Malware scan: pass → unverified
- [security] Stability: Stability not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to compare.
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Schema quality: Schema quality not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to assess.
- [functional] Package version: 0.1.0 → 0.1.2

### 2026-10-14 (score 61, +27)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good

### 2026-10-12 (score 34)

First indexed and scored.

## MCP tools (15)

### `prices_daily` (~116 tokens)

Daily OHLCV bars for a stock symbol (e.g. AAPL). Returns one row per trading day with open, high, low, close and volume; prices are in the listing currency and `adjust` controls split/dividend adjustment ("splits" by default). On the free tier, history is limited to the last 12 months; older dates are clipped and the result carries a free_tier_note.

Input parameters:

- `adjust` (string)
- `end`
- `start`
- `symbol` (string, required)

### `backtest_export` (~153 tokens)

Daily bars for a symbol packaged as ready-to-load files for an open-source backtester or trading framework:
backtrader, backtesting_py (backtesting.py), vectorbt, zipline (zipline-reloaded csvdir bundle), lean (QuantConnect LEAN),
nautilus (NautilusTrader), freqtrade or qlib. Returns files (path, encoding, content; LEAN zips are base64) and load_code
showing how to load them. Write each file to disk at its path, then run the load_code. Free tier: last 12 months.

Input parameters:

- `end`
- `framework` (string)
- `start`
- `symbol` (string, required)

### `cot` (~157 tokens)

Commitments of Traders (CFTC) positioning, weekly: long, short and net contracts by trader group for a futures market. Easiest use: market="gold" (a word from the market name) with report="legacy_fo", where large speculators are the non-commercial columns and hedgers the commercial ones; other reports are disagg_fo (managed money) and tff_fo (financial futures). Use cot_markets(query=...) to look up an exact code. Rows come newest week first. Counts are in contracts. On the free tier, only the last 12 months are returned.

Input parameters:

- `code`
- `end`
- `market`
- `report`
- `start`

### `cot_markets` (~109 tokens)

The list of futures markets available in the Commitments of Traders data, with each market's name and code, for a given report (default legacy_fo). Pass query (e.g. "gold", "s&p 500", "crude") to filter by market name; use the result's code or market with the cot tool. Note that dated COT history on the free tier is limited to the last 12 months.

Input parameters:

- `query`
- `report` (string)

### `macro` (~93 tokens)

Time series for a macroeconomic indicator (e.g. CPIAUCSL for US CPI, UNRATE for unemployment). Returns one row per observation date with the value in the series' own units (index points, percent, millions, etc.). On the free tier, history is limited to the last 12 months; older dates are clipped.

Input parameters:

- `end`
- `series` (string, required)
- `start`

### `macro_search` (~92 tokens)

Search the catalogue of macroeconomic series by keyword (matched against the series id and title) and/or category. Returns matching series with their id, title, units and frequency, so you can pick a series id for the macro tool. Note that fetching a series' history on the free tier is limited to the last 12 months.

Input parameters:

- `category`
- `limit` (integer)
- `query`

### `short_interest` (~72 tokens)

Short interest history for a stock ticker: one row per settlement date with shares sold short and related figures (share counts, not dollars). On the free tier, history is limited to the last 12 months; older dates are clipped.

Input parameters:

- `end`
- `start`
- `ticker` (string, required)

### `insiders` (~80 tokens)

Insider transaction filings (buys, sells, option exercises) for a company ticker and/or an owner name. Returns one row per transaction with shares, price and value in the listing currency. On the free tier, history is limited to the last 12 months.

Input parameters:

- `end`
- `owner`
- `start`
- `ticker`

### `fundamentals` (~118 tokens)

Raw SEC XBRL facts a company reported in its 10-K/10-Q filings (columns: concept, unit, value, start, end, fy, fp, form, filed), optionally narrowed to one us-gaap concept such as NetIncomeLoss, Assets or RevenueFromContractWithCustomerExcludingAssessedTax. For ready-made income statements, balance sheets and cash flows use financial_statements instead. On the free tier, only filings from the last 12 months are returned.

Input parameters:

- `concept`
- `ticker` (string, required)

### `financial_statements` (~119 tokens)

Standardised financial statements for a US company from its SEC filings: statement is "income" (revenue, gross profit, operating income, net income, EPS, shares), "balance" (cash, assets, liabilities, equity) or "cashflow"; freq is "quarterly" or "annual". Values in US dollars, one row per period. On the free tier, only periods filed in the last 12 months are returned.

Input parameters:

- `freq` (string)
- `statement` (string)
- `ticker` (string, required)

### `company_profile` (~71 tokens)

Reference profile for a US stock or ETF: name, exchange, sector, industry, country, state, IPO date, first and last date of price history, and whether it is delisted. Dated data elsewhere on the free tier is limited to the last 12 months.

Input parameters:

- `symbol` (string, required)

### `earnings_dates` (~74 tokens)

Past earnings release dates for a ticker from SEC 8-K Item 2.02 filings: report date, filing time (US Eastern) and whether it came before the open or after the close. No EPS or forecasts. On the free tier, only the last 12 months are returned.

Input parameters:

- `ticker` (string, required)

### `valuation` (~85 tokens)

Daily point-in-time valuation for a US stock from its SEC filings (P/E, P/B, P/S, EV/EBITDA, market cap, dividend yield), as known on each date. On the free tier, history is limited to the last 12 months; older dates are clipped.

Input parameters:

- `end`
- `start`
- `ticker` (string, required)

### `institutional_ownership` (~82 tokens)

SEC Form 13F institutional ownership of a stock, quarter by quarter: number of holders, shares, reported value and the quarter's new, closed, increased and decreased positions. On the free tier, history is limited to the last 12 months; older quarters are clipped.

Input parameters:

- `end`
- `start`
- `ticker` (string, required)

### `institutional_holders` (~76 tokens)

Every 13F manager that reported a stock in one quarter (latest by default, or period like "2026Q2"), largest position first, with shares and reported value. The free tier covers quarters in the last 12 months.

Input parameters:

- `limit` (integer)
- `period`
- `ticker` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/finzdata-finzdata-mcp/finzdata-mcp#diagnostics

## Score history

- 2026-10-18: 63
- 2026-10-17: 47
- 2026-10-16: 19
- 2026-10-15: 19
- 2026-10-14: 61
- 2026-10-13: 34
- 2026-10-12: 34

## 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 PyPI package (finzdata-mcp).

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

io.github.FinzData/finzdata-mcp scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. 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 15 tools: prices_daily, backtest_export, cot, cot_markets, macro, and 10 more. Their descriptions and schemas cost roughly 1,497 tokens of context every time the server is loaded.

### 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.

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

io.github.FinzData/finzdata-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/finzdata-mcp/
- Socket report: https://socket.dev/pypi/package/finzdata-mcp
- Changelog RSS feed: https://verifymcp.io/servers/finzdata-finzdata-mcp/finzdata-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/finzdata-finzdata-mcp/finzdata-mcp.json
- HTML version of this page: https://verifymcp.io/servers/finzdata-finzdata-mcp/finzdata-mcp