Financial Datasets logo

Financial Datasets

Query SEC filings, institutional holdings, fund portfolios, and insider transactions through MCP.

Install Financial Datasets

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "financial-datasets": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-financial-datasets"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 4 tools correctly (8d ago).

Overview

Financial Datasets MCP server exposes financialdatasets.ai data through the Pipeworx gateway. Its four focused tools cover SEC filings, institutional 13F holders, institutional portfolio positions, and insider Form 3/4/5 transactions. Use it when an agent needs structured ownership, filing, or insider-activity data for a company or fund. It supports hosted MCP connections and a local npm stdio bridge.

Use cases

  • Find institutional holders for a stock
  • Inspect a fund's latest 13F portfolio
  • Review recent insider purchases and sales
  • Retrieve filtered SEC filings
  • Ask Pipeworx questions about financial datasets

Key features

  • Institutional 13F holder lookup
  • Institutional filer portfolio lookup by SEC CIK
  • Insider Form 3/4/5 transaction search
  • SEC filing retrieval with type filtering
  • Hosted MCP and local npm stdio access
  • Optional Pipeworx meta-tools and routing

Tools4

What Financial Datasets lets your agent do. Expand a tool for its parameters.

Verified live~895 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

9/9 checks healthy over the last 44d

What it can do

From the 4 tools this server returned when we ran it; 4 declare their own safety hints.

Makes network requests · 4Read-only tools · 4
Network at startup4 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age40 days
Maintainers1

Observed 2026-11-03 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @pipeworx/mcp-financial-datasets (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads1kPackage downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed4Callable tools this server registers over MCP.

How Financial Datasets works

What Financial Datasets does

Financial Datasets provides MCP access to financial data sourced through financialdatasets.ai and routed by the Pipeworx gateway. The integration focuses on SEC-related company and ownership records rather than broad market-data coverage.

Agents can investigate which institutions hold a stock, inspect the long positions reported by a particular institutional filer, review recent insider activity, or retrieve a company's latest SEC filings. Results include structured fields such as tickers, investor names, shares, market values, report periods, transaction details, filing dates, and document URLs.

The repository describes the integration as an independent, unofficial connection to the upstream provider.

How it works

A hosted MCP client can connect to the pack endpoint:

config.json
{
  "mcpServers": {
    "financial-datasets": {
      "url": "https://gateway.pipeworx.io/financial-datasets/mcp"
    }
  }
}

The endpoint lists the pack's tools along with shared Pipeworx gateway tools. Those shared tools include ask_pipeworx, which can route a natural-language question across the wider Pipeworx catalog. The full gateway is also available at https://gateway.pipeworx.io/mcp when an agent should access all connected packs directly.

For local stdio use, the npm package starts a bridge that forwards requests to the same hosted endpoint. The bridge requires network access and has no offline mode.

Setup and configuration

Add the hosted URL to an MCP client, or run the local bridge with npx:

config.json
{
  "mcpServers": {
    "financial-datasets": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-financial-datasets"]
    }
  }
}

The upstream data tools accept an _apiKey argument. The local bridge can also authenticate to Pipeworx with PIPEWORX_API_KEY:

config.json
{
  "env": {
    "PIPEWORX_API_KEY": "<your key>"
  }
}

Anonymous bridge use is capped at 50 calls per day. A free Pipeworx account raises the allowance to 200 calls per day. The key is sent as a Bearer token, and calls are metered and billed in the same way as hosted connections.

Set PIPEWORX_META_TOOLS=1 in the local bridge configuration if the connection should list the shared Pipeworx tools in addition to the Financial Datasets tools. Proxy users may need NODE_USE_ENV_PROXY=1 because Node's built-in fetch does not automatically read HTTPS_PROXY.

Tools and capabilities

  • fd_institutional_holders finds institutional investors reporting holdings in a ticker's latest SEC Form 13F. It returns investor names, shares, market values, and report periods.
  • fd_investor_portfolio returns the long positions reported in an institutional filer's latest Form 13F. The filer is identified with a 10-digit, zero-padded SEC CIK.
  • fd_insider_transactions retrieves recent purchases and sales reported by officers, directors, and 10% or greater owners in SEC Forms 3, 4, and 5. Results include the insider, title, transaction type, shares, price, date, and board-director status.
  • fd_filings retrieves recent company filings such as 10-K, 10-Q, 8-K, 20-F, and 6-K records, including filing type, report period, filing date, and document URL. An optional filing_type filter narrows the results.

The tools support a limit argument in the examples, allowing callers to control the number of returned records.

Limitations and notes

This integration depends on the remote Pipeworx gateway and the upstream financial data service, so it cannot operate offline. A hosted pack endpoint also exposes shared gateway meta-tools, increasing the tool list beyond the four Financial Datasets-specific tools. The local bridge lists only the pack tools unless meta-tools are enabled.

Use a fund's SEC CIK, not just its common name, with fd_investor_portfolio. For example, Berkshire Hathaway is represented by 0001067983. API-key usage and request allowances apply when calling the data tools through the gateway.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Financial Datasets

Financial Datasets is an MCP server that connects AI agents to financialdatasets.ai through the Pipeworx gateway, exposing tools for SEC filings, institutional 13F holders and portfolios, and insider Form 3/4/5 transactions. It accepts ticker or filer CIK inputs and returns structured market and filing data.

Install it by adding the hosted MCP URL or running the npm stdio bridge with npx. Use `https://gateway.pipeworx.io/financial-datasets/mcp` for a remote connection, or configure `@pipeworx/mcp-financial-datasets` with the `-y` npx argument.

Yes, Cursor is named as a supported MCP client in the setup instructions. Add the Financial Datasets hosted URL to Cursor's MCP configuration, or configure the local npm bridge if you prefer a stdio connection.

Call `fd_investor_portfolio` with the institution's 10-digit, zero-padded SEC CIK in `filer_cik`. The response contains each reported long position, including ticker, shares, market value, and report period.

Pass a filing type to the `filing_type` argument of `fd_filings`, such as `8-K`. The tool returns matching filing records with the filing type, report period, filing date, and document URL.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewFinancial Datasets AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/financial-datasets?style=directory)](https://allmcps.com/mcp/financial-datasets)
HTML Embed
<a href="https://allmcps.com/mcp/financial-datasets"><img src="https://allmcps.com/api/badge/financial-datasets?style=directory" alt="Financial Datasets on AllMCPs" /></a>