mcp-investment-data

A small Model Context Protocol (MCP) server that exposes investment-data tools to any MCP host (Claude Desktop, the MCP Inspector, or a custom client). It's the warm-start for an AI-native data layer.

What it exposes

Four tools over a ~10,000-company synthetic firmographic dataset (generated by data.py — deterministic, no external data):

• search_companies(query, limit) — match companies by name, sector, or HQ

• get_company(name) — one company's full record

• get_signals(name) — a company's financial-intent signals (intent score, hiring velocity, web-traffic trend, news mentions)

• list_recent_funding(sector, since, limit) — recent funding rounds, newest first, filterable by sector and date

No JSON Schema, no request parsing, no validation code — the type hints are the schema. That's the point of MCP: business logic in, protocol handled for you.

The dataset is generated, not real: data.py produces 10k companies with firmographics (sector, HQ, headcount, funding) and mock "financial-intent" signals — the shape of the investment-data problem, without shipping anyone's real data.

Related MCP server: Company Records

Run it

Requires Python 3.10+.

pip install -r requirements.txt

Verify it (no extra tooling) — a tiny MCP client that spawns the server, does the handshake, and calls a tool:

python test_client.py

Expected (abridged):

Connected. Tools: ['search_companies', 'get_company', 'get_signals', 'list_recent_funding']

search_companies('Open Banking', limit=3): ...
get_signals('<company>'): {"intent_score": ..., "hiring_velocity_90d": ..., ...}
list_recent_funding('Crypto Exchange', since='2026-01-01'): ...

Use it in Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json, then restart Claude Desktop and ask it to "use investment-data to search companies for UAE."

{
  "mcpServers": {
    "investment-data": {
      "command": "/absolute/path/to/python",
      "args": ["/absolute/path/to/server.py"]
    }
  }
}

The args array is the reliable way to pass paths — unlike a single command string (e.g. the MCP Inspector's box), it never splits on spaces, so a project path containing a space works as-is.

Design note (why v1.x, not v2)

The MCP Python SDK's v2 is a pre-release (alpha/beta) with breaking changes between builds — the SDK's own README says not to use it in production. This repo pins stable v1.x (mcp[cli]>=1.27,<2) so it keeps working. Deliberate dependency hygiene, not laziness.

Roadmap

• v0 — hello world: two tools over a 5-company in-memory dataset.

• v1 — real dataset: ~10k generated firmographic rows + get_signals and list_recent_funding. (this)

• v2 — agent: a small agent (thesis-agent) that consumes this server — "given a fund's thesis, return the top candidate companies and why."

• v3 — write-up: essay "What MCP means for investment-data infrastructure" + a buyer-facing README.