Setup guides · VALUEFOCUS RESEARCH

How to Install Financial Datasets MCP Server for Claude Desktop

A practical, security-first setup guide for connecting Financial Datasets MCP Server to Claude Desktop.

1 Tools coveredClaude Desktop

Tools covered

Financial Datasets MCP Server

An MCP server for income statements, balance sheets, cash flow, prices and company news.

Recommended workflow

1
Verify the repository, license and latest release
2
Install in an isolated environment and keep credentials in environment variables
3
Enable read-only tools first and inspect every exposed capability
4
Run a sourced test query and confirm timestamps before relying on output

Examples and expected outcomes

Example 1

Fetch prices and statements in agent chat

Sourced evidence
Repeatable steps
Explicit uncertainty

Example 2

Create a read-only research brief

Sourced evidence
Repeatable steps
Explicit uncertainty

Example 3

Compare tickers with source timestamps

Sourced evidence
Repeatable steps
Explicit uncertainty

Access requirements

Keys and runtime

FINANCIAL_DATASETS_API_KEY

License and data rights

MIT repository license; upstream data terms apply

Rate limits

Plan-based API limits; cache statements and prices

Connect to your Agent

Claude config

{
  "mcpServers": {
    "financial-datasets-mcp-review": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/mcp-server",
        "run",
        "server.py"
      ],
      "env": {
        "FINANCIAL_DATASETS_API_KEY": "YOUR_KEY"
      }
    }
  }
}

Prompt example

“Use Financial Datasets MCP Server to research AAPL. List sources and timestamps first, then separate facts, calculations, risks and missing data. Do not give personalized trading advice.”

When not to use it

Repository activity is older than leading alternatives
Requires a Financial Datasets API key

How to choose

Prefer primary sources for filings, maintained adapters for convenience, and narrow permissions for every agent tool. Treat model conclusions as analysis rather than financial advice.

Evidence to retain

Original source URL and retrieval timestamp

Exact tool inputs and normalized output

Missing-data and rate-limit messages

A clear separation between facts and interpretation