Datafood MCP Server

DataFood: 16 data sources (crypto/DeFi/security/news/finance) via one MCP. Bundles save ~92%.

Local serverstdio

What is the Datafood MCP server?

DataFood: 16 data sources (crypto/DeFi/security/news/finance) via one MCP. Bundles save ~92%. That is what the datafood mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

All 16 types share one schema, one auth, one billing surface.

The tools it exposes

The server publishes 4 tools. What each one is for:

  • datafood_query — Fetch one data type. Free 1-row preview
  • datafood_bundle — 1–20 queries across any types in a single call
  • datafood_portfolio_ask — NL Q&A on a Plaid-linked portfolio with citations
  • datafood_watch_session — Open a public /watch/{id} URL streaming agent events

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Datafood's toolset — datafood_query, datafood_bundle, datafood_portfolio_ask and 1 more — is a fair guide to whether it matches your workflow. It is maintained by atmflow55; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Datafood's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
datafood_queryFetch one data type. Free 1-row preview.
datafood_bundle1–20 queries across any types in a single call.
datafood_portfolio_askNL Q&A on a Plaid-linked portfolio with citations.
datafood_watch_sessionOpen a public /watch/{id} URL streaming agent events.

How to install the Datafood MCP server

{
  "mcpServers": {
    "datafood": {
      "transport": "http",
      "url": "https://toughlovesec.win/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Datafood to datafood query.
  • Use Datafood to datafood bundle.
  • Use Datafood to datafood portfolio ask.

Frequently asked questions

It connects Datafood to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (datafood_query, datafood_bundle, datafood_portfolio_ask, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Datafood directly.