FoodData Central

This project demonstrates how to build an MCP server that enables AI agents to access the USDA FoodData Central API. It allows searching for foods, retrieving detailed nutritional information, and accessing comprehensive food data through keyword search and structured queries.

The server provides three essential food data access tools:
- search_foods: Search for foods using keywords with optional filters for data type, brand, date range, etc.
- get_food_details: Get comprehensive nutritional and ingredient information for a specific food item by FDC ID
- get_multiple_foods: Retrieve detailed information for multiple foods at once (up to 20 items)

git clone https://github.com/FelipeAdachi/mcp-food-data-central.git cd food-data-central-mcp

Create a.envfile based onenv.example:

Configure your environment variables in the.envfile (see Configuration section)

docker build -t food-data-central-mcp --build-arg PORT=8050 .

Create a.envfile based onenv.exampleand configure your environment variables

# Set TRANSPORT=sse in .env then: uv run src/main.py

The MCP server will essentially be run as an API endpoint that you can then connect to with config shown below.

With stdio, the MCP client itself can spin up the MCP server, so nothing to run at this point.

docker run --env-file .env -p 8050:8050 food-data-central-mcp

The MCP server will essentially be run as an API endpoint within the container that you can then connect to with config shown below.

With stdio, the MCP client itself can spin up the MCP server container, so nothing to run at this point.

Once you have the server running with SSE transport, you can connect to it using this configuration:

{ "mcpServers": { "food-data-central": { "transport": "sse", "url": "http://localhost:8050/sse" } } }

Note for Windsurf users: UseserverUrlinstead ofurlin your configuration:

{ "mcpServers": { "food-data-central": { "transport": "sse", "serverUrl": "http://localhost:8050/sse" } } }

Note for n8n users: Use host.docker.internal instead of localhost since n8n has to reach outside of its own container to the host machine:

Make sure to update the port if you are using a value other than the default 8050.

Add this server to your MCP configuration for Claude Desktop, Windsurf, or any other MCP client:

A nutrition analysis platform integrating Canada's Food Guide recipes with Health Canada's official nutrition databases.

Interact with DROMA drug-omics association analysis databases using natural language.

Enhanced Medication Information MCP Server

Provides real-time access to FDA drug data, including shortages, labeling, and recalls, via the openFDA API.

FDA-only compliance data MCP (recalls, warning letters, inspections, 483s, approvals, CFR parts).

Source-provenanced US federal healthcare provider data over MCP. Resolve any NPI or CCN across NPPES, OIG LEIE, SAM.gov, state Medicaid exclusions, CMS PECOS, Care Compare, and Open Payments — every field carries a 14-field provenance contract, and an "excluded or compromised anywhere" check runs on every lookup.

Unofficial server for accessing Open Targets platform data for gene-drug-disease associations research.

Access nutrition information for over 600,000 foods from the USDA FoodData Central database.

A search server for PubMed, the biomedical literature database, using a pure Node.js implementation.

Unified access to global medical terminologies: ICD-11, SNOMED CT, LOINC, RxNorm, MeSH. 27 tools for medical coding, terminology lookup, and crosswalk mappings.