MCP Servers

fatsecret-mcp-server

Enables searching and retrieving nutrition data, recipes, and managing food diary entries through the FatSecret API.

README

FatSecret MCP Server

A remote Model Context Protocol server for the FatSecret nutrition API, deployed on Cloudflare Workers.

MCP Tools

Tool	Description
`search_foods`	Search the FatSecret food database
`get_food`	Get detailed nutrition info for a food
`search_recipes`	Search for recipes
`get_recipe`	Get recipe details, ingredients, and instructions
`get_user_profile`	Get the authenticated user's profile
`get_user_food_entries`	Get food diary entries for a date
`add_food_entry`	Log a food entry to the user's diary
`get_weight_month`	Get weight entries for a month
`check_auth_status`	Check current authentication status

Self-Hosting

Prerequisites

A FatSecret developer account with API credentials
Wrangler CLI installed

Deploy

# Clone and install
git clone https://github.com/fcoury/fatsecret-mcp.git
cd fatsecret-mcp
npm install

# Create KV namespace and note the ID
npx wrangler kv namespace create OAUTH_KV

# Update wrangler.jsonc with your KV namespace ID

# Set the encryption secret (generate with: openssl rand -hex 32)
npx wrangler secret put COOKIE_ENCRYPTION_KEY

# Deploy
npm run deploy

Usage

Visit your deployed server URL (e.g. https://fatsecret-mcp-server.<you>.workers.dev)
Click Setup Your Account
Enter your FatSecret Client ID, Client Secret, and Consumer Secret
Connect your FatSecret account via OAuth
Copy the MCP configuration shown on the setup page into your MCP client

The configuration looks like:

{
  "mcpServers": {
    "fatsecret": {
      "url": "https://fatsecret-mcp-server.<you>.workers.dev/mcp",
      "transport": {
        "type": "http",
        "headers": {
          "Authorization": "Bearer <your-session-token>"
        }
      }
    }
  }
}

Development

npm run dev          # Local dev server on port 8787
npm run test         # Run tests (vitest)
npm run test:run     # Run tests once
npm run type-check   # TypeScript type checking
npm run format       # Format with Biome
npm run lint:fix     # Lint and auto-fix with Biome

License

MIT

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured

E2B

Using MCP to run code via e2b.

Official

Featured