Edamam Remote Food MCP
Edama remote MCP effectively gives an AI the ability to "understand" food in the same way a nutritionist would, by translating natural language descriptions, images or barcodes into structured nutrition and food.
Public MCP server for the Edamam Food Database API
Nutrition and food logging for AI applications
Feed your AI powered agent project with nutrition information from Edamam.
- Nutrition from plain language
- Food image analysis
- UPC/EAN barcode lookup
Production endpoint https://mcp.edamam.com/mcp/food
Copy
Get API keys Connect an MCP client Try Demos
Transport
Streamable HTTP
Tools
Nutrition + Vision
Auth
Bearer app_id:app_key
Starting at
$14/ month
Food MCP is included with Edamam Food Database API plans, with volume, rate limits, and Vision capacity that scale from pilot builds to production workloads.
Basic Vision 100,000 calls/month
$14
Core 750,000 calls/month
$69
Plus 5,000,000 calls/month
$299
Subscribe Compare plans
Why Food MCP
Food APIs are built for apps. MCP makes them useful inside agent workflows.
Edamam Food MCP turns the Food Database API into a small set of LLM-friendly tools. The agent keeps the conversation natural, while the server handles food parsing, quantity resolution, UPC lookup, nutrition calculation, and image-based dish analysis.
01
One endpoint for agents
Use a single MCP endpoint for initialize, tools/list, and tools/call. No custom adapter layer for every assistant or automation tool.
02
Nutrition from plain language
Send phrases like "cheddar cheese", "1 cup cooked rice", "200g chicken breast", or a UPC/EAN barcode.
03
Food image analysis
Provide a public image URL or base64 data URI and return detected food plus nutrition estimates from Edamam's Vision API.
Get API keys
In conversation
The agent asks naturally. The MCP server returns structured nutrition.
User
I had a chicken enchilada and a French onion soup with a slice of bread for lunch. How many calories in this
Agent
Based on the nutrition data provided (1 whole serving each):
Calories (lunch total)
- Chicken enchilada (1 whole): 503.7 kcal
- French onion soup (1 whole): 395.6 kcal
- Bread (1 slice): 79.5 kcal
Total calories: 978.7 kcal (approx 979 kcal)
get_food_nutrition({
"queries": ["1 chicken enchilada", "1 French onion soup", "1 slice of bread"]
})
User
Give me macro breakdown and what diets is this good for?
Agent
Macro breakdown (whole lunch)
- Protein: 53.0 g
- Carbs: 81.8 g
- Fat: 47.8 g
Diet fit: Best for a general omnivorous/balanced diet. This meal is not a strong fit for keto/low-carb, low-fat, low-sodium, vegan, vegetarian, gluten-free, or dairy-free eating patterns (includes wheat/gluten and milk cautions in the returned items).
MCP Agent Nutrition Assistant Demo
Look up nutrition facts for one or more foods described in plain text. Identify food in a image and return a full nutritional breakdown.
Get API keys Try Demos
Quick start
Connect your MCP client in minutes.
Add the server URL to your client and pass Edamam credentials as a bearer token. Discovery can connect first; actual tool calls require an Edamam Food Database API app_id and app_key.
Cursor VS Code Claude Code mcp-remote
.cursor/mcp.json Copy
{
"mcpServers": {
"edamam-food": {
"url": "https://mcp.edamam.com/mcp/food",
"headers": {
"Authorization": "Bearer <app_id>:<app_key>"
}
}
}
}
.vscode/mcp.json Copy
{
"servers": {
"edamam-food": {
"type": "http",
"url": "https://mcp.edamam.com/mcp/food",
"headers": {
"Authorization": "Bearer <app_id>:<app_key>"
}
}
}
}
terminal Copy
claude mcp add --transport http edamam-food \
https://mcp.edamam.com/mcp/food \
--header "Authorization: Bearer <app_id>:<app_key>"
stdio bridge Copy
{
"mcpServers": {
"edamam-food": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.edamam.com/mcp/food",
"--header",
"Authorization: Bearer <app_id>:<app_key>"
]
}
}
}
Tool surface
Two production tools, tuned for food questions.
The FastMCP server keeps the agent surface intentionally compact. Search, parsing, UPC recognition, and nutrient calculation are handled inside the nutrition tool; photos use a dedicated Vision tool.
tool
get_food_nutrition
Text or barcode
Look up calories, macros, diet labels, health labels, cautions, total nutrients, daily values, and resolved ingredient data for one or more foods.
| Argument | Type | Required | Description |
|---|---|---|---|
| queries | list[string] | Yes | One phrase per food item, such as "1 cup rice", "200g chicken breast", or "049000042566". |
Example JSON-RPC call
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "get_food_nutrition",
"arguments": {
"queries": ["1 croissant", "1 egg"]
}
},
"id": 3
}
tool
analyze_food_image
Image URL or base64
Identify food in a photograph and return the detected item, quantity, measure, ingredient lines, calories, labels, cautions, and full nutrient breakdown.
| Argument | Type | Required | Description |
|---|---|---|---|
| image | string | Yes | A public http/https URL or data:image/... base64 URI. |
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "analyze_food_image",
"arguments": {
"image": "https://example.com/plate.jpg"
}
},
"id": 4
}
Authentication
Use your Edamam credentials without storing them on the MCP server.
Tool calls use the Food Database API credentials supplied by the caller. Send a bearer token with the app_id and app_key joined by a colon.
HTTP header Copy
Authorization: Bearer <app_id>:<app_key>
For self-hosting: set EDAMAM_APP_ID and EDAMAM_APP_KEY as fallback credentials, or require every caller to pass the Authorization header.
Developer documentation
Everything needed to test, self-host, and integrate.
The public endpoint is for immediate MCP clients. The GitHub repository contains the FastMCP server, shared auth and logging code, pytest coverage, deployment notes, and examples for direct JSON-RPC calls.
Get API keys Food Database API docs MCP Streamable HTTP spec
1
Initialize
Client sends initialize to negotiate capabilities and receives an MCP-Session-Id.
2
Discover tools
Client calls tools/list and receives schemas for get_food_nutrition and analyze_food_image.
3
Call tools
Client sends tools/call with the session id and Edamam bearer credentials.
API coverage
Mapped to the Food Database API paths agents need most.
| Food Database capability | MCP mapping | Status |
|---|---|---|
| Parser search by food name or UPC | Internal step in get_food_nutrition | Available |
| Nutrients endpoint | get_food_nutrition | Available |
| Nutrients from image | analyze_food_image | Available |
| Autocomplete and browse filters | Not exposed as MCP tools | Out of scope |
Plans
Included with Edamam Food Database API plans.
Edamam lists Food MCP as included with Food Database API plans. Choose the plan by API volume, Vision usage, throttling, caching rights, and support needs.
Enterprise
Basic Vision
$14 / month
- 100,000 calls/month
- 50 food and nutrition calls/min
- 500 Vision requests/month
- 30 day trial period Subscribe
Enterprise
Core
$69 / month
- 750,000 calls/month
- 100 food and nutrition calls/min
- Vision pay as you go
- Email and phone support Subscribe
Enterprise
Plus
$299 / month
- 5,000,000 calls/month
- 300 food and nutrition calls/min
- 10,000 Vision requests/month
- Email and phone support Subscribe
Plan details change over time. Confirm current prices, quotas, caching rights, and terms on the Edamam Food Database API page before launch.
Security and usage
Read-only food data, with API-key responsibility at the client edge.
Keep app keys private
Never commit app_key values to source control or paste them into shared prompts. Treat them like passwords.
Human initiated usage
Edamam API terms restrict automated collection, scraping, or building a copy of returned data.
Attribution required
When showing Edamam nutrition data to end users, display the required Edamam attribution and link.
Informational output
Nutrition and Vision results should be presented as estimates for product use, not as medical or dietary advice.
Get API keys
FAQ
Common setup questions.
Do I need Edamam API keys before connecting an MCP client?
You can connect to the public Food MCP endpoint and discover available tools first. To run actual tool calls, you need an Edamam Food Database API app_id and app_key sent as a Bearer token.
How do I subscribe to a Food MCP plan?
Choose a Food Database API plan from the pricing section or the signup modal, create your API account, and then log in to complete the next billing step for API access.
Does the server store my Edamam credentials?
No. Public-client calls pass credentials in the Authorization header. Self-hosted deployments may set environment variables as fallback credentials.
Why is there no standalone search_food tool?
The current FastMCP implementation resolves food search internally inside get_food_nutrition. A separate search-only tool can be added later if user workflows need browse-style results.
Related Servers
Copus
Search human-curated content recommendations from real people who explain why resources are valuable - The Internet Treasure Map
Fabric Marketplace
An agent-native marketplace API where any participant ("Node") can publish allocatable resources, search for what they need, negotiate structured offers, and exchange contact details after mutual acceptance.
BibTeX MCP Server
Search academic references from arXiv, DBLP, Semantic Scholar, and OpenAlex, and generate BibTeX entries.
Sleeper Hit Studio Public Discovery
Read-only discovery for opted-in screenwriters and writer-approved public project assets.
arXiv LaTeX
Fetches and processes arXiv papers using LaTeX source for accurate equation handling.
Banana Prompts MCP Server
MCP server that allows you to search for high-quality AI art prompts directly from Banana Prompts (bananaprompts.fun).
IndieStack
Search and discover 130+ curated indie SaaS tools from your AI coding assistant
BrowseAI Dev
Evidence-backed web research for AI agents. BM25+NLI claim verification, confidence scores, citations, contradiction detection. 12 MCP tools. Works with Claude Desktop, Cursor, Windsurf. Python SDK (pip install browseaidev), LangChain, CrewAI, LlamaIndex integrations. npx browseai-dev
NPM Search
Search for npm packages
ArXiv-MCP
Search and retrieve academic papers from arXiv based on keywords.