Model Context Protocol
Connect your AI agent
Plug foodnear.me into Claude Desktop, Cursor, or any MCP host — 5 tools, 4 resources, 3 prompts, no API key during beta.
Quick start
- Open ~/.cursor/mcp.json or Claude Desktop's claude_desktop_config.json
- Paste the config below
- Restart your MCP host
{
"mcpServers": {
"foodnear-me": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://foodnear.me/mcp"]
}
}
}Endpoint: https://foodnear.me/mcp · mcp-server.json · llms.txt
Tools
search_restaurants— lat/lng search, cuisine, dietary, ADOget_restaurant— profile + Schema.org JSON-LDget_menu— Menu Protocol v1.0 menuget_ado_score_breakdown— ADO factors + recommendationsvalidate_menu_protocol— validate MP JSON before publish
Resources
- foodnearme://spec/menu-protocol
- foodnearme://spec/openapi
- foodnearme://agent/skill
- foodnearme://examples/search-flow
Prompts
find_dinner_near_me— location + optional cuisine/dietarydietary_constrained_menu— restaurant_id + restrictionsvalidate_my_menu— validate Menu Protocol JSON before publish
Tool errors
Failed tool calls return _meta.error with code, hint, and retryable so agents can self-correct.
VALIDATION_ERROR · NOT_FOUND · UPSTREAM
Canonical host documentation (FAQ, verify commands, architecture): GitHub README · foodnear.me