Server data from the Official MCP Registry
AI-native restaurant discovery with verified Menu Protocol data.
AI-native restaurant discovery with verified Menu Protocol data.
Remote endpoints: streamable-http: https://foodnear.me/mcp
Valid MCP server (1 strong, 0 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
5 tools verified · Open access · No issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"me-foodnear-foodnear-me": {
"url": "https://foodnear.me/mcp"
}
}
}From the project's GitHub README.
Model Context Protocol server for AI-native restaurant discovery — search verified restaurants, retrieve Menu Protocol menus, and validate structured menu data. Plug into Claude Desktop, Cursor, ChatGPT, or any MCP host in about 30 seconds.
Production endpoint: https://foodnear.me/mcp · 5 tools · 4 resources · 3 prompts · No API key (beta)
Cursor — ~/.cursor/mcp.json (macOS/Linux) or %USERPROFILE%\.cursor\mcp.json (Windows)
Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json (macOS), %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"foodnear-me": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://foodnear.me/mcp"]
}
}
}
“Find vegan Thai restaurants near Brooklyn Bridge and show me a menu for the top result.”
Your agent should call search_restaurants → get_menu (or get_restaurant first).
| Tool | Description |
|---|---|
search_restaurants | Search verified restaurants by lat/lng, cuisine query, dietary filters, ADO score |
get_restaurant | Restaurant profile with Schema.org JSON-LD + Menu Protocol extensions |
get_menu | Full Menu Protocol v1.0 menu (dietary flags, allergens, signatures) |
get_ado_score_breakdown | ADO score factors and improvement recommendations |
validate_menu_protocol | Validate a Menu Protocol JSON payload before publish |
| URI | Content |
|---|---|
foodnearme://spec/menu-protocol | Menu Protocol v1.0 specification |
foodnearme://spec/openapi | OpenAPI 3.1 spec pointer |
foodnearme://agent/skill | Agent skill summary |
foodnearme://examples/search-flow | Example search → menu flow |
| Prompt | Args | Guides agent to |
|---|---|---|
find_dinner_near_me | location (required), cuisine?, dietary? | search_restaurants → get_menu |
dietary_constrained_menu | restaurant_id, restrictions | get_menu with explicit MP flags/allergens |
validate_my_menu | strict? (true for strict mode) | validate_menu_protocol |
| Setting | Value |
|---|---|
| MCP URL | https://foodnear.me/mcp |
| Transport | HTTP JSON-RPC (POST); discovery via GET /mcp |
| Auth | None during beta (rate limits apply) |
| Registry | me.foodnear/foodnear-me (official MCP Registry) |
Preview / local: Replace the URL with http://localhost:3000/mcp when running npm run dev in apps/web.
┌─────────────────────┐ POST /mcp (JSON-RPC) ┌─────────────────────────┐
│ MCP host │ ────────────────────────────▶│ apps/web/app/mcp │
│ (Cursor / Claude) │ GET /mcp (discovery) │ Next.js route handler │
└─────────────────────┘ └────────────┬────────────┘
│
▼
┌─────────────────────────┐
│ Supabase + PostGIS │
│ Menu Protocol (MP) │
└─────────────────────────┘
Implementation: apps/web/app/mcp/route.ts · Flow runner: apps/web/lib/mcp/mcp-flow-runner.ts
Failed tools/call responses include structured metadata in _meta.error:
| Field | Meaning |
|---|---|
code | VALIDATION_ERROR · NOT_FOUND · UPSTREAM · RATE_LIMITED · UNKNOWN |
message | What went wrong |
hint | How to fix the request |
retryable | Whether the agent should retry |
docs | https://foodnear.me/docs#quick-start |
Human-readable text is still in content[0].text for hosts that ignore _meta.
From repo root (with apps/web dev server running for localhost):
# Automated agent flows (13 flows when Supabase + seed configured; 10 without DB)
npm run test:mcp-flows
# Against production
npm run test:mcp-flows:http
# Discovery GETs + MCP tools/list count
npm run smoke:mcp
# Full deploy gate (13 checks)
npm run preflight -w web
# or: ./apps/web/scripts/deploy-preflight.sh https://foodnear.me
Production monitoring: GitHub Actions workflow MCP Production Smoke runs smoke:mcp daily and on manual dispatch (.github/workflows/mcp-smoke.yml).
| File | URL |
|---|---|
llms.txt | https://foodnear.me/llms.txt |
llms-full.txt | https://foodnear.me/llms-full.txt |
| MCP manifest | https://foodnear.me/.well-known/mcp-server.json |
| AgentRoot | https://foodnear.me/.well-known/agentroot.json |
| Skill file | https://foodnear.me/SKILL.md |
| OpenAPI | https://foodnear.me/openapi.json |
| Web quick reference | https://foodnear.me/docs |
Scripted flows: apps/web/docs/example-agent-flows.md
verification_status: verified restaurants appear in search_restaurants.dietary.* flags and allergens[]; do not infer from dish titles.Do I need an API key?
No for beta MCP access. Future paid tiers may use API keys or x402 (USDC on Base). See x402-prepaid-spec.md in your local docs/Food Near Me playbook.
Tools not showing after restart?
Confirm the config URL ends with /mcp. Restart the host completely. Run npm run smoke:mcp against your target base URL.
Empty search results?
Beta data is seeded for specific metros (e.g. Williamsburg, NYC). Use coordinates near 40.7128, -74.006 for demos, or run npm run db:seed -w web locally.
Cursor vs Claude config path?
See Quick start above — each host uses a different JSON file; only the mcpServers block matters.
How is this different from DoorDash / Uber Eats APIs?
We expose owner-verified Menu Protocol data for agents — not scraped aggregator menus or ordering checkout.
This repository ships the MCP server inside the foodnear.me web app:
| Path | Purpose |
|---|---|
apps/web | Next.js app — MCP at /mcp, landing, API routes |
packages/menu-protocol | Menu Protocol schema + validators |
database | Migrations, seeds, schema |
server.json | Official MCP Registry metadata |
Business strategy and runbooks live in a separate local docs folder (not in this repo) — see your team's docs/Food Near Me playbook.
npm install
cd apps/web && cp .env.example .env.local # Supabase keys
npm run dev # http://localhost:3000
npm run test:mcp-flows # POST localhost:3000/mcp
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.