Food Near Me

food-near-me/platform

Gives your AI agent eight restaurant discovery tools backed by Menu Protocol validated menus. The three-tier search returns verified, menu_indexed, and discovered restaurants with structured dietary flags and allergen data. You get geographic search by lat/lng, full menu retrieval with dietary filtering, ADO score breakdowns, and composite tools for route-based discovery and restaurant comparison. Ships with resources for the Menu Protocol spec and three prompts that guide common flows. No API key during beta. Drop the npx command into Claude Desktop or Cursor's MCP config and you're querying Supabase-backed restaurant data with PostGIS search in under a minute. Useful when you need structured, citation-ready menu data instead of scraping review sites.

tools: 10
transport: HTTP
last updated: Jul 18, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://foodnear.me/mcp --name foodnear-me

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http foodnear-me https://foodnear.me/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 10 tools

Verified live against the running server on Nov 6, 2026.

search_restaurantsCall this tool when the user wants restaurant or food discovery near a known location and may need menu trust signals. Input Requirements (CRITICAL): provide either flat `lat`/`lng` or Google-style `locationBias.circle.center.latitude`/`longitude`; if the user gave only a vagu...

Call this tool when the user wants restaurant or food discovery near a known location and may need menu trust signals. Input Requirements (CRITICAL): provide either flat `lat`/`lng` or Google-style `locationBias.circle.center.latitude`/`longitude`; if the user gave only a vagu...

No parameters. Call it with no arguments.

get_restaurantCall this tool after `search_restaurants` when you need a detailed restaurant profile for a returned `id`. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a `search_restaurants` result; do not invent IDs. Returns Schema.org/Restaurant JSON-LD markup p...1 params

Call this tool after `search_restaurants` when you need a detailed restaurant profile for a returned `id`. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a `search_restaurants` result; do not invent IDs. Returns Schema.org/Restaurant JSON-LD markup p...

Parameters* required

restaurant_id*string

Restaurant UUID (from search_restaurants results)

get_menuCall this tool only when a `search_restaurants` or `get_restaurant` response has `menu_available: true`. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a prior FNM result. Returns the full menu in Menu Protocol v1.0 format with item dietary booleans,...1 params

Call this tool only when a `search_restaurants` or `get_restaurant` response has `menu_available: true`. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a prior FNM result. Returns the full menu in Menu Protocol v1.0 format with item dietary booleans,...

Parameters* required

restaurant_id*string

Restaurant UUID (from search_restaurants results)

get_ado_score_breakdownCall this tool when a restaurant owner, operator, or agent wants to understand why a restaurant is more or less agent-ready. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a FNM result. Shows ADO (Agent Discovery Optimization) scoring across menu com...1 params

Call this tool when a restaurant owner, operator, or agent wants to understand why a restaurant is more or less agent-ready. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a FNM result. Shows ADO (Agent Discovery Optimization) scoring across menu com...

Parameters* required

restaurant_id*string

Restaurant UUID

get_safety_attestationCall this tool when you need a citable, tamper-evident allergy-safety statement for ONE restaurant — for example before telling a user a place is safe for a severe allergy. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a prior FNM result. Returns an...1 params

Call this tool when you need a citable, tamper-evident allergy-safety statement for ONE restaurant — for example before telling a user a place is safe for a severe allergy. Input Requirements (CRITICAL): `restaurant_id` MUST be a UUID copied from a prior FNM result. Returns an...

Parameters* required

restaurant_id*string

Restaurant UUID

validate_menu_protocolCall this tool when validating a draft or exported Menu Protocol payload before submission or integration. Input Requirements (CRITICAL): provide a JSON object in `payload`; set `strict: true` when checking formal spec compliance, and leave strict false for exploratory debuggi...2 params

Call this tool when validating a draft or exported Menu Protocol payload before submission or integration. Input Requirements (CRITICAL): provide a JSON object in `payload`; set `strict: true` when checking formal spec compliance, and leave strict false for exploratory debuggi...

Parameters* required

payload*object

The Menu Protocol JSON payload to validate. Should include version, domain, restaurant, and menu objects.

strictboolean

If true, schema warnings are promoted to errors and `valid` reflects strict spec compliance. Default: false (lenient mode).default: false

explore_area_for_dietCall this tool when the user wants a neighborhood overview that surfaces trust tiers explicitly — for example, "what's good for vegan eaters within a mile of this location" or "survey the area around X". Input Requirements (CRITICAL): `location` MUST be `{latitude, longitude}`...4 params

Call this tool when the user wants a neighborhood overview that surfaces trust tiers explicitly — for example, "what's good for vegan eaters within a mile of this location" or "survey the area around X". Input Requirements (CRITICAL): `location` MUST be `{latitude, longitude}`...

Parameters* required

dietaryarray

Optional dietary filter applied with AND logic. Only narrows the verified tier; menu_indexed and discovered rows pass through unfiltered (matches search_restaurants semantics).

location*object

Center of the area to explore (Google-style nested latitude/longitude).

radius_metersnumber

Default 1000 m (about 0.62 mi). Max 80467 m (50 miles).

top_n_per_tierinteger

Default 3, max 10. Each tier bucket is trimmed independently.

compare_restaurants_for_dietCall this tool when the user wants a side-by-side dietary comparison for 2 to 5 specific restaurants already identified in FNM results. Input Requirements (CRITICAL): `restaurant_ids` MUST be UUIDs copied from prior FNM responses, and `dietary` MUST include at least one suppor...3 params

Call this tool when the user wants a side-by-side dietary comparison for 2 to 5 specific restaurants already identified in FNM results. Input Requirements (CRITICAL): `restaurant_ids` MUST be UUIDs copied from prior FNM responses, and `dietary` MUST include at least one suppor...

Parameters* required

dietary*array

Dietary flags applied with AND logic at item level.

restaurant_ids*array

UUIDs copied from prior search_restaurants results.

user_locationobject

Optional caller location. When set, each compared restaurant carries `distance_meters` (great-circle from this point) and distance becomes the final tiebreaker after item_count and trust tier. Rest...

find_restaurants_along_routeCall this tool when the user wants route-adjacent dining options between two known coordinates and may care about dietary fit. Input Requirements (CRITICAL): both `origin` and `destination` MUST be `{latitude, longitude}` objects; optional `route_polyline` MUST be a valid enco...5 params

Call this tool when the user wants route-adjacent dining options between two known coordinates and may care about dietary fit. Input Requirements (CRITICAL): both `origin` and `destination` MUST be `{latitude, longitude}` objects; optional `route_polyline` MUST be a valid enco...

Parameters* required

destination*object

Route end coordinates.

dietaryarray

Optional dietary filter. When set, route ranking prefers restaurants with more matching menu items.

max_resultsinteger

Default 5, max 20.

origin*object

Route start coordinates.

route_polylinestring

Optional encoded polyline from the caller's routing source (Google encoded polyline format).

find_safe_places_near_meCall this tool when the user needs a place that is safe for a specific allergy or diet near a location — for example "where can my celiac kid eat near Brickell tonight". Input Requirements (CRITICAL): `location` MUST be `{latitude, longitude}`; `needs` MUST list one or more of...5 params

Call this tool when the user needs a place that is safe for a specific allergy or diet near a location — for example "where can my celiac kid eat near Brickell tonight". Input Requirements (CRITICAL): `location` MUST be `{latitude, longitude}`; `needs` MUST list one or more of...

Parameters* required

location*object

Where the user is or will be (Google-style nested latitude/longitude).

needs*array

Allergy needs the place must be curated for, AND semantics. One or more of: gluten_free, dairy_free, nut_aware, vegetarian.

open_now_onlyboolean

When true, places closed right now are left out and counted in left_out.reasons.closed_now.

radius_milesnumber

Default 12 (curated allergy places are sparse). Max 20.

time_zonestring

IANA time zone for open-now evaluation. Default America/New_York.

Readme

Food Near Me — MCP Server

Model Context Protocol server for AI-native restaurant discovery — three-tier search (verified → menu_indexed → discovered), Menu Protocol menus, and structured menu validation. Plug into Claude Desktop, Cursor, ChatGPT, or any MCP host in about 30 seconds.

Production endpoint: https://foodnear.me/mcp · 8 tools · 4 resources · 3 prompts · No API key (beta)

Quick start {#quick-start}

1. Add this to your MCP host config

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"]
    }
  }
}

2. Restart your MCP host

3. Try a prompt

View the full README on GitHub

Details

Repository: github.com/food-near-me/platform
Website: foodnear.me
Category: Data & Analytics
Transport: HTTP
Registry: MCP registry, active
Resources: 4
Prompts: 3
Tools verified: Nov 6, 2026

Related Data & Analytics MCP servers

View all

SkillAuditmegamind-0x/skillauditSecurity scanner for AI agent skills and MCP servers. Detects credential theft, data exfiltration, prompt injection, obfuscated code, and 80+ threat patterns. F0stars

Mercury X402 Mcpmercuryx402/mercury-x402-mcpAgent-payable web data over x402: 18 keyless services an agent pays per call.0stars

Microquery Mcpmicroqueryhq/microquery-mcpSQL over real-world data — FDA, SEC, blockchain, genomics, CVEs, and more. No config.0stars

Stocksensemikejj-creation/stocksenseFinancial data for AI agents: SEC filings, price history, insider trades, and more.0stars

Mirabello Immigration Intelligencemirabello-consultancy/mcp-serverCitizenship, residency & tax-residency data for 190+ countries, with origin-aware route planning0stars

Aide Mcp Servernetapp/aide-mcp-serverMCP server for NetApp AI Data Engine0stars