LearnHouse
Build, edit and run courses, learning paths and communities in your LearnHouse academy.
AI-native restaurant discovery: verified/menu-indexed/discovered tiers + signed allergy-safety data.
作者提供的原文
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-07-18 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 4/4 项(仅展示,不用于排序)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Food Near Me。按照 https://mcp.popnx.com/i/me-foodnear-foodnear-me.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/4 项检查 · 你的提问会经过开发者的服务器(foodnear.me) · ✓ 命令已检查 2026年11月20日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Food Near Mehttps://foodnear.me/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsFood Near Me
用 Food Near Me 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Food Near Me,或回答中出现 Food Near Me 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Food Near Mehttps://foodnear.me/mcp开启新聊天,输入前先从插件列表中选择 Food Near Me
用 Food Near Me 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Food Near Me,或回答中出现 Food Near Me 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user foodnear-me https://foodnear.me/mcp应能看到 Food Near Me 在列表中并显示已连接
用 Food Near Me 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Food Near Me,或回答中出现 Food Near Me 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 Food Near Me 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Food Near Me,或回答中出现 Food Near Me 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 Food Near Me 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Food Near Me,或回答中出现 Food Near Me 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://foodnear.me/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user foodnear-me https://foodnear.me/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"foodnear-me": {
"url": "https://foodnear.me/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"foodnear-me": {
"type": "http",
"url": "https://foodnear.me/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月16日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
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 vague p
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 plus
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, de
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 comple
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 ex
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 debugging
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}` (G
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 supported
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 encoded
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 `g
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月21日
注册名称已通过域名 foodnear.me 验证(注册中心会核实域名所有权)
代码最后更新于21天前
不适用:由 foodnear.me 的所有者自己运行的云端服务器,你不会运行仓库里的代码
在 149 毫秒内响应(HTTP 200)
无需登录
已读取 10 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/me-foodnear-foodnear-me)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于21天前,最新版本(1.1.0)于4个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:LearnHouse, Anime Garden, WilmAI, Lumify Sports Intelligence, Savecraft
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Build, edit and run courses, learning paths and communities in your LearnHouse academy.
Finland's Wilma school system for parents and students: schedule, homework, exams and messages.
Schedules, scores, odds, splits & explainable AI bet confidence — 8+ sports, free instant key.
Savecraft serves real save game data and expert game knowledge to AI assistants.
| 本项 Food Near Me | LearnHouse | Anime Garden | WilmAI | Lumify Sports Intelligence | Savecraft | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 是 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 4/4 | 5/5 | 4/4 | 3/3 | 4/4 | 3/4 |
| 许可证 | – | AGPL-3.0 | AGPL-3.0 | MIT | MIT | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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)
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 | Three-tier geo search by lat/lng — verified → menu_indexed → discovered; check menu_available before get_menu |
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 |
explore_area_for_diet | Composite: bucketed neighborhood overview (verified / menu_indexed / discovered); optional dietary filter narrows the verified tier only |
compare_restaurants_for_diet | Composite: compare 2–5 known restaurants by dietary-eligible menu items and trust tier ranking |
find_restaurants_along_route | Composite: route-adjacent restaurant discovery between origin/destination with optional dietary ranking |
get_safety_attestation | Signed (Ed25519, fnm-safety-v1) allergy-safety tier statement for one restaurant; unknown + advisory when uncurated |
find_safe_places_near_me | The pack: at most 3 human-curated places for an allergy need, each with curator_checked_at; left_out cut line; explicit empty_state |
| 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.
Operational tool filter: set FNM_MCP_ENABLED_TOOLS=search_restaurants,get_menu to expose only a comma-separated subset in tools/list and GET /mcp. Leave unset or * to expose all tools. This is for temporary degradation/context control, not privacy or auth.
┌─────────────────────┐ 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 (14 flows when Supabase + seed configured; 11 without DB)
npm run test:mcp-flows
npm run test:mcp-flows:http
npm run smoke:mcp
npm run check:discovery-copy
npm run preflight -w web
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
search_restaurants returns verified → menu_indexed → discovered.verification_status and menu_available. Call get_menu only when menu_available is true.discovered → menu_indexed → verified. See https://foodnear.me/attribution for data sources.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 verified menus are seeded for specific metros (e.g. Williamsburg, NYC). 7 `menu_indexed` restaurants in Williamsburg have automated menus from website ingest. Discovered place listings cover many US metros — use coordinates in an imported region. Demo coords: 40.7128, -74.006. Run npm run db:seed -w web locally for verified test data.
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
menu_indexed website ingestPromote discovered → menu_indexed via free website/ordering-platform parsers (ChowNow API, order.online, Sauce, Squarespace, BentoBox, Toast, Playwright). Always dry-run first — headless is slow.
cd apps/web
npm run db:probe:menu-batch -- --headless --limit=10 npm run db:import:menu-indexed:website:headless:dry-run -- --limit=10 npm run db:import:menu-indexed:website:headless -- --limit=10 # live
No Uber Eats / DoorDash / Grubhub / RapidAPI scrapers. See apps/web/docs/example-agent-flows.md.