Map Canvas MCP
Enables interactive map display with up to 50 marked places and optional route lines, using a bundled Leaflet UI and OpenStreetMap tiles.
README
Map Canvas MCP
An embedded interactive map for MCP Apps hosts such as ChatGPT. The Worker returns map data plus a stable UI loader. Each tool result selects a content-addressed Leaflet bundle served from Cloudflare Static Assets, so UI updates do not require refreshing unchanged tool metadata. The user's browser fetches visible OpenStreetMap tiles directly from the standard tile servers.
Production endpoint
https://map-canvas.android-mxdiego9.workers.dev/mcp
The endpoint is public and does not require authentication.
Local development
npm install
npm run check
npm run dev
npm run check type-checks the Worker and runs MCP smoke tests for
initialization, tool discovery, tool execution, and widget resource loading.
The local MCP endpoint is http://localhost:8787/mcp. Test it with the MCP
Inspector:
npx @modelcontextprotocol/inspector@latest
Deploy
Deploy from a terminal:
npm run deploy
No API key is required. Do not add secrets to source or wrangler.jsonc; use
Cloudflare secrets if authentication is added later.
Deploy with GitHub Actions
The included workflow deploys on every push to main, then runs the production
MCP smoke test against the public endpoint. It can also be run manually from the
Actions tab. Add these repository Actions secrets first:
CLOUDFLARE_API_TOKEN: a token scoped to edit Workers in the target accountCLOUDFLARE_ACCOUNT_ID: the target Cloudflare account ID
The values stay in GitHub Actions secrets and must not be committed to the repository.
Tool
show_map accepts 1–50 places with decimal latitude/longitude coordinates.
Simple callers can still use connectPlaces; travel itineraries can also add:
- day/date and time labels with day filtering
- categories and confirmed/planned/tentative status
- transport legs for walking, car, taxi, bus, rail, ferry, and flights
- schematic straight connections or actual route geometry
- verified place links, with a Google Maps coordinate link as the fallback
The widget uses numbered, category-colored markers, an itinerary panel, a reset-view action, and optional fullscreen presentation in ChatGPT. Schematic legs are dashed and explicitly labeled so they are not mistaken for turn-by-turn navigation.
Map data © OpenStreetMap contributors.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。