Sandbox
@baidu-maps/mcp

MCP server for Baidu Maps location tools

This repo packages Baidu Maps as an MCP server so agents can call geocoding, reverse geocoding, POI search, route planning, weather, traffic, and IP lookup tools. It works with any MCP-compliant client, and the README shows setup for Claude and Cursor through a simple server command and API key.

443 stars47 forksPythonUpdated 1y ago
Who it's for

Builders who want their agent to look up places, plan routes, and read live map data.

What it delivers

You can add real location intelligence to agent workflows without wiring each map API by hand.

What it does

Geocoding and reverse geocoding

Converts addresses to coordinates and coordinates back into address, region, and POI details.

POI search and details

Finds places by keyword, type, region, or radius, then fetches detailed information for a POI ID.

Route planning

Provides single-route and batch route matrix tools for driving, walking, cycling, and transit.

Weather and traffic lookup

Returns real-time and forecast weather plus road or region traffic conditions.

IP location and POI extraction

Looks up city and coordinates from an IP address and can extract POIs from free text with extra permission.

MCP client integration examples

Shows JSON config examples for MCP clients such as Claude and Cursor, plus Python and Node.js install commands.

How to get it

  1. 1Install the SDK
    pip install mcp-server-baidu-maps
  2. 2Run as a script
    python -m mcp_server_baidu_maps
  3. 3Install
    npm install @baidumap/mcp-server-baidu-map

README

中文| English


stars python MIT License pypi npm


🚀 Introduction

Baidu Map MCP Server is a fully MCP-compliant, open-source Location-Based Service (LBS) solution, providing a comprehensive suite of geospatial APIs and tools for developers and AI agents. As the first map service provider in China to support the Model Context Protocol (MCP), Baidu Map MCP Server bridges the gap between large language models (LLMs), AI agents, and real-world location data and services.

With Baidu Map MCP Server, you can easily empower your applications, LLMs, and agents with advanced mapping, geocoding, POI search, route planning, weather, traffic, and more — all via standardized, developer-friendly MCP interfaces.

Key Features:

  • Full MCP Protocol Support: Seamless integration with any MCP-compliant agent, LLM, or platform.
  • Rich LBS Capabilities: Geocoding, reverse geocoding, POI search, route planning (driving, walking, cycling, transit), weather, IP location, real-time traffic, and more.
  • Cross-Platform SDKs: Official Python and TypeScript SDKs, easy CLI and cloud deployment.
  • Enterprise-Grade Data: Powered by Baidu Maps' authoritative, up-to-date geospatial data.
  • High Performance & Stability: Recommended SSE (Server-Sent Events) access for low latency and high reliability.
  • Open Source & Extensible: MIT licensed, easy to customize and extend.

Whether you are building a travel assistant, logistics platform, smart city solution, or an LLM-powered agent, Baidu Map MCP Server provides the essential geospatial intelligence and tools you need.

The MCP Server architecture enables:

  • Seamless AI Integration: Allows LLMs and agents to understand and process location data naturally
  • Contextual Understanding: Provides rich geospatial context for more intelligent decision-making
  • Standardized Interfaces: Consistent API design following MCP principles for easy integration
  • Scalable Implementation: Suitable for projects of any size, from small applications to enterprise solutions

Whether you're building a navigation app, delivery service, smart city solution, or enhancing an AI agent with location awareness, Baidu Map MCP Server provides the tools and infrastructure you need to succeed.

🛠️ Supported Tools & APIs

Baidu Map MCP Server provides the following MCP-compliant APIs (tools):

Tool NameDescription
map_geocodeConvert address to geographic coordinates.
map_reverse_geocodeGet address, region, and POI info from coordinates.
map_search_placesSearch for global POIs by keyword, type, region, or within a radius.
map_place_detailsGet detailed info for a POI by its unique ID.
map_directions_matrixBatch route planning for multiple origins/destinations (driving, walking, cycling).
map_directionsPlan routes between two points (driving, walking, cycling, transit).
map_weatherQuery real-time and forecast weather by region or coordinates.
map_ip_locationLocate city and coordinates by IP address.
map_road_trafficQuery real-time traffic conditions for roads or regions.
map_poi_extract*Extract POI info from free text (requires advanced permission).

*Some advanced features require additional permissions. See Authorization for details.

All APIs follow the MCP protocol and can be called from any MCP-compliant client, LLM, or agent platform.

⚡ Quick Start

1. Get Your API Key

Register and create a server-side API Key (AK) at Baidu Maps Open Platform. Be sure to enable “MCP (SSE)” service for best performance.

2. Python Integration

Install the SDK:

pip install mcp-server-baidu-maps

Run as a script:

python -m mcp_server_baidu_maps

Configure in your MCP client (e.g., Claude, Cursor):

{
  "mcpServers": {
    "baidu-maps": {
      "command": "python",
      "args": ["-m", "mcp_server_baidu_maps"],
      "env": {
        "BAIDU_MAPS_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

3. Node.js/TypeScript Integration

Install:

npm install @baidumap/mcp-server-baidu-map

Configure in your MCP client:

{
  "mcpServers": {
    "baidu-map": {
      "command": "npx",
      "args": [
        "-y",
        "@baidumap/mcp-server-baidu-map"
      ],
      "env": {
        "BAIDU_MAP_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

4. Recommended: Use SSE for low-latency, stable access

See SSE Quickstart.

5. More Platforms

  • Claude/Agent/千帆AppBuilder: See README_zh.md for detailed integration guides and advanced configuration.

🚀 Advanced Use Cases

  • Travel Planning Assistant:
    Use map_search_places, map_directions, and map_weather to build an agent that plans optimal sightseeing routes, checks weather, and recommends POIs.

  • Batch Route Matrix:
    Use map_directions_matrix to calculate multiple routes and durations for logistics or delivery optimization.

  • Text-to-POI Extraction:
    Use map_poi_extract to extract POIs from user input or travel notes (requires advanced permission).

  • Real-time Traffic & Weather-aware Navigation:
    Combine map_road_traffic and map_weather for dynamic, context-aware travel suggestions.

  • Integration with Claude, Qianfan, AppBuilder:
    Seamlessly connect Baidu Map MCP Server to LLMs and agent frameworks for natural language geospatial reasoning.

See README_zh.md for more detailed Chinese documentation, configuration, and examples.


⛰️ Advanced Tutorials

👩‍👩‍👧‍👦 Contributors

🌟 Star History

Star History Chart

📄 License

MIT © baidu-maps

Files in the repo

Repository payload5 top-level entries
  • img
  • src
  • LICENSE
  • README_zh.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k