Table of Content
AI Information
AI Tutorial
AI Agent
Latest Information
Hot Information
LLMs Information
Technical Frontiers
Industry Applications
Prompt Tutorial
AI Programming
AI Video Generation
AI Audio Generation
Knowledge Base Setup
AI Development Guides
Industry Tutorials
Practical Cases
AI Resource Library
Agent Information
Agent Setup
Agent Training

Baidu Map MCP Server Practice Guide

Written by
Iris Vance
Updated on:July-09th-2025
Recommendation

The first map service provider in China that is compatible with the MCP protocol, a practical guide for Baidu Map MCP Server.

Core content:
1. Baidu Map core API is fully compatible with the MCP protocol
2. Steps to create server-side AK and configuration files
3. Use windsurf editor to load and verify Baidu Map MCP Server

Yang Fangxian
Founder of 53AI/Most Valuable Expert of Tencent Cloud (TVP)
Last week, Baidu Maps Core API was fully compatible with the MCP protocol, making it the first map service provider in China to be compatible with the MCP protocol. The MCP tool list currently provided includes 8 core API interfaces and MCP protocol docking, covering reverse geocoding, location retrieval, route planning , etc.
Let's practice how to use Baidu Map MCP Server.
1. Create a server AK in the Baidu Map Open Platform console
Only through AK can you call Baidu Map API capabilities
2. Open windsurf editor
Add the following configuration to the configuration file. BAIDU_MAP_API_KEY is the AK for accessing the Baidu Map Open Platform API.
{ "mcpServers": { "baidu-map": { "command": "npx", "args": [ "-y", "@baidumap/mcp-server-baidu-map" ], "env": { "BAIDU_MAP_API_KEY": "xxx" } } }}
Restart windsurf, and the settings panel has successfully loaded Baidu Map MCP Server. You can see that there are 8 available MCP tools, click them to view details.
Next, you can ask questions to verify the use of Baidu mcp.

Related PostsView More
Prompt-Tuning
In-depth analysis of Prompt-Tuning, an innovative method for fine-tuning large models, which is an efficient way to fine-tune parameters. By adding learnable sticky note parameters to the input layer, most of the original model parameters are frozen, achieving fast training, resource saving, small storage and good results without affecting the original model. The code fully demonstrates its...
Jasper Cole
Teach you how to deploy large models in clusters
"Want to master the cluster deployment skills of large models? This article teaches you how to use AI tools step by step. It details the steps of hardware and software environment preparation, model downloading, and Ray cluster startup. Whether it is large model fine-tuning technology or how to fine-tune a large model, here are the answers you want. Click to read and find out!"
Iris Vance
A Plain Language Analysis of DPO: How to Let AI Learn Human Preferences Directly?
In-depth analysis of the unique charm of DPO in AI big models! This article explains in a popular way how DPO makes the output of big models more in line with human preferences, compares existing complex methods, and explains in detail its technical architecture and innovations. For example, how the model learns to "favor good answers" and how to obtain scores. Click to read to gain insight...
Jasper Cole