OpenStreetMap Tagging Schema MCP Server
Provides AI agents access to OpenStreetMap's comprehensive tagging knowledge base, enabling tag queries, preset discovery, and validation of OSM tags for mapping applications.
README
OpenStreetMap Tagging Schema MCP Server
<!-- Code Quality & Security -->
What is this?
This is a Model Context Protocol (MCP) server designed specifically for AI agents and LLM applications. It acts as a bridge between artificial intelligence systems and the comprehensive OpenStreetMap tagging knowledge base provided by the official @openstreetmap/id-tagging-schema library.
Current Status: Production-ready MCP server, actively maintained and continuously improved. The service is deployed and accessible at https://mcp.gander.tools/osm-tagging/.
We welcome your feedback! Have ideas for improvements? Found a bug? Want to discuss features? Please open an issue or start a discussion.
What this is NOT
⚠️ Important clarifications:
- Not a standalone application: This server requires integration with AI systems (like Claude Code or Claude Desktop) to be useful. It has no user interface or web frontend.
- Not for direct human use: Without an AI agent as an intermediary, this tool provides no value to end users. It's designed exclusively for programmatic access by LLM applications.
- Not a public API for general use: The deployed service at mcp.gander.tools is intended for integration with AI agents, not for direct HTTP requests or high-volume automated queries. Please do not attempt to abuse the service with DDoS attacks or excessive traffic.
If you're looking for a user-facing OSM tagging tool, consider iD editor or JOSM instead.
Features
7 MCP Tools organized into 3 categories:
- Tag Query (2 tools): Query tag values and search tags
- Preset Discovery (2 tools): Search and explore OSM presets with detailed configurations
- Validation (3 tools): Validate tags, check for deprecated tags, suggest improvements
📖 Full tool reference: docs/api/
Installation
Using npx (Recommended)
# No installation needed - run directly
npx @gander-tools/osm-tagging-schema-mcp
Using Docker
# Run with stdio transport
docker run -i ghcr.io/gander-tools/osm-tagging-schema-mcp:latest
📖 More options: docs/user/installation.md (source installation, verification, troubleshooting)
Quick Start
With Claude Code CLI
# Add to Claude Code
claude mcp add --transport stdio osm-tagging-schema -- npx -y @gander-tools/osm-tagging-schema-mcp
# Use in conversations
# Ask Claude: "What OSM tags are available for restaurants?"
# Ask Claude: "Validate these tags: amenity=parking, capacity=50"
With Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"osm-tagging-schema": {
"command": "npx",
"args": ["@gander-tools/osm-tagging-schema-mcp"]
}
}
}
📖 Next steps:
- Configuration Guide - Setup for Claude Code/Desktop and custom clients
- Usage Guide - Tool examples and workflows
- API Reference - Complete tool documentation
- Deployment Guide - Production HTTP/Docker deployment
Testing with MCP Inspector
Test and debug the server using the official MCP Inspector:
# Test published package (quickest)
npx @modelcontextprotocol/inspector npx @gander-tools/osm-tagging-schema-mcp
# Test Docker image
npx @modelcontextprotocol/inspector docker run --rm -i ghcr.io/gander-tools/osm-tagging-schema-mcp
The Inspector provides an interactive web UI to test all tools, inspect responses, and debug issues.
📖 Complete inspection guide: docs/development/inspection.md (includes HTTP transport testing)
Development
Built with Test-Driven Development (TDD) and Property-Based Fuzzing:
- Comprehensive test suite (unit + integration) with 100% pass rate
- Property-based fuzz tests with fast-check for edge case discovery
- Continuous fuzzing in CI/CD (weekly schedule + on every push/PR)
npm install # Install dependencies
npm test # Run all tests
npm run test:fuzz # Run fuzz tests
npm run build # Build for production
📖 Development guides: docs/development/development.md | docs/development/fuzzing.md
Contributing
Contributions welcome! This project follows Test-Driven Development (TDD).
- Fork and clone the repository
- Install dependencies:
npm install - Create a feature branch
- Write tests first, then implement
- Ensure all tests pass:
npm test - Submit a pull request
📖 Guidelines: docs/development/contributing.md
Documentation
Quick Navigation
Choose your path:
| I want to... | Go to |
|---|---|
| Install and run the server | Installation Guide |
| Configure with Claude Code/Desktop | Configuration Guide |
| Learn how to use the tools | Usage Guide → API Reference |
| Test and debug the server | Inspection Guide |
| Deploy in production (HTTP/Docker) | Deployment Guide |
| Fix issues or errors | Troubleshooting Guide |
| Contribute to the project | Contributing Guide |
Complete Documentation
User Guides:
- Installation - Setup guide (npx, Docker, source)
- Configuration - Claude Code/Desktop configuration
- Usage - Tool examples and workflows
- API Reference - Complete tool documentation
- Troubleshooting - Common issues and solutions
Developer Docs:
- Contributing - Contribution guidelines (TDD workflow)
- Development - Development setup and debugging
- Inspection - MCP Inspector testing guide
- Fuzzing - Security fuzzing and property testing
- Roadmap - Project roadmap and future features
- Release Process - Release and publishing workflow
Deployment Docs:
- Deployment - HTTP/Docker production deployment
- Security - Security features, provenance, and SLSA
Project Info:
- CHANGELOG.md - Version history
License
GNU General Public License v3.0 - See LICENSE file for details.
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。