Proto Server
Enables AI assistants to explore and understand Protocol Buffer (.proto) files through fuzzy search, service definitions, and message structure analysis. Integrates with Cursor IDE to provide natural language queries about protobuf schemas and API definitions.
README
Quick Start Guide
Get up and running with MCP Proto Server in under 5 minutes.
Prerequisites
- Python 3.11 or later
- pip package manager
Setup Steps
Step 1: Clone the Repository
git clone https://github.com/umuterturk/mcp-proto.git
cd mcp-proto
Step 2: Install Dependencies
⚠️ Required: You must manually install Python dependencies.
pip install -r requirements.txt
This installs:
mcp- Model Context Protocol SDKprotobuf- Proto parsing supportrapidfuzz- Fast fuzzy searchwatchdog- File watching (optional)
Step 3: Configure Cursor
Add to your Cursor MCP settings file:
macOS: ~/Library/Application Support/Cursor/mcp.json
Windows: %APPDATA%\Cursor\mcp.json
{
"mcpServers": {
"proto-server": {
"command": "python",
"args": [
"/absolute/path/to/mcp-proto/mcp_proto_server.py",
"--root",
"/absolute/path/to/your/proto/files"
]
}
}
}
Important:
- Use absolute paths (not relative)
- Replace
/absolute/path/to/mcp-proto/with your clone location - Replace
/absolute/path/to/your/proto/fileswith your proto directory - Or use the included
examples/folder to test
Example for macOS:
{
"mcpServers": {
"proto-server": {
"command": "python",
"args": [
"/Users/yourname/mcp-proto/mcp_proto_server.py",
"--root",
"/Users/yourname/mcp-proto/examples"
]
}
}
}
Step 4: Restart Cursor
Close and reopen Cursor. The server will automatically start!
Note: Cursor automatically starts/stops the server. You don't need to run it manually.
Usage
Once configured, ask Cursor questions about your proto files:
- "What services are available?"
- "Show me the User message structure"
- "How do I authenticate?"
The AI will use three MCP tools to explore your protos:
search_proto- Fuzzy search across all definitionsget_service_definition- Get complete service with all RPCsget_message_definition- Get message with all fields
Troubleshooting
"Module not found" error:
- Run:
pip install -r requirements.txt - Check Python version:
python --version(need 3.11+)
"No proto files found":
- Verify the
--rootpath in your config points to a directory with.protofiles - Test:
find /path/to/protos -name "*.proto"
Server not appearing in Cursor:
- Ensure absolute paths are used in
mcp.json - Check Cursor's MCP logs for errors
- Restart Cursor completely
Optional: Testing Before Configuration
Want to verify everything works before configuring Cursor?
Step 3: Test the Installation (Optional)
Run the test suite:
python test_server.py
Expected output:
✓ Indexed 3 proto files
✓ Indexing: PASSED
✓ Search: PASSED
✓ Get Service: PASSED
✓ Get Message: PASSED
✓ Fuzzy Matching: PASSED
Or test the server manually:
# Test with included examples
python mcp_proto_server.py --root examples/
# Test with your own protos
python mcp_proto_server.py --root /path/to/your/protos
Press Ctrl+C to stop the server.
What's Next?
- USAGE.md - Detailed examples and JSON responses
- ARCHITECTURE.md - How the system works
- RECURSIVE_RESOLUTION.md - Efficiency features
Ready to explore your proto files with AI!
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。