📇 🏠 - Formats files using .editorconfig rules so AI-generated code follows project formatting standards
EditorConfig MCP Server
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
A Model Context Protocol (MCP) compliant server that formats files using .editorconfig rules.
This project started from a specific workflow issue I kept running into. I found that while working with AI coding agents, they would often generate code with minor formatting errors, like trailing whitespace or inconsistent newlines. Our linters would then flag these issues, and the agent would spend valuable cycles fixing its own simple mistakes.
This EditorConfig MCP Server is the tool I built to solve that problem for myself. It acts as a proactive formatting gatekeeper, using your project's .editorconfig rules to ensure files are correct from the start. My hope is that it might be useful to others who've encountered a similar frustration in their AI-assisted development process.
Installation
Global Installation (Recommended)
Then start the server:
Using npx (No Installation)
Local Installation
Then add to your project's scripts in package.json:
From Source
Features
- **MCP Compliant**: Follows all MCP design patterns and best practices
- **JSON Schema Validation**: All inputs are validated using JSON Schema
- **Rate Limiting**: Built-in rate limiting (100 requests/minute)
- **OpenAPI Spec**: Self-documenting API with OpenAPI 3.0 specification
- **Versioned API**: Uses semantic versioning with /v1/ prefix
- **Stateless**: No state retained between requests
- **Security**: Path validation prevents directory traversal attacks
- **Error Handling**: Consistent error format with helpful hints
Installation
Usage
Starting the Server
The server will start on port 8432 by default.
Configuration
- PORT - Server port (default: 8432)
- Default port chosen to avoid conflicts with common development servers
- Example: PORT=8080 editorconfig-mcp-server
Integration with AI Tools
Claude Code
To add this server to Claude Code, run:
Other MCP-Compatible Tools
This server is designed to be used with AI coding assistants that support MCP. Configure your AI tool to connect to:
- Base URL: http://localhost:8432
- Protocol: MCP over HTTP
API Endpoints
Tools (Actions)
POST /v1/tools/format_file
Format a single file using .editorconfig rules.
**Request:**
**Response:**
POST /v1/tools/format_files
Format multiple files matching a glob pattern.
**Request:**
**Response:**
Metadata
- GET /openapi.json - OpenAPI 3.0 specification
- GET /.well-known/mcp/servers.json - MCP server manifest
- GET /health - Health check endpoint
Error Handling
All errors follow a consistent format:
Rate Limiting
The server implements rate limiting:
- Window: 1 minute
- Max requests: 100 per window
- Returns 429 status when exceeded
Security
- Input validation using JSON Schema
- Path traversal protection
- Payload size limit (1MB)
- Ignores sensitive directories (node_modules, .git)
Versioning
This project follows Semantic Versioning: