Skip to main content

Cursor项目记忆文件创建器 - MCP服务,用于在当前项目的.cursor/目录下自动创建.mdc文件

Project description

Cursor Memory MCP

Python Version License: MIT smithery badge

🧠 Enable AI assistants to create and manage project memory files in Cursor through a simple MCP interface.

The Cursor Memory MCP Server provides a bridge between AI assistants and Cursor's project memory system through the Model Context Protocol (MCP). It allows AI models to automatically create and manage .mdc memory files in your project's .cursor/rules/ directory.

Project Screenshot Project Screenshot

✨ Core Features

  • 🧠 memory record: Automatically create task memory files in .cursor/rules/ directory
  • 📝 structure format: Generate properly formatted .mdc files following Cursor specifications
  • 🔄 context saving: Preserve task execution context for future reference
  • 🌐 multi-language: Full support for Chinese and international content
  • 💻 cross-platform: Works seamlessly on Windows, macOS, and Linux
  • MCP standard protocol: Built on the Model Context Protocol for seamless AI integration

🚀 Quick Start

Installing via pip

Install using uv for better performance and isolation:

# Install globally as a tool
uv tool install cursor-memory-mcp

# Update PATH to use the tool
uv tool update-shell

step1 . cursor settings --> MCP --> add configuration (reffered later)

step2 . cursor settings --> RULES --> add user rule:

After task execution is completed, use `cursor memory` to track task execution records

step3 . call agent to help you with coding

when you dev step by step, proj rules will record cursor operation history, and when cursor need them, it will reffer it and do your job with memory.

Installing for Development

For development and contributing:

# Clone and set up development environment
git clone https://github.com/yourusername/cursor-memory-mcp.git
cd cursor-memory-mcp

# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate  # Linux/macOS
# or
.venv\Scripts\activate     # Windows

# Install with development dependencies
pip install -e ".[dev]"

Alternative: Using uv (Recommended)

# Install globally
uv tool install cursor-memory-mcp

# For development
git clone https://github.com/yourusername/cursor-memory-mcp.git
cd cursor-memory-mcp
uv venv
source .venv/bin/activate  # Linux/macOS
# or
.venv\Scripts\activate     # Windows
uv pip install -e ".[dev]"

🔌 MCP Integration

Cursor Integration

Add this configuration to your Cursor MCP settings:

{
    "mcpServers": {
        "cursor-memory-mcp": {
            "command": "uv",
            "args": [
                "tool",
                "run",
                "cursor-memory-mcp",
            ]
        }
    }
}

Development Configuration

For development with local installation:

{
    "mcpServers": {
        "cursor-memory-mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/cloned/cursor-memory-mcp",
                "run",
                "cursor-memory-mcp",
            ]
        }
    }
}

💡 Available Tools

The server provides one powerful tool for memory management:

Memory Creation Tool

Create project memory files with comprehensive context:

result = await call_tool("create_cursor_memory", {
    "task_summary": "实现了用户认证系统,包括JWT token生成、密码加密验证和权限管理功能",
    "task_name": "user_authentication_system",
    "task_description": "用户认证和授权系统实现"
})

Parameters:

Parameter Type Required Description
task_summary string 详细的任务执行上下文总结
task_name string 简短的任务名称(用作文件名)
task_description string 可选的详细任务描述
project_path string 当前项目的绝对路径

Validation Rules:

  • task_name must contain only letters, numbers, underscores, and hyphens
  • task_summary cannot be empty or whitespace only
  • Files are automatically timestamped if duplicates exist

📁 Generated File Format

The server creates .mdc files with the following structure:

---
description: "get the summary of previous step: {task_description}"
globs:
alwaysApply: false
---
{task_summary}

🤝 Contributing

We welcome contributions of all kinds! Please see our Contributing Guide for details.

🙏 Acknowledgments


Made with ❤️ for the AI development community

Star ⭐ this repo if you find it helpful!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cursor_memory_mcp-0.1.1.tar.gz (20.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cursor_memory_mcp-0.1.1-py3-none-any.whl (7.2 kB view details)

Uploaded Python 3

File details

Details for the file cursor_memory_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: cursor_memory_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 20.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for cursor_memory_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 3b9d09de0b909c70aa46bfe4b71ac97fcdbf110382f5a0be0a6c68db90fda4cc
MD5 e51a969eb992fcf4eac5b64fd0be19c4
BLAKE2b-256 5e62bee1627243be9b1c2d2de8836dab75c186d23426a8058b0d3db9d94a8d33

See more details on using hashes here.

File details

Details for the file cursor_memory_mcp-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for cursor_memory_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 3f69fddfbc2c84d5ffd3c0e96bb195f1c871ad847b2ba009885b13abd4316c95
MD5 f740acf09f14a74a3060e94fee281a0a
BLAKE2b-256 66bd4ae8f7ae01249784d9104a4c7177c6a9df8be14ca169d3c33d118194dacc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page