{ "markdown": "# Cursor History MCP\n\n[🇨🇳 中文文档](docs/README_zh.md) | [🇫🇷 Français](docs/README_fr.md) | [🇪🇸 Español](docs/README_es.md)\n\n

\n \"cursor-history-mcp\n

\n\n[![npm version](https://img.shields.io/npm/v/cursor-history-mcp.svg)](https://www.npmjs.com/package/cursor-history-mcp)\n[![npm downloads](https://img.shields.io/npm/dm/cursor-history-mcp.svg)](https://www.npmjs.com/package/cursor-history-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Node.js](https://img.shields.io/badge/Node.js-20%2B-green.svg)](https://nodejs.org/)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.0%2B-blue.svg)](https://www.typescriptlang.org/)\n\n[![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/install-mcp?name=cursor-history&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImN1cnNvci1oaXN0b3J5LW1jcCJdfQ==)\n\n**MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history.**\n\nBring your Cursor AI chat history directly into Claude. Search past conversations, export sessions, create backups, and generate year-in-review reports—all through natural language. Built on the [Model Context Protocol](https://modelcontextprotocol.io/) for seamless AI assistant integration.\n\nFree, open-source, and MIT licensed. Built by the community, for the community.\n\n## Why This Project?\n\nThere are other Cursor history tools out there (like the Python-based [Cursor-history-MCP](https://github.com/Nossim/Cursor-history-MCP)). Here's what makes this one different:\n\n| Feature | cursor-history-mcp (this project) | Other Solutions |\n|---------|-----------------------------------|-----------------|\n| 📦 **Setup** | ✅ `npx cursor-history-mcp` - zero install | ❌ Docker, Python, dependencies |\n| ⚡ **Speed** | ✅ Instant - direct SQLite reads | ❌ Slow - requires LLM vectorization |\n| 🔍 **Search** | ✅ Grep-style text matching - precise & stable | ❌ Vector retrieval - unpredictable results |\n| 🤖 **LLM Required** | ✅ No - works offline | ❌ Yes - needs Ollama/embeddings |\n| 🛠️ **Language** | ✅ TypeScript (type-safe) | ⚠️ Python |\n| 💾 **Backup/Restore** | ✅ Built-in | ❌ Not available |\n| 🚚 **Migration** | ✅ Move sessions between workspaces | ❌ Not available |\n| 📋 **Dependencies** | ✅ Minimal (just Node.js) | ❌ Docker, LanceDB, Ollama, FastAPI |\n\n### Key Advantages\n\n- **Blazing Fast**: No embedding or vectorization step. Reads directly from Cursor's native SQLite database, so results are instant.\n- **Grep-Style Search**: Uses direct text matching instead of vector retrieval. More lightweight, predictable, and stable for most use cases—no hallucinated results, no embedding drift, and exact matches every time.\n- **Zero Configuration**: Run with `npx` - no Docker containers, no Python environments, no API keys, no LLM setup.\n- **Works Offline**: Everything runs locally without any external services or AI models.\n- **Data Portability**: Full backup, restore, and cross-workspace migration capabilities to keep your chat history safe and portable.\n- **Lightweight**: ~50KB package vs multi-GB Docker images with vector databases.\n\n## Installation\n\nNo installation required! Run directly via npx:\n\n```bash\nnpx cursor-history-mcp\n```\n\n## Configuration\n\n### Cursor\n\n![cursor-mcp-setup](./docs/cursor-mcp-setup.gif)\n\n### Claude Code\n\nAdd to your Claude Code MCP settings:\n\n```json\n{\n \"mcpServers\": {\n \"cursor-history\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"cursor-history-mcp\"]\n }\n }\n}\n```\n\n### Claude Desktop\n\nAdd to your Claude Desktop configuration (`~/.claude/claude_desktop_config.json`):\n\n```json\n{\n \"mcpServers\": {\n \"cursor-history\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"cursor-history-mcp\"]\n }\n }\n}\n```\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `cursor_history_list` | List chat sessions with metadata |\n| `cursor_history_show` | View full conversation content |\n| `cursor_history_search` | Search across all sessions |\n| `cursor_history_export` | Export session to Markdown or JSON |\n| `cursor_history_backup` | Create backup of all history |\n| `cursor_history_restore` | Restore from backup (destructive) |\n| `cursor_history_migrate` | Move/copy sessions between workspaces (destructive) |\n| `cursor_history_year_pack` | Generate year-in-review data package with stats, topics, and prompt template |\n\n## 🎆 Year in Review\n\nGenerate a personalized annual report from your Cursor AI chat history — discover your coding patterns, favorite topics, and development journey.\n\n### What You Get\n\n| | |\n|---|---|\n| 📊 **Chat Stats** | Total questions, active months, monthly activity |\n| 🏷️ **Topic Discovery** | Auto-detected coding topics and interests |\n| 📈 **Trend Tracking** | How your focus shifted throughout the year |\n| 🔑 **Keywords** | Your most-used terms and phrases |\n| 🔒 **Privacy Safe** | Sensitive data automatically masked |\n| 📝 **LLM Prompt** | Ready-to-use prompt for a polished report |\n\n### Try It\n\n- \"Generate my 2025 Cursor year in review\"\n- \"Create a year pack for ~/myapp\"\n- \"Generate my 2025 year in review in English\"\n\n## Usage Examples\n\nAfter configuring, ask your AI assistant:\n\n- \"List my Cursor chat sessions\"\n- \"Show me session #1\"\n- \"Search my Cursor history for 'authentication'\"\n- \"Export session #1 as markdown\"\n- \"Backup my Cursor chat history\"\n\n## Requirements\n\n- Node.js 20+\n- Cursor IDE installed with existing chat history\n\n## Contributing\n\nContributions are welcome! Whether it's bug reports, feature requests, documentation improvements, or code contributions—all PRs and issues are appreciated.\n\n- [Open an issue](https://github.com/S2thend/cursor-history-mcp/issues)\n- [Submit a pull request](https://github.com/S2thend/cursor-history-mcp/pulls)\n\n## License\n\nMIT\n", "bytes": 5887, "sha": "2ee14549e561c7e58350039bdbf065e6523a4faa9d58afa694186aa4ab8e4ced", "repo_slug": "s2thend/cursor-history-mcp", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_s2thend_cursor_history_48095e16/readme" }