io.github.S2thend/cursor-history
MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history
Open source Open in the app JSON README (API)
About
MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history
Details
- Kind
- MCP servers
- Topic
- No topic detected
- Publisher
- s2thend
- Origin
- official
- Category
- ferramentas
- Transport
- local
- Version
- 0.2.4
- Stars
- 32
- Forks
- 2
- Last push
- 2026-03-08T09:13:04Z
- Repository state
- ativo
- Language
- TypeScript
- License
- MIT
- Added
- 2026-08-29 03:02:13
- Updated
- 2026-08-29 03:02:13
- Origin id
io.github.S2thend/cursor-history
README
# Cursor History MCP
[🇨🇳 中文文档](docs/README_zh.md) | [🇫🇷 Français](docs/README_fr.md) | [🇪🇸 Español](docs/README_es.md)
<p align="center">
<img src="docs/cursor-history-mcp-logo.jpg" alt="cursor-history-mcp logo" width="200">
</p>
[](https://www.npmjs.com/package/cursor-history-mcp)
[](https://www.npmjs.com/package/cursor-history-mcp)
[](https://opensource.org/licenses/MIT)
[](https://nodejs.org/)
[](https://www.typescriptlang.org/)
[](https://cursor.com/install-mcp?name=cursor-history&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImN1cnNvci1oaXN0b3J5LW1jcCJdfQ==)
**MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history.**
Bring 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.
Free, open-source, and MIT licensed. Built by the community, for the community.
## Why This Project?
There 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:
| Feature | cursor-history-mcp (this project) | Other Solutions |
|---------|-----------------------------------|-----------------|
| 📦 **Setup** | ✅ `npx cursor-history-mcp` - zero install | ❌ Docker, Python, dependencies |
| ⚡ **Speed** | ✅ Instant - direct SQLite reads | ❌ Slow - requires LLM vectorization |
| 🔍 **Search** | ✅ Grep-style text matching - precise & stable | ❌ Vector retrieval - unpredictable results |
| 🤖 **LLM Required** | ✅ No - works offline | ❌ Yes - needs Ollama/embeddings |
| 🛠️ **Language** | ✅ TypeScript (type-safe) | ⚠️ Python |
| 💾 **Backup/Restore** | ✅ Built-in | ❌ Not available |
| 🚚 **Migration** | ✅ Move sessions between workspaces | ❌ Not available |
| 📋 **Dependencies** | ✅ Minimal (just Node.js) | ❌ Docker, LanceDB, Ollama, FastAPI |
### Key Advantages
- **Blazing Fast**: No embedding or vectorization step. Reads directly from Cursor's native SQLite database, so results are instant.
- **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.
- **Zero Configuration**: Run with `npx` - no Docker containers, no Python environments, no API keys, no LLM setup.
- **Works Offline**: Everything runs locally without any external services or AI models.
- **Data Portability**: Full backup, restore, and cross-workspace migration capabilities to keep your chat history safe and portable.
- **Lightweight**: ~50KB package vs multi-GB Docker images with vector databases.
## Installation
No installation required! Run directly via npx:
```bash
npx cursor-history-mcp
```
## Configuration
### Cursor
### Claude Code
Add to your Claude Code MCP settings:
```json
{
"mcpServers": {
"cursor-history": {
"command": "npx",
"args": ["-y", "cursor-history-mcp"]
}
}
}
```
### Claude Desktop
Add to your Claude Desktop configuration (`~/.claude/claude_desktop_config.json`):
```json
{
"mcpServers": {
"cursor-history": {
"command": "npx",
"args": ["-y", "cursor-history-mcp"]
}
}
}
```
## Available Tools
| Tool | Description |
|------|-------------|
| `cursor_history_list` | List chat sessions with metadata |
| `cursor_history_show` | View full conversation content |
| `cursor_history_search` | Search across all sessions |
| `cursor_history_export` | Export session to Markdown or JSON |
| `cursor_history_backup` | Create backup of all history |
| `cursor_history_restore` | Restore from backup (destructive) |
| `cursor_history_migrate` | Move/copy sessions between workspaces (destructive) |
| `cursor_history_year_pack` | Generate year-in-review data package with stats, topics, and prompt template |
## 🎆 Year in Review
Generate a personalized annual report from your Cursor AI chat history — discover your coding patterns, favorite topics, and development journey.
### What You Get
| | |
|---|---|
| 📊 **Chat Stats** | Total questions, active months, monthly activity |
| 🏷️ **Topic Discovery** | Auto-detected coding topics and interests |
| 📈 **Trend Tracking** | How your focus shifted throughout the year |
| 🔑 **Keywords** | Your most-used terms and phrases |
| 🔒 **Privacy Safe** | Sensitive data automatically masked |
| 📝 **LLM Prompt** | Ready-to-use prompt for a polished report |
### Try It
- "Generate my 2025 Cursor year in review"
- "Create a year pack for ~/myapp"
- "Generate my 2025 year in review in English"
## Usage Examples
After configuring, ask your AI assistant:
- "List my Cursor chat sessions"
- "Show me session #1"
- "Search my Cursor history for 'authentication'"
- "Export session #1 as markdown"
- "Backup my Cursor chat history"
## Requirements
- Node.js 20+
- Cursor IDE installed with existing chat history
## Contributing
Contributions are welcome! Whether it's bug reports, feature requests, documentation improvements, or code contributions—all PRs and issues are appreciated.
- [Open an issue](https://github.com/S2thend/cursor-history-mcp/issues)
- [Submit a pull request](https://github.com/S2thend/cursor-history-mcp/pulls)
## License
MIT