What runtime does Cursor History require?
Node.js 20+ and a Cursor IDE installation with existing chat history.

@S2thend
Basic information
Bring your Cursor AI chat history directly into Claude. Search past conversations, export sessions, create backups, and only MCP to migrate chat sessions to new project dir and generate year-in-review reports—all through natural language. Built on the Model Context Protocol for s
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cursor-history": {
"command": "npx",
"args": [
"-y",
"cursor-history-mcp"
]
}
}
}List Cursor AI chat sessions. Returns recent sessions with metadata including workspace, message count, and timestamps.
Show the full content of a specific Cursor AI chat session including all messages, tool calls, and AI responses.
Search across all Cursor AI chat sessions for a keyword or phrase. Returns matching sessions with context around each match.
Export a Cursor AI chat session to Markdown or JSON format. Returns the formatted content.
Create a backup of all Cursor AI chat history. Saves a portable archive that can be restored later.
⚠️ DESTRUCTIVE: Restore Cursor AI chat history from a backup file. This operation OVERWRITES your current chat history. Consider creating a backup of your current data first using cursor_history_backup.
⚠️ DESTRUCTIVE: Move or copy chat sessions between workspaces. When moving (not copying), the original session is deleted. Consider creating a backup first using cursor_history_backup.
Generate a year-in-review data package from Cursor AI chat history. Produces a sanitized JSON summary with statistics, topics, and keywords, plus a prompt template for LLM-based report generation. Read-only operation.
Cursor History is an MCP (Model Context Protocol) server that exposes your Cursor AI chat history to AI assistants like Claude. It lets you browse, search, export, back up, and migrate Cursor chat sessions—all through natural language, directly reading from Cursor’s native SQLite database.
Run the server with a single npx cursor-history-mcp command (no installation required). Then configure the MCP settings in Cursor, Claude Code, or Claude Desktop by adding the server definition with command: "npx" and args: ["-y", "cursor-history-mcp"]. After setup, use natural language requests like “List my Cursor chat sessions” or “Search my Cursor history for ‘authentication’”.
npxNode.js 20+ and a Cursor IDE installation with existing chat history.
No. Everything runs locally and offline – no OpenAI key, Ollama, or any AI model required.
It reads directly from Cursor’s native SQLite database; no separate database, vector embeddings, or Docker containers are needed.
It is written in TypeScript, requires no Docker or Python, uses direct SQLite reads for instant performance, and includes built‑in backup/restore and migration features.
Yes, it is open‑source under the MIT license.

Give your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

DrUrls audits websites for SEO, and its MCP server lets Claude, ChatGPT, Claude Code, Cursor or VS Code work with those audits directly: list your sites with their latest score and grade, read each issue across SEO, perf
Comments