MCP.so
Sign In
Servers

Cursor History

@S2thend

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

Overview

What is Cursor History?

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.

How to use Cursor History?

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’”.

Key features of Cursor History

  • Zero‑configuration setup – just npx
  • Blazing fast direct SQLite reads
  • Grep‑style text search (exact, predictable)
  • Works completely offline – no external services
  • Built‑in backup, restore, and cross‑workspace migration
  • Export sessions to Markdown or JSON
  • Generate year‑in‑review data packages
  • Minimal dependencies – only Node.js 20+

Use cases of Cursor History

  • Quickly find a past conversation by searching across all sessions
  • Export a chat session as Markdown or JSON for sharing or documentation
  • Create a full backup of your Cursor chat history
  • Move or copy chat sessions between different Cursor workspaces
  • Generate a year‑in‑review summary with stats, topics, and a report prompt

FAQ from Cursor History

What runtime does Cursor History require?

Node.js 20+ and a Cursor IDE installation with existing chat history.

Does Cursor History need an LLM or internet connection?

No. Everything runs locally and offline – no OpenAI key, Ollama, or any AI model required.

How does Cursor History store or access my data?

It reads directly from Cursor’s native SQLite database; no separate database, vector embeddings, or Docker containers are needed.

How is this different from other Cursor history tools?

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.

Is Cursor History free?

Yes, it is open‑source under the MIT license.

Tags

More from Developer Tools