cursor_history_backup
Create a backup of all Cursor AI chat history. Saves a portable archive that can be restored later.
LABSCO SUMMARY
The answer you already worked out, findable a month later.
Search is plain text matching over the local store, which means results are predictable and immediate — you get the sessions that literally contain the phrase, rather than whatever an embedding model thought was close. The archive side is the other half of the value and the part to handle carefully: back up before restoring, since restore overwrites current history and migrating in move mode deletes the original session.
What it is
A reader and archive tool for Cursor's local AI chat history. It reads Cursor's SQLite store directly — no vectors, no embedding model, no separate service — and can also move, back up and restore that history.
What you get
- cursor_history_search does grep-style matching across every session and returns each hit with surrounding context
- cursor_history_list shows recent sessions with their workspace, message count and timestamps, paged with limit and offset
- cursor_history_show returns a whole session — messages, tool calls and AI responses
- cursor_history_export writes a session out as Markdown or JSON
- cursor_history_backup saves a portable archive of all chat history; cursor_history_restore reads one back, and says plainly that it overwrites what is there now
- cursor_history_migrate moves or copies sessions between workspaces, deleting the original when moving rather than copying
- cursor_history_year_pack builds a sanitised year-in-review summary — statistics, topics and keywords — plus a prompt template for turning it into a report, and is read-only
Requirements
Cursor installed with existing chat history, and Node.js 20+. It runs as npx cursor-history-mcp — nothing to install, no account, no key, and it works offline since everything is read from the local database. Note that restore and migrate change that history: restore overwrites it, and a move deletes the source session. MIT.
Setup effort
One command — npx -y cursor-history-mcp
USE CASES
01
Finding how you solved this before
Search every past session for the error message or API name, read the context around each hit, then open the session that had it.
02
Turning a good session into documentation
Export it as Markdown and keep it somewhere the rest of the team can read.
03
Keeping history safe before a machine change
Create a portable backup archive, then restore it on the other side — after backing up whatever is already there.
04
Filing sessions where they belong
Copy or move sessions into the right workspace, so a project's history sits with the project.
05
Looking back at a year of work
Generate the sanitised summary of statistics, topics and keywords, and let the included prompt template turn it into a readable report.
8 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
cursor_history_export
Export a Cursor AI chat session to Markdown or JSON format. Returns the formatted content.
cursor_history_list
List Cursor AI chat sessions. Returns recent sessions with metadata including workspace, message count, and timestamps.
cursor_history_migrate
⚠️ 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.
cursor_history_restore
⚠️ 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.
cursor_history_search
Search across all Cursor AI chat sessions for a keyword or phrase. Returns matching sessions with context around each match.
cursor_history_show
Show the full content of a specific Cursor AI chat session including all messages, tool calls, and AI responses.
cursor_history_year_pack
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.
BEFORE YOU INSTALL
What to know first
Tools you get
8 tools when we connected.
Requires
- Node.js 20+
- Cursor IDE installed with existing chat history
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y cursor-history-mcpMCP Clients
Claude Code, Claude Desktop
JSON
{
"mcpServers": {
"cursor-history": {
"command": "npx",
"args": [
"-y",
"cursor-history-mcp"
]
}
}
}
