# io.github.S2thend/cursor-history (npm · cursor-history-mcp)

MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history

- Trust score: 71/100 (medium)
- Change this week: +25
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `cursor-history-mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/s2thend-cursor-history/cursor-history-mcp.md), [page](https://verifymcp.io/servers/s2thend-cursor-history/cursor-history-mcp)

## Channel facts

- Registry: `npm`
- Package: `cursor-history-mcp`
- Version: `0.2.4`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 71/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 1.0.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (55 of 56), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 96/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to S2thend/cursor-history-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 204 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 717 tokens (~89/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add s2thend-cursor-history -- npx -y cursor-history-mcp
```

### Codex

```bash
codex mcp add s2thend-cursor-history -- npx -y cursor-history-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "s2thend-cursor-history": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "cursor-history-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add s2thend-cursor-history --command npx --arg -y --arg cursor-history-mcp
```

### Hermes

```yaml
mcp_servers:
  s2thend-cursor-history:
    command: "npx"
    args: ["-y", "cursor-history-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "s2thend-cursor-history": {
      "command": "npx",
      "args": [
        "-y",
        "cursor-history-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 71, −2)

No change was recorded against any check on this day. Supply Chain Security went from 80 to 71. Other categories moved too: Stability & Change Management rose 4.

### 2026-08-02 (score 73, +68)

- [security regression] CVE-2025-66414 affects this package: high
- [security regression] CVE-2026-39244 affects this package: high
- [security regression] Known CVEs: unverified → fail
- [security improvement] Provenance: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security improvement] Install scripts: unverified → pass
- [security] The attested source repository moved: S2thend/cursor-history-mcp
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 5, −16)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-31 (score 21, −25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 46, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (8)

### `cursor_history_list` (~90 tokens)

List Cursor AI chat sessions. Returns recent sessions with metadata including workspace, message count, and timestamps.

Input parameters:

- `limit` (integer): Maximum number of sessions to return (default: 20, max: 1000)
- `offset` (integer): Number of sessions to skip for pagination (default: 0)
- `workspace` (string): Filter sessions by workspace path (absolute path to project folder)

### `cursor_history_show` (~51 tokens)

Show the full content of a specific Cursor AI chat session including all messages, tool calls, and AI responses.

Input parameters:

- `sessionIndex` (integer, required): The session index (1-based, as shown in list output)

### `cursor_history_search` (~87 tokens)

Search across all Cursor AI chat sessions for a keyword or phrase. Returns matching sessions with context around each match.

Input parameters:

- `context` (integer): Number of characters of context to show around each match (default: 50)
- `limit` (integer): Maximum number of results to return (default: 10)
- `query` (string, required): The search query (keyword or phrase to find)

### `cursor_history_export` (~69 tokens)

Export a Cursor AI chat session to Markdown or JSON format. Returns the formatted content.

Input parameters:

- `format` (string): Export format: 'markdown' for human-readable, 'json' for structured data
- `sessionIndex` (integer, required): The session index (1-based, as shown in list output)

### `cursor_history_backup` (~80 tokens)

Create a backup of all Cursor AI chat history. Saves a portable archive that can be restored later.

Input parameters:

- `force` (boolean): Overwrite existing backup file if it exists (default: false)
- `outputPath` (string): Path where the backup file should be saved. If not specified, saves to ~/cursor-history-backups/ with a timestamp.

### `cursor_history_restore` (~85 tokens)

⚠️ 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.

Input parameters:

- `backupPath` (string, required): Path to the backup file to restore from
- `force` (boolean): Skip confirmation and force overwrite of existing data (default: false)

### `cursor_history_migrate` (~106 tokens)

⚠️ 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.

Input parameters:

- `destination` (string, required): Absolute path to the destination workspace folder
- `mode` (string): Migration mode: 'move' deletes original, 'copy' keeps original
- `sessionIndexes` (array, required): List of session indexes to migrate (1-based, as shown in list output)

### `cursor_history_year_pack` (~149 tokens)

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.

Input parameters:

- `language` (string): Report language preference (default: en)
- `maxSampleLength` (integer): Maximum characters per sample (default: 120)
- `maxSamples` (integer): Maximum sample questions to include (default: 30)
- `topicsCount` (integer): Number of topics to extract (default: 7)
- `workspace` (string): Optional workspace path to filter sessions
- `year` (integer): Calendar year to analyze (default: current year)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/s2thend-cursor-history/cursor-history-mcp#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 73
- 2026-08-01: 5
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/cursor-history-mcp
- Socket report: https://socket.dev/npm/package/cursor-history-mcp
- Repository: https://github.com/S2thend/cursor-history-mcp
- Changelog RSS feed: https://verifymcp.io/servers/s2thend-cursor-history/cursor-history-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/s2thend-cursor-history/cursor-history-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/s2thend-cursor-history/cursor-history-mcp