広告掲載
MCP.so
ログイン

MCP Command History

@rajpdus

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

rajpdus

MCP Command History について

An MCP(Model Context Protocol) Server for retrieving and sharing your bash/zsh history with MCP Client (Cursor, Claude etc.)

MCP Command History の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-histfile": {
      "command": "python",
      "args": [
        "mcp_history_server.py"
      ]
    }
  }
}

MCP Command History のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Command History?

MCP Command History provides programmatic access, search, and management of your shell command history through the Model Context Protocol (MCP) interface. It is designed for developers who want to query and interact with their command history from MCP‑compatible tools like Cursor.

How to use MCP Command History?

Install from source with Git and pip. Start the server with python mcp_history_server.py; it reads history from the HISTFILE environment variable (default: ~/.bash_history). Once running, use MCP tools such as search_commands, get_recent_commands, and get_command from a Cursor client or any MCP‑compatible host.

Key features of MCP Command History

  • Access shell command history programmatically
  • Search history with text queries
  • Retrieve most recent commands with configurable limit
  • Get a specific command by its numeric ID
  • Seamless integration with Cursor and other MCP tools
  • Supports Bash, Zsh, and any shell with history files

Use cases of MCP Command History

  • Search for a forgotten command pattern (e.g., all git commit occurrences)
  • Quickly retrieve recently executed commands for auditing or replay
  • Obtain a specific command by ID after a search or listing
  • Integrate command history retrieval into automated workflows or AI assistants

よくある質問

1

How does MCP Command History access my shell history?

It reads from the `HISTFILE` environment variable; if that is not set, it falls back to `~/.bash_history`.

2

What are the runtime requirements?

Python 3.6 or higher and a shell with history support (Bash, Zsh, etc.). No external authentication or networking beyond the MCP protocol.

3

How do I start the server?

Run `python mcp_history_server.py` in the repository directory after installing dependencies with `pip install -r requirements.txt`.

4

What MCP tools are provided?

Three tools: `search_commands(query: str)`, `get_recent_commands(limit: int = 10)`, and `get_command(command_id: int)`.

5

Can I use MCP Command History with tools other than Cursor?

Yes, any MCP‑compatible client can invoke the server’s tools and resources (e.g., `history://recent/{limit}` and `history://search/{query}`).

コメント

「開発者ツール」の他のコンテンツ

LastPing

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

1

LocalCan

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

82

Eased

easedui

Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.

OpenMark

OpenMark AI

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.

広告掲載