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`.
@rajpdus
Basic information
An MCP(Model Context Protocol) Server for retrieving and sharing your bash/zsh history with MCP Client (Cursor, Claude etc.)
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-histfile": {
"command": "python",
"args": [
"mcp_history_server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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.
git commit occurrences)It reads from the `HISTFILE` environment variable; if that is not set, it falls back to `~/.bash_history`.
Python 3.6 or higher and a shell with history support (Bash, Zsh, etc.). No external authentication or networking beyond the MCP protocol.
Run `python mcp_history_server.py` in the repository directory after installing dependencies with `pip install -r requirements.txt`.
Three tools: `search_commands(query: str)`, `get_recent_commands(limit: int = 10)`, and `get_command(command_id: int)`.
Yes, any MCP‑compatible client can invoke the server’s tools and resources (e.g., `history://recent/{limit}` and `history://search/{query}`).

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
Comments