What shells does Terminal History MCP support?
It supports zsh, bash, and fish. All three have both history parsing and optional hook‑based capture for exit code, duration, and working directory.

@HasanJahidul
基本情報
terminal-history-mcp gives AI agents (Claude Code, Cursor, Cline, Zed, any MCP client) full-text search over your shell history.
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": {
"terminal-history": {
"command": "npx",
"args": [
"-y",
"terminal-history-mcp"
]
}
}
}Re-parses the local shell history files (`~/.zsh_history`, `~/.bash_history`) and the hook's extended log into the SQLite index. Idempotent — already-indexed commands are skipped by hash, so it is safe to call repeatedly. Run it after a burst of shell activity to make recent commands searchable. Reads only local files; writes only to `~/.terminal-history-mcp/`. Takes no arguments. Returns counts of parsed / inserted / skipped entries.
Read-only. Full-text search (SQLite FTS5, stemmed, Unicode-aware) over all indexed shell commands. Supports keyword and prefix queries — e.g. `docker build`, `git reb*`. Returns the most recent matches first, each with timestamp, shell, cwd, and exit code when available. Local index only; nothing is sent anywhere. If a query returns nothing you may need `reindex` first.
Read-only. Lists the most recent commands that were run with a given working directory — answers "what was I doing in this project?". Requires the shell hook to have been installed (legacy entries have no cwd and won't appear). Returns newest first with timestamps and exit codes. Local index only.
Read-only. Lists recent commands that exited non-zero — a quick "what just broke?" feed. Optionally restrict to commands after a given epoch-millisecond timestamp. Requires the shell hook for exit-code capture (legacy entries have no exit code). Newest first. Local index only.
Read-only. For each command matching `query`, returns the commands run within a time window around it (default ±5 min) — surfacing multi-step sequences like `cd → npm run build → deploy`. Useful for reconstructing "how did I do X last time?". Returns up to `limit` chains, each a time-ordered list of command rows. Local index only.
Terminal History MCP lets AI coding agents search your local shell history (zsh, bash, fish) using SQLite FTS5 full‑text search. Commands are secret‑redacted before storage and never leave your machine.
Install globally with npm, then run terminal-history-mcp index for a one‑time backfill and terminal-history-mcp install-hook to capture working directory, exit code, and duration. Alternatively, use zero‑install via npx by adding it to your mcpServers configuration. Tools available: reindex, search_history, recent_in_dir, failed_commands, command_chains.
It supports zsh, bash, and fish. All three have both history parsing and optional hook‑based capture for exit code, duration, and working directory.
Data stays entirely local. Secrets are redacted before insertion using 11 ordered patterns (GitHub PATs, OpenAI keys, AWS keys, etc.). The database is at `~/.terminal-history-mcp/history.db`.
No. It makes zero network calls and runs fully offline.
Install via `npm install -g terminal-history-mcp`, then index your history. Or skip installation by using `npx -y terminal-history-mcp` in your MCP client configuration.
The optional hook captures the current working directory, exit code, and execution duration for each command, enriching the searchable history.

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

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.
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
コメント