Terminal History MCP
terminal-history-mcp
Busque en su historial de shell (zsh / bash / fish) desde Claude Code, Cline, Cursor, Zed o cualquier cliente MCP. Solo local. SQLite FTS5. Secretos redactados antes del almacenamiento.

Qué puede preguntar
"¿Cuándo hice ssh por última vez al servidor de staging?"
"Muestra los comandos fallidos recientes."
"¿Qué ejecuté ayer en
/etc/nginx?""¿Cuál es esa bandera larga de docker compose que usé hace 3 semanas?"
"Muestra cadenas de comandos alrededor de
kubectl apply."
Related MCP server: ClaudeX
Instalación
npm install -g terminal-history-mcp
terminal-history-mcp index # one-time backfill from existing history(O ejecute desde un clon: git clone … && npm install && npm run build && npm link.)
Conectar a Claude Code
claude mcp add --scope user terminal-history -- terminal-history-mcp
claude mcp listConectar a otros clientes MCP
En cualquier lugar que acepte una configuración de servidor MCP stdio:
{
"mcpServers": {
"terminal-history": {
"command": "terminal-history-mcp"
}
}
}Conectar mediante MCPize
Utilice este servidor MCP al instante sin instalación local:
npx -y mcpize connect @HasanJahidul/terminal-history --client claudeO conéctese en: https://mcpize.com/mcp/terminal-history
Capturar cwd + código de salida (recomendado)
Por defecto, los archivos de historial de zsh/bash solo almacenan el comando. Para desbloquear recent_in_dir y failed_commands, instale el hook de shell:
terminal-history-mcp install-hook zsh # or bash, or fish
exec $SHELL # reloadEl hook añade líneas delimitadas por tuberías a ~/.terminal-history-mcp/extended.log. La reindexación las recoge.
Para inspeccionar el fragmento primero:
terminal-history-mcp print-hook zshPara eliminar:
terminal-history-mcp uninstall-hook zshHerramientas
Herramienta | Qué hace |
| Palabra clave FTS5 + coincidencia de prefijo en todo el historial |
| Últimos N comandos en un directorio de trabajo (necesita hook) |
| Comandos con salida distinta de cero (necesita hook) |
| Para cada coincidencia, enumera los comandos dentro de ±5 min |
| Vuelve a analizar los archivos de historial + registro extendido |
Privacidad
Todo es local. La base de datos reside en ~/.terminal-history-mcp/history.db. No se sube nada.
Los secretos se eliminan antes de la inserción. Patrones detectados:
GitHub PATs (
ghp_*,gho_*, …)Claves de OpenAI (
sk-*)Tokens de Slack (
xox[baprs]-*)Claves de acceso de AWS (
AKIA…)Authorization: Bearer/Basic <valor>Cabeceras
X-*-Token: …,X-*-Key: …,X-*-Secret: …Variables de entorno que contienen
TOKEN/KEY/SECRET/PASSWORD/API_KEYBanderas CLI
--token=…,--api-key …,-k …Autenticación básica de URL
https://user:pass@hostJWTs (
eyJ.*.*)
Si encuentra una filtración, por favor abra un issue. Para borrar y reindexar después de actualizar los patrones:
rm ~/.terminal-history-mcp/history.db*
terminal-history-mcp indexDesarrollo
git clone https://github.com/hasanjahidul/terminal-history-mcp
cd terminal-history-mcp
npm install
npm run build
npm testLicencia
MIT — ver LICENSE.
Available Tools
7 toolsask_historyARead-onlyIdempotent
Read-only. Answers a natural-language question about your shell history, with citations (retrieval-augmented generation). Retrieves the top k entries with hybrid search, then, if TERMINAL_HISTORY_CHAT_MODEL is set, asks that chat model to answer only from those entries and cite them as [id:N]. Retrieved commands are passed as delimited untrusted data, never as instructions. Replies exactly "No relevant history found." when nothing retrieved is relevant. Without a chat model it returns the retrieved context only. Cited ids are checked against the retrieved set; any others are listed in invalid_citation_ids.
Inputs: question (required), k. Returns: note, answer, cited_ids, retrieved, +5 more
command_chainsARead-onlyIdempotent
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.
Inputs: query (required), limit, window_ms. Returns: count, chains
failed_commandsARead-onlyIdempotent
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.
Inputs: limit, since_ts_ms. Returns: count, results
recent_in_dirARead-onlyIdempotent
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.
Inputs: cwd (required), limit. Returns: count, results
reindexAIdempotent
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.
Inputs: no named parameters. Returns: parsed, skipped, inserted, ext_applied, +1 more
reindex_embeddingsAIdempotent
Builds the vector index behind search_history semantic/hybrid modes and ask_history. Embeds distinct indexed command texts (identical commands share one vector) that have no vector yet for the configured model, newest first, in batches of 64, via the OpenAI-compatible endpoint in TERMINAL_HISTORY_LLM_BASE_URL (default Ollama at http://localhost:11434/v1, model nomic-embed-text from TERMINAL_HISTORY_EMBED_MODEL). Non-localhost endpoints are refused unless TERMINAL_HISTORY_ALLOW_REMOTE_LLM=1. Sends only already-redacted text read from the local index. Changing the embedding model re-embeds everything for the new model. Run reindex first, then call until remaining is 0. Returns embedded / skipped / failed / remaining counts.
Inputs: limit. Returns: error, model, failed, skipped, +2 more
search_historyARead-onlyIdempotent
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. Default keyword mode is local index only; nothing is sent anywhere. semantic and hybrid modes embed only the query through the configured OpenAI-compatible endpoint (localhost Ollama by default) and need reindex_embeddings to have run. If a query returns nothing you may need reindex first.
Inputs: query (required), mode, limit. Returns: mode, count, results, keyword_error, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct role: raw indexing, embedding indexing, keyword/semantic search, RAG-style Q&A, command-chain reconstruction, failure listing, and cwd-scoped recency listing. The two reindex tools are explicitly differentiated by their descriptions, and search_history vs. ask_history is cleanly separated as retrieval vs. natural-language answering.
Names are all snake_case and readable, but they mix verb_noun forms (search_history, ask_history), a bare verb (reindex), and noun/adjective phrases (command_chains, failed_commands, recent_in_dir). The pattern is not predictable from one tool to the next, though the names remain understandable.
Seven tools is well-scoped for a terminal-history server, covering indexing, search, semantic retrieval, and several targeted history views. Each tool has a clear reason to exist and none feels redundant or excessive.
The surface covers the core lifecycle: index raw history, build embeddings, search, ask questions, and inspect chains/failures/recent directory activity. Minor gaps exist, such as fetching a specific indexed command by id or managing/pruning the index, but these are not blocking for the stated purpose.
Maintenance
Related MCP Connectors
One searchable history across every AI coding tool, with secret scanning and a shared task board.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Work on your own computers from Claude or ChatGPT: run commands, edit and search files.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA powerful tool for exploring, searching, and managing your shell command history through the MCP (Model Control Protocol) interface. This project allows you to easily access, search, and retrieve your previously executed shell commands.2MIT
- AlicenseAqualityDmaintenancePersistent memory + FTS5 full-text search for Claude Code conversation history. Indexes ~/.claude/projects/ JSONL into SQLite, exposes 10 MCP tools (store/recall/search memories, browse sessions, get summaries) plus prompts. Includes a web UI for visual exploration10106 npm98MIT
- AlicenseAqualityDmaintenanceInspect, manage, and kill local dev servers via MCP. Stop guessing what's on :3000. Five tools: list servers with framework detection, inspect ports, find zombies, diagnose conflicts, safe-kill with dry-run default. Local, no cloud, no telemetry.510 npm4MIT
- AlicenseAqualityDmaintenanceSemantic git queries via MCP. Beyond git log — answer who/what/why about any line, file, or branch with blame, co-change, PR linkage.67 npm2MIT