MCP server de bash
Commit 21 oct 2026Permite que un asistente de IA ejecute comandos bash en una máquina local a través de un conector WebSocket seguro.
También conocido como assistant-core/mcp-bash
- Stars
- 0
- Herramientas
- 3
- Descargas, 30 días
- —
- Última versión
- —
- Último commit
- 21 oct 2026
- Licencia
- MIT
¿Qué es bash MCP?
Permite que un asistente de IA ejecute comandos bash en una máquina local a través de un conector WebSocket seguro. Expone 3 herramientas, como command, timeout_seconds, restart.
Resumen generado a partir del README del proyecto
Acerca del MCP server de bash
Ejecutar comandos de terminal directamente desde un asistente de IA es lo que mcp-bash permite a los desarrolladores que trabajan con Assistant Core. Este servidor actúa como un conector local que se conecta mediante un WebSocket para vincular tu máquina con el asistente sin necesidad de una URL pública o de abrir puertos. Proporciona una única herramienta bash que permite al modelo ejecutar comandos, gestionar directorios y recibir salidas como stdout y stderr.
Para configurarlo, ejecutas el conector localmente usando un token y una URL específicos proporcionados por el administrador de Assistant Core. Puedes personalizar el nombre de la herramienta y restringir qué interfaces, como la aplicación móvil o web, pueden acceder a la funcionalidad bash. Debido a que la herramienta puede modificar tu sistema, está diseñada para ser utilizada con asistentes de confianza y es recomendable ejecutarla bajo una cuenta de bajos privilegios o dentro de un contenedor rootless.
La seguridad se gestiona mediante un sistema de aprobación donde puedes permitir, preguntar o bloquear patrones de comandos específicos. El servidor también mantiene un registro de auditoría en formato jsonl para rastrear cada comando ejecutado, incluyendo el código de salida y la duración.
Qué puedes hacer con él
- 1Automatizar tareas repetitivas de la terminalUn desarrollador puede instruir a una IA para ejecutar git status u otros comandos frecuentes sin tener que escribirlos manualmente.
- 2Gestionar múltiples máquinas remotasPuedes conectar varios ordenadores distintos a un único asistente asignando un nombre de herramienta único a cada conector.
- 3Ejecutar comandos con variables de entorno específicasPuedes pasar credenciales sensibles, como tokens de GitHub, a la herramienta bash solo cuando una tarea específica lo requiera.
- 4Mantener conexiones de larga duraciónUsa tmux para asegurar que el conector bash permanezca activo incluso después de que te desconectes de una sesión SSH.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Herramientas de bash MCP 3
Detectado desde el READMEcommandtimeout_secondsrestart
| command | — | |
| timeout_seconds | — | |
| restart | — |
Configuración
BASH_TOOL_NAMELOCAL_CONNECTOR_TOKENLOCAL_CONNECTOR_URL
| Nombre | Descripción | Tipo |
|---|---|---|
| BASH_TOOL_NAME | — | |
| LOCAL_CONNECTOR_TOKEN | — | |
| LOCAL_CONNECTOR_URL | — |
Verificaciones automáticas
Ejecutado 14 nov 2026Informe completo →Aún no verificado. Un servidor necesita una puntuación de 80, ningún hallazgo grave y suficientes datos para que podamos revisarlo. Cómo funcionan las verificaciones · Qué corregir para obtener más puntos
- Repositorio de origen vinculado y accesibleassistant-core/mcp-bash is public and reachablegithub.com/assistant-core/mcp-bash ↗Aprobado
- El paquete indica este repositorio como su origenNo verificado
- Procedencia de la compilación (atestación de Sigstore)No verificado
- Licencia de código abierto (OSI)MITspdx.org/licenses/MIT.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-10-21github.com/assistant-core/mcp-bash ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo verificado
- No hay avisos críticos en el paquete ni en sus dependenciasNo verificado
- Sin instrucciones ocultas para el modelo3 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo tool named like delete, drop or execAprobado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en GitHubmcp-bash
A minimal MCP server that lets an AI assistant run bash commands on your machine, connected as an Assistant Core local connector. The connector dials out over WebSocket, so the machine needs no public URL or open port.
⚠️ Anyone who can chat with the connected assistant can run commands as your user. Use it only with assistants you trust, run it under a low-privilege account, and stop it when you are done.
Quick start
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
# Assistant Core admin → MCP → Local connector → Add connector (token shown once)
export LOCAL_CONNECTOR_URL="wss://api.assistantcore.com/local-connector/ws"
export LOCAL_CONNECTOR_TOKEN="lc_..."
python connector.py
Then click Refresh tools in the admin: the assistant gets one tool, bash. Assistant Core offers a connector's tools only as the owner last refreshed them, so refresh again after changing BASH_TOOL_NAME, BASH_SURFACES or the server.
You can also put both settings in a .env file (see .env.example). To connect a different stdio MCP server, pass its script: python connector.py my_server.py.
Where the tool is offered
On Assistant Core the tool is offered only in the web and mobile apps (BASH_SURFACES=app), never to website widget visitors, messaging apps, voice devices or the public API, where anyone the assistant talks to could run commands. To widen it, list the surfaces: BASH_SURFACES=app,api. The admin can narrow this further, not widen it.
When it asks first
Assistant Core asks before every command unless a rule says otherwise, because the tool can change anything on the machine. The tool tells Assistant Core which argument holds the command line, so rules can name commands instead of the whole tool:
- On an approval card, tick Don't ask again (for commands starting with
git status) to rungit statuswithout asking next time, in chat and in scheduled tasks. Manage these in Settings → Approvals. - The assistant's owner sets rules for everyone in the admin (Approvals): Allow
git status, Ask fordocker, Blockrm. Block wins over Ask, Ask over Allow.
A command line runs without asking only when every command in it is allowed: git status && rm -rf x still asks. Lines with $(…), backticks, redirections or variables, and commands that run other commands (sudo, bash -c, xargs, python…), are never allowed by a command rule.
After updating this server, refresh tools in the admin once so Assistant Core sees the new definition.
Several machines or several assistants
One assistant, several machines. Add a connector per machine in the admin, each with its own token, and give each machine its own tool name so the model can tell them apart:
# on web01, with web01's token
BASH_TOOL_NAME=web01_bash python connector.py
# on db01, with db01's token
BASH_TOOL_NAME=db01_bash python connector.py
Then refresh tools in the admin. A tool name belongs to the connector that offered it first: a second machine offering the same name is refused, and its log says so. Each token connects one machine at a time, and deleting or regenerating one disconnects only that machine.
One machine, several assistants. A connector token belongs to one assistant, so run one connector per assistant, each with its own token and audit log:
LOCAL_CONNECTOR_TOKEN=lc_AAA BASH_AUDIT_LOG=~/audit-a.jsonl python connector.py
LOCAL_CONNECTOR_TOKEN=lc_BBB BASH_AUDIT_LOG=~/audit-b.jsonl python connector.py
Everyone who can chat with any of those assistants can run commands on the machine.
Limit what commands can reach
The server only starts commands; it does not confine them. For anything beyond a personal machine:
- Run the connector as a dedicated user without
sudo, owning only the directories the assistant should touch. - Better, run it in a rootless container with a read-only root filesystem and one writable volume, and restrict its outbound network if you can: commands can send anything they read to the internet.
- Pass secrets with
BASH_PASS_ENVonly when a task needs them, and reviewaudit.jsonl.
Keep it running on a server
To keep the connector running after you close SSH, start it inside tmux:
tmux new -s connector
cd ~/mcp-bash && source .venv/bin/activate && python connector.py
# Ctrl+B then D to detach; the connector keeps running
tmux attach -t connector # back to the logs
tmux kill-session -t connector # stop it
tmux survives SSH disconnects, but not a server reboot, and nothing restarts the connector if it exits.
The bash tool
| Parameter | Description |
|---|---|
command |
Bash command to run |
timeout_seconds |
1–120, default 30 |
restart |
Start from BASH_WORKDIR instead of where the last command ended |
Returns stdout, stderr, exit_code, timed_out, truncated and cwd (where the command ended).
- The first command starts in
BASH_WORKDIR(default: your home directory); each later one starts where the previous one ended, like a terminal. Environment variables, aliases and functions do not carry over: every call is a new shell. A command that times out keeps the directory it started in. This is a starting point, not a sandbox. - Commands see only a minimal environment (
PATH,HOME,USER,SHELL, locale,TERM,TMPDIR,TZ), so secrets in your shell, including the connector token, never reach the assistant. Pass extra variables explicitly withBASH_PASS_ENV=GITHUB_TOKEN,AWS_PROFILE; anything you pass, the assistant can read. - stdin is closed, so commands that prompt for input fail instead of hanging.
- On timeout the whole process group is killed. A process that starts its own session (
setsid) can outlive it; there is no sandbox to stop that. - Background jobs keep running after the command returns; redirect their output (
cmd > log 2>&1 &), since the result is returned as soon as bash exits. - stdout and stderr are each truncated to 20,000 characters, keeping the first 8,000 and the last 12,000, and memory stays bounded however much a command prints.
- At most 2 commands run at once; extra calls return an error.
- Every command is appended to
audit.jsonlnext tobash_server.py(orBASH_AUDIT_LOG): time, command, starting directory, exit code and duration, not the output. The file is readable only by you. - Requires bash (macOS, Linux, or WSL on Windows).
Reconnection
connector.py reconnects with exponential backoff (1 s up to 10 min), and starts over after a session that stayed up for a minute. If the connector token is regenerated or deleted in the admin, the log says so; restart with the new token. If the relay refuses the connection because the token is already in use or another machine offers the same tool name, the log names the conflict.
Tests
pip install pytest && pytest -q
Preguntas sobre bash MCP
¿Qué herramientas proporciona bash MCP?
Expone 3 herramientas, incluidas command, timeout_seconds, restart.
¿Cómo ejecuto comandos bash a través de este servidor?
El servidor proporciona una herramienta bash que acepta una cadena de comando, un timeout opcional y un flag de reinicio para determinar el directorio de trabajo.
¿Puedo restringir qué comandos tiene permitido ejecutar el asistente?
Sí, el administrador de Assistant Core puede establecer reglas para permitir (Allow), preguntar (Ask) o bloquear (Block) comandos específicos, siendo la opción Block la que tiene prioridad.
¿Cómo gestiona el conector la conectividad de red?
El conector realiza una conexión de salida vía WebSocket, lo que significa que la máquina no requiere una URL pública ni puertos abiertos, y utiliza un sistema de exponential backoff para las reconexiones.