bridge-mcp
The bridge-mcp server is a local MCP bridge that connects AI clients (like ChatGPT) to a local machine, enabling filesystem, shell, Git, terminal, and diagnostic operations.
System Info: Retrieve OS, Node.js, CPU, memory, hostname, and current working directory details.
Filesystem Operations:
List directory contents recursively with depth limits
Read UTF-8 text files with a configurable max byte limit
Write or append UTF-8 text files, with automatic parent directory creation
Apply exact string replacement patches to text files
Shell & Command Execution:
Run shell commands in a specified working directory with configurable timeout, capturing stdout/stderr
Manage persistent terminal sessions: start, write input, read output, stop, and list active sessions
Git Operations:
Get the short Git status of the current project
Add or update a GitHub HTTPS remote
Stage all changes and create a commit
Push the current branch to a remote
Diagnostics & Health:
Check tunnel-client health and readiness
Run a comprehensive self-check (typecheck, build, Git status, tunnel health, terminal inventory)
Request restart and check restart status
Metrics: View tool usage metrics including status, summary, and recent entries.
Provides tools for interacting with Git repositories, including checking status, setting remotes, committing all changes, and pushing the current branch.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bridge-mcpcheck git status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
bridge-mcp
MCP local propio para conectar ChatGPT/Kairos/KChat con MauroPrime y, más adelante, la laptop u otros clientes.
El objetivo no es depender de un runner genérico: este repo es el puente local controlado por nosotros para filesystem, shell, Git, diagnósticos, reinicio seguro y métricas.
Estado actual
Versión esperada del servidor:
bridge-mcp v0.4.0Modo recomendado actual:
Production-candidate: HTTP local + OpenAI Secure MCP TunnelRuta activa recomendada:
ChatGPT
-> OpenAI Secure MCP Tunnel
-> tunnel-client profile bridge-local-http
-> http://127.0.0.1:3001/mcp
-> bridge-mcp Streamable HTTP en MauroPrime
-> filesystem / shell / git / procesosstdio sigue siendo el rollback estable.
Related MCP server: codex-web-bridge
Stack
Node.js / TypeScript
Node v24.x
node:sqlitepara métricas locales@modelcontextprotocol/sdkzodMCP Streamable HTTP local
OpenAI Secure MCP Tunnel mediante
tunnel-client
Tools actuales
Base local:
system_info: datos básicos de la máquina.list_dir: lista carpetas con profundidad limitada.read_text_file: lee texto UTF-8 con límite de tamaño.write_text_file: escribe o agrega texto UTF-8.apply_patch: reemplazo exacto y controlado en archivos de texto.run_command: ejecuta comandos concwd, timeout y salida capturada.
Terminal persistente:
terminal_startterminal_writeterminal_readterminal_stopterminal_list
Git, túnel y diagnóstico:
git_statusgit_set_remotegit_commit_allgit_push_current_branchtunnel_healthbridge_self_checkbridge_request_restartbridge_restart_status
Métricas de tools:
bridge_metrics_statusbridge_metrics_summarybridge_metrics_recentbridge_visualization_catalogbridge_visualize_metrics
Nota: puede que ChatGPT no muestre tools nuevas en una conversación ya abierta hasta refrescar el conector/reabrir el chat, pero el runtime ya las expone.
Scripts principales
npm install
npm run check
npm run build
npm run start
npm run start:httpHTTP local production-candidate
Endpoints locales:
http://127.0.0.1:3001/healthz
http://127.0.0.1:3001/readyz
http://127.0.0.1:3001/status
http://127.0.0.1:3001/mcpPerfil de túnel:
bridge-local-http -> http://127.0.0.1:3001/mcpValidación:
.\scripts\test-bridge-http.ps1
Invoke-RestMethod http://127.0.0.1:3001/status
Invoke-RestMethod http://127.0.0.1:8081/readyzEl modo HTTP ya valida:
initializeMcp-Session-Idnotifications/initializedcon respuesta 202limpieza de sesiones idle
limpieza de transports anónimos
límite máximo de sesiones
watchdog para reinicio de HTTP
watchdog para reinicio de
tunnel-client
Ver HTTP_LOCAL_MCP.md.
Watchdog local
Modo HTTP recomendado:
Set-Location C:\dev\bridge-mcp
.\scripts\start-bridge-http-watchdog.ps1 -ProjectRoot C:\dev\bridge-mcp -Profile bridge-local-http -TunnelBaseUrl http://127.0.0.1:8081Instalación al inicio de sesión de Windows sin permisos de administrador:
Set-Location C:\dev\bridge-mcp
.\scripts\install-bridge-watchdog-task.ps1 -InstallMode Startup -WatchdogMode HttpEsto crea:
%APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup\BridgeMCP-Watchdog.cmdRollback stdio:
Set-Location C:\dev\bridge-mcp
.\scripts\start-bridge-watchdog.ps1 -ProjectRoot C:\dev\bridge-mcpMétricas y logs
Runtime local:
logs/bridge-events.jsonl
data/bridge-metrics.sqliteConsultas rápidas:
node .\scripts\query-bridge-metrics.mjs status
node .\scripts\query-bridge-metrics.mjs summary 50
node .\scripts\query-bridge-metrics.mjs recent 25
node .\scripts\query-bridge-metrics.mjs errors 25Variables útiles:
BRIDGE_MCP_METRICS_ENABLED=0
BRIDGE_MCP_METRICS_DIR=...
BRIDGE_MCP_LOG_DIR=...
BRIDGE_MCP_METRICS_SQLITE=...
BRIDGE_MCP_EVENTS_JSONL=...Las métricas guardan nombres de tools, duración, éxito/error, claves de input y tamaño de salida. No guardan argumentos completos.
Modelo de uso desde laptop
Si usás ChatGPT desde la laptop pero el conector apunta al túnel que corre en MauroPrime, las tools se ejecutan en MauroPrime.
Laptop con ChatGPT UI
-> OpenAI
-> Secure MCP Tunnel activo en MauroPrime
-> tools ejecutadas en MauroPrimePara que las tools se ejecuten en la laptop, la laptop necesitaría su propio bridge/tunnel/profile corriendo localmente.
Seguridad
No commitear:
node_modules/dist/binarios del tunnel-client
.env/ claves / tokenslogs
base SQLite de métricas
sandbox local
Mantener secretos como variables de entorno de Windows o en perfiles locales fuera de Git.
Local auth model
El perfil HTTP local es intencionalmente loopback-only y no-auth en el listener MCP. La barrera de seguridad real es el OpenAI Secure MCP Tunnel + runtime key + permisos del workspace.
Ver OPENAI_TUNNEL_LOCAL_AUTH.md.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mauro3422/bridgeWEB-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server