Puente MCP local de código abierto para ChatGPT desktop Quick Chat + GPT-5.6 Pro.
Los agentes de codificación en Codex, OpenCode, Claude u otros hosts MCP llaman a ProBridge. ProBridge encola el trabajo, abre una sesión de ChatGPT Quick Chat verificada y envía el prompt. Dentro de esa sesión de ChatGPT, LocalAnt / DevSpace es el conector que llega a tu Mac local y al espacio de trabajo activo.
Se usa la cuota de ChatGPT Pro. No se usa la cuota de modelos de Codex. No hay ninguna clave de API de modelos.
Objetivo actual: macOS. Windows y Linux aún no son compatibles. Las contribuciones que añadan un controlador real para esas plataformas son bienvenidas.
Codex / OpenCode / Claude
|
| MCP tool call
v
ProBridge
prompt · queue · status · follow-up
|
| drives ChatGPT desktop Quick Chat
v
ChatGPT Quick Chat (GPT-5.6 Pro)
|
| LocalAnt / DevSpace inside ChatGPT
v
authenticated device tunnel
|
v
local Mac / active workspaceEl agente que llama solo necesita tres herramientas:
gpt56_pro_start({ prompt })
gpt56_pro_status({ jobId })
gpt56_pro_followup({ jobId, prompt })start devuelve inmediatamente un jobId. Consulta status. Usa follow-up solo después de que esa misma ronda de Quick Chat haya terminado.
Related MCP server: mcacp
LocalAnt / DevSpace da a ChatGPT acceso a tu Mac. ProBridge no reemplaza ese conector y no puede instalarlo por ti.
ProBridge da a tu agente de codificación un puente hacia ChatGPT Pro. Un host MCP envía un prompt a ProBridge; ProBridge lo encola, maneja Quick Chat y devuelve el estado del trabajo a través de MCP. Por eso este repositorio tiene sentido cuando ya quieres que ChatGPT Pro realice trabajo local, pero quieres que Codex, OpenCode, Claude u otro agente lo invoque como subagente.
macOS
Node 20+
Herramientas de línea de comandos de Xcode (swiftc)
ChatGPT desktop con sesión iniciada con Pro
Permiso de Accesibilidad para el binario bin/ax-driver
LocalAnt / DevSpace es lo que le da a ChatGPT Pro manos en la máquina. ProBridge es lo que permite que otros agentes envíen trabajo a esa sesión de ChatGPT.
ProBridge necesita que ChatGPT ya tenga un conector que pueda llegar a tu Mac local. Elige un conector y completa su configuración previa antes de instalar ProBridge:
LocalAnt (la vía probada): sigue la guía de configuración de LocalAnt. El inicio rápido es:
npx -y localant setup
localant tools profile codinglocalant setup imprime tu endpoint de MCP autenticado. En ChatGPT desktop, ve a Ajustes → Apps y conectores, activa Modo de desarrollo, elige Conectores → Crear, pega ese endpoint de MCP, selecciona Autenticación: Ninguna y llama al conector LocalAnt. Mantén los ajustes locales de aprobación y seguridad de LocalAnt apropiados para tu máquina.
DevSpace: sigue Waishnav/devspace y conecta su entorno local a ChatGPT según las instrucciones de ese proyecto.
Abre una sesión de ChatGPT Quick Chat y verifica que el conector seleccionado puede leer un archivo inofensivo del proyecto antes de continuar. Esto es una configuración independiente del lado de ChatGPT; instalar ProBridge por sí solo no le da a ChatGPT acceso a tu Mac.
git clone https://github.com/HAMZADEMIR33412005/probridge.git
cd probridge
node scripts/build-ax.mjs
node scripts/install.mjs
node scripts/doctor.mjsinstall.mjs crea ~/.codex/config.toml si es necesario, escribe la entrada MCP de ProBridge y en el archivo de configuración existente un backup con marca de tiempo. Luego concede Accesibilidad a bin/ax-driver si macOS lo pide, mantén Programa de CPT de escritorio y abre un nuevo chat de Codex.
No establece cwd; Codex debe iniciar el servidor desde el proyecto que ya tienes abierto.
Automático:
node scripts/install.mjsManual: copia examples/codex.config.toml en ~/.config/codex/config.toml y reemplaza la ruta absoluta del servidor.
El nombre de servidor registrado es probridge. Después de cualquier actualización, inicia un nuevo chat de Codex para que recargue el proceso MCP y el protocolo del daemon.
Apuntan a un servidor MCP stdio en este checkout:
{
"mcpServers": {
"probridge": {
"command": "/Applications/ChatGPT.app/Contents/Resources/cua_node/bin/node",
"args": ["/ABS/PATH/TO/probridge/src/server.mjs"]
}
}
}Consulta examples/claude-code.mcp.json y examples/opencode.json. Si te falta el Node console que no se incluido con ChatGPT, cualquier binario Node 20+ funciona.
El host MCP debe iniciar el servidor desde el espacio de trabajo del proyecto, o bien indicar exactamente un raíz file://. ProBridge rechaza la carpeta home, Desktop, Documents y otras carpetas amplias similares.
Desde un agente en el espacio de trabajo del proyecto:
gpt56_pro_start({
prompt: "Inspect the failing tests, fix the root cause, run focused tests, and report changed files."
})Poll:
gpt56_pro_status({ jobId: "pro_..." })Continúa el mismo Quick Chat después de que se complete:
gpt56_pro_followup({
jobId: "pro_...",
prompt: "Now implement the review findings."
})Los trabajos se encolan. Se puede enviar un segundo New chat tan pronto como el prompt anterior se verifique como enviado. Los seguimientos quedan en la misma conversación.
El estado está en dos lugares:
~/.chatgpt-pro-subagent/ — estado autoritativo del daemon, cola y bloqueo
<workspace>/.chatgpt-pro-jobs/<jobId>.md — archivo de control cooperativo que ChatGPT escribe a través de LocalAnt / DevSpace
LocalAnt — puerta de enlace MCP local / conector de computadora de ChatGPT.
DevSpace — conector de entorno local / computadora que se usa con ChatGPT
Plataforma | Estado |
macOS | Compatible. Controlador de Accesibilidad nativo. |
Windows | No compatible. Necesita otro controlador de interfaz. |
Linux | No compatible. Necesita otro controlador de interfaz. |
El servidor MCP, la cola y el protocolo de archivo de control son independientes del sistema. La pieza que falta en otras plataformas es una reemplazo confiable para src/native/ax-driver.swift.
ProBridge drive la aplicación de ChatGPT en la que ya has iniciado sesión, y luego ChatGPT usa LocalAnt / DevSpace para tocar el espacio de trabajo. Trátalo como una ejecución local de tu mismo usuario, no como un sandbox.
Los archivos en tiempo de ejecución bajo ~/.chatgpt-pro-subagent son privados (0700 / 0600). Los archivos de trabajo del workspace se excluyen de git mediante .git/info/exclude cuando sea posible. Las carpetas personales y amplias se rechazan como workspaces.
npm test
npm run build:ax
node scripts/doctor.mjsMIT
Queue a follow-up in the verified same Quick Chat thread. The target must be the latest completed round and must have a captured chat title. Returns a child jobId; poll gpt56_pro_status.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | Latest completed job id in the Quick Chat thread. | |
| prompt | Yes | The follow-up task to send into that verified conversation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and it discloses key behavior: the operation is queued (non-blocking), returns a child jobId, and requires verification. It also tells the agent the next step (poll status). It stops short of describing error/failure behavior, but the core behavioral contract is transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action and target, with the second sentence covering the return and polling behavior. No filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter tool with no output schema, the description supplies the preconditions, the return value, and the follow-up polling action. It is slightly thin on failure/error conditions, but complete enough for an agent to invoke and process the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so both jobId and prompt are already documented. The description restates the recency constraint for jobId ('latest completed round') and frames prompt as a follow-up task, reinforcing but not adding meaning beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a precise action (queue a follow-up) and a specific resource (verified Quick Chat thread), clearly differentiated from siblings by emphasizing the same thread and returning a child jobId. It also names the polling sibling, so an agent can distinguish from gpt56_pro_start and gpt56_pro_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit preconditions: the target must be the latest completed round and must have a captured chat title, and directs the agent to poll gpt56_pro_status. It does not explicitly name gpt56_pro_start as the alternative for new threads, but the phrase 'follow-up in the verified same Quick Chat thread' strongly implies it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Queue one verified GPT-5.6 Sol / Effort Pro Quick Chat sub-agent job for this MCP workspace. Returns immediately with a jobId. The local daemon serializes full job execution, verifies the UI send, and keeps authoritative lifecycle state outside the workspace. Poll gpt56_pro_status.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The complete task for the LocalAnt / DevSpace-capable GPT-5.6 Pro sub-agent. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and discloses key behavior: immediate return with jobId, daemon serialization, UI verification, and external lifecycle state. It does not mention failure modes or idempotency, but the async nature and polling requirement are clearly conveyed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences each serve a distinct purpose: stating the action, describing the return behavior, and explaining daemon internals and next step. The key information is front-loaded, and there is no filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter async queue tool with no output schema, the description covers what to send, what is returned (jobId), and what to do next (poll status). It does not explicitly say how to use the jobId with siblings, but that is a minor inferable gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents the single 'prompt' parameter with a full description (100% coverage), so the baseline is 3. The tool description adds no new parameter-specific detail beyond the schema's own description, merely restating that the prompt is the task.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb 'Queue' and a specific resource 'GPT-5.6 sub-agent job', making the tool's role clear. The phrase 'for this MCP workspace' scopes it further, and the sibling tools (status, followup) are implied to have different purposes. The description distinguishes this as the start action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context that this queues a job and returns immediately, and instructs to poll gpt56_pro_status afterward. However, it does not explicitly compare to the followup sibling or state when not to use this tool, so usage is more implied than fully specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read authoritative daemon state and the latest validated cooperative control-file report for a job in this MCP workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | Job id returned by gpt56_pro_start or gpt56_pro_followup. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It signals this is a read operation (non-mutating, safe to call). However, terms like 'authoritative daemon state' and 'cooperative control-file report' are unexplained jargon that obscure the actual behavior and return semantics. The description gives hints (read-only, latest/validated data) but doesn't disclose what an agent will actually receive or whether repeated calls are safe.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no filler words, front-loading the key verb 'Read' and specifying the resource. The structure is efficient — a busy agent can extract the action quickly. Points are deducted only because the dense, jargony phrasing ('authoritative daemon state', 'validated cooperative control-file report') achieves brevity at the expense of immediate clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a status-checking tool with no output schema and no annotations, the description carries significant responsibility, and it's mostly adequate: it conveys read-only semantics and a job-scoped scope. However, it doesn't clarify what an agent will do with the output (e.g., does it return a job state like pending/running/completed?) or how 'daemon state' differs from the 'control-file report.' The existence of siblings suggests a workflow (start → status → followup), but the description doesn't articulate where the boundaries lie.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3 with no additional parameter info needed. The description's phrase 'for a job in this MCP workspace' loosely references the job context, but the schema already documents that jobId comes from gpt56_pro_start or gpt56_pro_followup. The description adds no meaning beyond what the schema provides, which is acceptable given full coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Read') and identifies a concrete resource ('authoritative daemon state and the latest validated cooperative control-file report') scoped to a job in the MCP workspace. It clearly distinguishes from siblings: start and followup are different operations, so an agent would not confuse this with them. The phrase 'in this MCP workspace' adds a scoping qualifier that reduces over-flagging as a general system status tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: check status of a job in the MCP workspace, presumably after gpt56_pro_start or gpt56_pro_followup. However, there's no explicit guidance on when to prefer this tool over siblings, when polling is appropriate, or what conditions would call for gpt56_pro_followup instead. The context is implied by the workflow rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.2.0gpt56_pro_followupgpt56_pro_startgpt56_pro_statusScored across 3 tools
Each tool corresponds to one distinct lifecycle action: starting an initial job, polling its status, and queueing a follow-up to a completed thread. There is no meaningful overlap, even though start and followup both create work.
All tools share a clear gpt56_pro_ prefix and consistent lowercase snake_case formatting. Minor deviation: start and followup are verbs while status is a noun, but the action each tool performs is still highly predictable.
Three tools is well-scoped for the server's apparent purpose: launch a job, check status, and continue the conversation. Each tool earns its place, and no unnecessary tools inflate the surface.
The primary start-status-followup workflow is fully covered and workable. The main gaps are optional lifecycle conveniences like canceling a queued/running job or listing all active jobs, but agents can work around these.
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Build and supervise fleets of agents from Claude Code, Codex or Cursor. Connects over OAuth.
