Открытый локальный MCP-мост для ChatGPT desktop Quick Chat + GPT-5.6 Pro.
Программные агенты в Codex, OpenCode, Claude или аналогичных MCP-хостах вызывают ProBridge. ProBridge ставит задачу в очередь, открывает проверенный ChatGPT Quick Chat и отправляет промпт. Внутри этой сессии ChatGPT LocalAnt / DevSpace — это коннектор, который получает доступ к вашему локальному Mac и активному рабочему пространству.
Используется квота ChatGPT Pro. Квота модели Codex не используется. Ключа API модели нет.
Текущая цель: macOS. Windows и Linux пока не поддерживаются. Приветствуются contributions, добавляющие реальный драйвер для этих платформ.
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 workspaceВызывающему агенту нужны только три инструмента:
gpt56_pro_start({ prompt })
gpt56_pro_status({ jobId })
gpt56_pro_followup({ jobId, prompt })start возвращает jobId немедленно. Опросите status. Используйте follow-up только после завершения того же сеанса Quick Chat.
Related MCP server: mcacp
LocalAnt / DevSpace даёт ChatGPT доступ к вашему Mac. ProBridge не заменяет этот коннектор и не может установить его за вас.
ProBridge предоставляет мост от вашего программного агента к ChatGPT Pro. MCP-хост отправляет запрос в ProBridge; ProBridge ставит его в очередь, запускает Quick Chat и возвращает состояние задания через MCP. Поэтому ProBridge имеет смысл, когда вы уже хотите, чтобы ChatGPT Pro выполнял локальную работу, но хотите, чтобы Codex, OpenCode, Claude или другой агент вызывал его как под-агента.
macOS
Node 20+
Инструменты командной строки Xcode (swiftc)
ChatGPT desktop со входом в Pro
Разрешение на доступ к специальным возможностям для скомпилированного bin/ax-driver
LocalAnt / DevSpace — это то, что даёт ChatGPT доступ к машине. ProBridge — это то, что позволяет другим агентам отправлять работу в этот сеанс ChatGPT.
ProBridge требует, чтобы у ChatGPT уже был коннектор, который может получить доступ к вашему Mac. Выберите один коннектор и завершите его настройку до установки ProBridge:
LocalAnt (проверенный путь): следуйте руководству по настройке LocalAnt. Быстрый старт:
npx -y localant setup
localant tools profile codinglocalant setup выведет ваш аутентифицированный MCP-эндпоинт. В настольном приложении ChatGPT перейдите в Settings → Apps & Connectors, включите Developer Mode, выберите Connectors → Create, вставьте этот MCP-эндпоинт, выберите Authentication: None и назовите коннектор LocalAnt. Убедитесь, что локальные настройки подтверждения и безопасности LocalAnt соответствуют вашим требованиям.
DevSpace: следуйте Waishnav/devspace и подключите его локальное окружение к ChatGPT в соответствии с инструкциями этого проекта.
Откройте ChatGPT Quick Chat и убедитесь, что выбранный коннектор может прочитать безвредный локальный файл перед продолжением. Это отдельная настройка на стороне ChatGPT; установка одного ProBridge не даёт ChatGPT доступа к вашему 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 создаёт ~/.codex/config.toml при необходимости, записывает запись MCP ProBridge и создаёт резервную копию с меткой времени при изменении существующего конфига. Затем предоставьте доступ к специальным возможностям для bin/ax-driver, если macOS запросит, держите настольное приложение ChatGPT открытым и начните новый чат Codex.
Он не задаёт cwd; Codex должен запустить сервер из проекта, который у вас уже открыт.
Автоматически:
node scripts/install.mjsВручную: скопируйте examples/codex.config.toml в ~/.codex/config.toml и замените абсолютный путь на путь к этому репозиторию.
Зарегистрированное имя сервера — probridge. После любого обновления начните новый чат Codex, чтобы он перезагрузил сервер MCP и демон-протокол.
Укажите stdio MCP-сервер, указывающий на этот репозиторий:
{
"mcpServers": {
"probridge": {
"command": "/Applications/ChatGPT.app/Contents/Resources/cua_node/bin/node",
"args": ["/ABS/PATH/TO/probridge/src/server.mjs"]
}
}
}См. examples/claude-code.mcp.json и examples/opencode.json. Если встроенный Node в ChatGPT отсутствует, подойдёт любой бинарник Node 20+.
MCP-хост должен запускать сервер из рабочего каталога проекта или предоставить ровно один корень file://. ProBridge отказывается работать с ~, ~/Desktop, ~/Documents и другими широкими папками.
В агенте, работающем в рабочем каталоге проекта:
gpt56_pro_start({
prompt: "Inspect the failing tests, fix the root cause, run focused tests, and report changed files."
})Отправьте задачу:
gpt56_pro_status({ jobId: "pro_..." })Отслеживайте статус:
gpt56_pro_followup({
jobId: "pro_...",
prompt: "Now implement the review findings."
})После завершения того же Quick Chat можно отправить follow-up:
npm test
npm run build:ax
node scripts/doctor.mjsЗадачи ставятся в очередь. Новый Quick Chat можно открыть сразу после подтверждения отправки предыдущего запроса. Follow-up остаётся в том же разговоре.
Статус хранится в двух местах:
~/.chatgpt-pro-subagent/ — авторитетное состояние демона, очередь и блокировка
<workspace>/.chatgpt-pro-jobs/<jobId>.md — управляемый файл, который ChatGPT записывает через LocalAnt / DevSpace
LocalAnt — MCP-шлюз ChatGPT / компьютерный коннектор
DevSpace — локальная среда / компьютерный коннектор
Платформа | Поддержка |
macOS | Поддерживается. |
Windows | Не поддерживается. Требуется другой драйвер. |
Linux | Не поддерживается. Требуется другой драйвер. |
ProBridge выполняет код на вашем Mac с вашими правами. Он не запускает непроверенный код. Однако любой агент, который может отправлять сообщения в Quick Chat, может получить доступ к локальному коннектору ChatGPT (например, LocalAnt / DevSpace). Убедитесь, что вы доверяете агентам, которым предоставляете доступ.
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.
