desktop-coworker-for-chatgpt
Self-hosted MCP coding server and unified local Control Center for ChatGPT web, enabling file editing, command execution, Git operations, and optional upstream MCP tools with conversation access controls.
README
<div align="center">
Desktop Coworker for ChatGPT
Self-hosted MCP coding server and unified local Control Center for ChatGPT web.
</div>
Independent community project; not affiliated with or endorsed by OpenAI.
Desktop Coworker for ChatGPT can read and change files, run commands, use Git, restore edit checkpoints, and proxy optional upstream MCP tools. This is high-impact access: read SECURITY.md before connecting it to a remote service.
Windows quick start
For end users, download the latest DesktopCoworker-Setup-*.exe from
GitHub Releases,
run it, and launch Desktop Coworker for ChatGPT from the Start menu. The
per-user installer includes Electron, the built application, and a verified
OpenAI Secure MCP Tunnel client; Node.js and npm are not required.
For source development, use Windows 10/11 and Git:
git clone https://github.com/colin-dmme/desktop-coworker-for-chatgpt.git
cd desktop-coworker-for-chatgpt
.\run.bat
run.bat is the source checkout entrypoint. It installs or updates Node.js, installs the
locked npm dependencies, builds the TypeScript sources, downloads the official
OpenAI Secure MCP Tunnel client when missing, and opens the Electron Control Center.
The first launch requires network access; later launches reuse installed files.
Connect an account
- In ChatGPT, enable Developer mode under Settings → Security and login. Availability may depend on your account and workspace policy.
- In OpenAI Platform tunnel settings, create a Secure MCP Tunnel, associate it with the ChatGPT workspace that will use it, and create a Runtime API key. Running and selecting the tunnel requires Tunnels Read + Use permission.
- Open the installed app, or run
run.batfrom a source checkout. - Choose Add account and enter a workspace, tunnel ID, Runtime API key, and ports.
- Start the account and wait until MCP, Admin, Tunnel, and Ready are green.
- Open ChatGPT Plugins, select the plus
button, choose Tunnel under Connection, and select the tunnel or paste its
tunnel_id. - Review the discovered tools, create the connection, and add it to a new conversation from the tools menu. Refresh the connection after server metadata changes.
See the official OpenAI documentation for Secure MCP Tunnel and connecting an MCP server from ChatGPT.
Profiles created by the former PySide dashboard are migrated automatically.
Profiles, telemetry, logs, runtime configuration, and upstream MCP settings live
outside the repository at %LOCALAPPDATA%\DesktopCoworkerForChatGPT.
The Control Center never returns a Runtime API key to browser JavaScript. The generated tunnel YAML also contains no key; it is passed only to the tunnel child process. The desktop build encrypts Runtime API keys with operating-system-backed Electron safe storage; all application data must still be treated as sensitive.
Conversation access control
Conversation access protection is off by default, preserving the original one-click
experience: ChatGPT can use tools as soon as the connector is ready. Owners of shared
accounts can opt in per account on the Chat access page. When enabled, a new
ChatGPT conversation cannot call computer tools until the local owner approves its
pending request or generates a short-lived one-time code.
Grants are scoped to one account and workspace, have a read, edit, or execute
tier, expire automatically, and can be revoked immediately.
The Chat access history keeps a local audit trail of pending requests, approvals, denials, revocations, protection changes, and one-time-code outcomes. It can be filtered by event, permission, date, fingerprint, label, or tool, and entries can be deleted individually or in filtered batches.
ChatGPT conversation, subject, and organization identifiers are stored only as keyed fingerprints. One-time codes are stored only as keyed hashes, are single-use, expire after two minutes by default, and trigger a temporary lockout after repeated failed attempts. Tool activity recursively redacts password, code, token, authorization, credential, and cookie fields before persistence or streaming.
One interface, three local services
Electron window -> localhost Control Center :2999
├─ manages accounts, ports, logs, activity, settings and upstream MCP
└─ starts one isolated pair per account
├─ MCP server :3000 (default)
│ ├─ filesystem / patches / checkpoints
│ ├─ shell / processes / Git
│ ├─ project context / memory
│ └─ optional upstream MCP servers
├─ Admin API :3001 (internal data source; /ui redirects to :2999)
└─ OpenAI Secure MCP Tunnel health :8080
Electron supplies the native window, tray, lifecycle, encrypted secret storage, installer, and updater. The existing web Control Center remains localhost-only and is reused inside that desktop shell instead of being rewritten.
Repository layout
public/control/ Unified Control Center frontend
public/control/locales/ Extensible English/Vietnamese UI catalogs
public/ui/ Legacy per-server fallback UI
src/control/ Account supervisor, telemetry and Control API
src/desktop/ Electron window, tray, secrets and updater
src/admin/ Per-server localhost Admin API
src/lib/ MCP services and infrastructure
src/tools/ MCP tool registration
scripts/windows/ Bootstrap and lifecycle scripts
scripts/release/ Release validation scripts
scripts/development/ Maintainer utilities
config/examples/ Safe example configurations
docs/ User and architecture documentation
third_party/ Bundled dependency licenses and notices
tests/control/ Control Center tests
tests/server/ MCP server tests
run.bat One-click Windows entrypoint
public/ui remains only as a standalone-server compatibility fallback. Normal
launches redirect its /ui route to the unified Control Center.
Development
Node.js 22.5 or newer is required because local telemetry uses the built-in SQLite module.
npm ci
npm run build
npm test
npm run test:all
npm run desktop:dev
Useful entrypoints:
npm start— Electron Control Center and account supervisor.npm run start:web— browser-only compatibility and diagnostics entrypoint.npm run start:server— one standalone MCP server without the supervisor.npm run desktop:dev— build and launch the Electron app from source.npm run desktop:dist— build a local Windows NSIS installer.npm run dev— browser Control Center in TypeScript watch mode.npm run dev:server— standalone MCP server in watch mode..\run.bat -SkipLaunch— complete Windows bootstrap smoke test.
See Desktop build and release guide for source ownership, versioning, signing, packaging, and GitHub release automation.
The Control Center defaults to English and remembers a language selected in the
UI. To add another language, copy a catalog under public/control/locales, keep
the same message keys as en.js, and register it in public/control/i18n.js.
The i18n test fails when catalogs or referenced keys fall out of sync.
Configuration
The Control Center writes per-account environment files under local app data.
For standalone server development, copy .env.example to .env.
| Variable | Default | Purpose |
|---|---|---|
CONTROL_CENTER_PORT |
2999 |
Unified local UI and Control API |
HOST |
127.0.0.1 |
MCP bind address; keep loopback for tunnel use |
PORT |
3000 |
MCP HTTP port |
ADMIN_PORT |
3001 |
Per-server localhost Admin API |
WORKSPACE_PATH |
current directory | Default project directory |
CHATGPT_TOOL_PROFILE |
slim |
slim or full exposed tool set |
SHELL_TIMEOUT |
120 |
Foreground command timeout in seconds |
CHECKPOINT_ENABLED |
true |
Enable edit checkpoints and rewind |
MCP_UPSTREAM_CONFIG |
local app data | Shared upstream MCP configuration |
CHATGPT_ACCESS_CONTROL |
off |
off, observe, or enforce conversation gate; Control Center sets it per account |
CHATGPT_ACCESS_DB |
local app data | Local SQLite access requests, grants, and hashed codes |
The workspace is a default working directory, not a sandbox. Absolute paths and commands run with the current Windows user's permissions.
Documentation
- Control Center guide
- Vietnamese Control Center guide / Hướng dẫn tiếng Việt
- Contributing
- Support
- Code of Conduct
- Changelog
- Security
- Agent onboarding
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。