DevSpace
Uses Cloudflare Tunnel as a public HTTPS front end so a locally running DevSpace server can be reached by ChatGPT via an HTTPS /mcp URL like https://your-tunnel-host.example.com/mcp.
Runs git commands inside opened workspaces and creates isolated Git worktrees to support multiple parallel coding sessions on the same repository.
Uses an ngrok tunnel to expose the local DevSpace MCP endpoint over public HTTPS so an MCP client can connect to it.
Uses Tailscale Funnel to publish the local DevSpace server over public HTTPS for MCP client connections.
Click on "Deploy 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., "@DevSpaceopen my ~/projects/api folder and run the tests"
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.

Give ChatGPT a secure connection to your own machine and Turn ChatGPT into Codex
DevSpace is a self-hosted MCP server that lets ChatGPT read, edit, search, and run code in your real local projects — your files, your tools, your terminal — without uploading anything to a third party. You run it on your machine, expose it through a tunnel you control, and approve the connection with a password only you have.
Sponsors and Special Thanks
Related MCP server: DevSpace
Installation
macOS App (recommended)
Download the latest DevSpace-macOS-*.dmg from the
GitHub Releases page, drag DevSpace.app
to Applications, and open it. The App bundles its own Node runtime and provides the full Control Center for
workspace roots, managed Tunnel, Browser control, Computer Use permissions, login startup, service status,
and diagnostics.
For a repeatable one-command install or update, use the release bootstrap. It installs into
~/Applications/DevSpace.app, verifies the published SHA-256 checksum, and delegates the actual replacement
to DevSpace's transactional updater:
curl -fsSL https://github.com/arthurwangwsx-code/DevSpace/releases/latest/download/install.sh | bashAfter installation, updates and rollback are also available through the App or CLI:
devspace update --check
devspace update
devspace rollback
devspace uninstallNormal uninstall preserves ~/.devspace configuration and credentials; use --purge-config only when an
explicit full reset is desired.
Development-signed releases may require Control-click → Open on first launch until the project has a Developer ID Application certificate and notarization configured. The Release notes state the trust status for each build.
CLI / source development
The CLI/source path requires Node >=22.19 <27.
See Distribution, Control Center, and Tunnel Architecture for the App/runtime/Tunnel architecture and release model.
Install the DevSpace CLI:
npm install -g @waishnav/devspaceThen initialize and start the server:
devspace init
devspace serveOr run it without a global install:
npx @waishnav/devspace init
npx @waishnav/devspace serveDuring setup, DevSpace asks for:
the local project folders ChatGPT is allowed to open through DevSpace
the local port, usually
7676your public HTTPS base URL from Cloudflare Tunnel, ngrok, Pinggy, Tailscale Funnel, or another reverse proxy
Use the public origin without /mcp during setup:
https://your-tunnel-host.example.comYou will configure your MCP client with the public /mcp URL after setup.
When the client connects, DevSpace opens an Owner password approval page. Enter
the Owner password printed by devspace init. It is also stored in:
~/.devspace/auth.jsonKeep that password private.
Connect Your MCP Client
The default local endpoint is:
http://127.0.0.1:7676/mcpMost users should connect through a public HTTPS tunnel:
https://your-tunnel-host.example.com/mcpUsing DevSpace as an MCP connector isn't against OpenAI's Usage Policies — it's a standard custom App/connector setup, and writing or running code isn't a restricted use case. But your account is governed by your usage, not by DevSpace. Don't point it at anything that would violate your provider's terms. Used normally, you're fine. (Based on OpenAI's Usage Policies and Service Terms as of June 2026.)
What ChatGPT Can Do
Once connected, ChatGPT can open one of your approved project folders as a workspace. From there, it can inspect the repo, make scoped edits, run commands, and show you what changed.
DevSpace gives ChatGPT tools to:
read, write, and edit files inside the opened workspace
search code and inspect directories
run shell commands for tests, builds, git, and package scripts
use isolated Git worktrees for parallel coding sessions
follow project instructions from
AGENTS.mdandCLAUDE.mddiscover local agent skills from your skill folders
show tool cards and optional change summaries in ChatGPT Apps-compatible hosts
Capability gateway preview
DevSpace can also mount stdio or Streamable HTTP MCP servers as dynamic
capabilities while keeping its public API fixed. Set DEVSPACE_CAPABILITIES=1, then connect an Agent
to /capabilities/mcp or use /api/capabilities/v1 from CI. See
Mount external MCP servers for the manifest format and CLI, and
Dynamic Provider management for runtime install/load APIs. The
current Chrome Provider reuses the official
chrome-devtools daemon, so CLI, CI, and DevSpace share one current-profile debugging connection.
Mental Model
DevSpace is remote access to selected local folders.
You decide which roots are allowed. The MCP client still has powerful local capabilities inside an opened workspace, including shell execution. Treat a connected client like a trusted coding partner with access to your machine.
For a normal ChatGPT coding session:
Start your tunnel.
Run
devspace serve.Connect the MCP client to your public
/mcpURL.Approve the connection with the Owner password.
Ask ChatGPT to open a project inside one of your allowed roots.
Platform Support
DevSpace supports Linux, macOS, and Windows environments with a Bash-compatible shell.
Platform | Status | Notes |
Linux | Supported | Requires Node, npm, Git, and Bash. |
macOS | Supported | Requires Node, npm, Git, and Bash. |
Windows with Git Bash, WSL, MSYS2, or Cygwin Bash | Supported | Git Bash is the simplest native Windows setup. |
Windows PowerShell or | Not supported yet | Install Git Bash or use WSL. |
Run this to inspect your local setup:
devspace doctorDocumentation
Product Capability Map — start here for the complete product design, feature inventory, architecture boundaries, and documentation map
Native macOS Onboarding — SwiftUI Control Center, Browser installation and permission-guided first run
MCP Resource Control and High-Concurrency Stability (Chinese)
Workspace handles are persistent. Keep them available across later turns;
call release_workspace only when the user requests resource release or a
workspace is known to be unused for a long time. It evicts only reconstructable
in-memory metadata, and later calls with the same workspaceId restore it
automatically. Checkout-mode open_workspace also resumes the latest handle
for the same path by default.
Philosophy
Every piece of software is becoming conversational. Natural language is redefining how we interact with tools, workflows, and systems.
My bet is that ChatGPT becomes the operating system for everything. Once we reach AGI, we will simply talk to ChatGPT, and it will prompt, coordinate, and orchestrate sub-agents that set up the right loops for us.
We are not there yet.
DevSpace is one attempt to fast-forward that future: a way for MCP-capable hosts like ChatGPT and Claude to work directly with local project files through explicit, inspectable tools.
Built by Waishnav
I'm Waishnav, I like building opinionated products and tools, and DevSpace is one example of that. This year, I started my journey to build a single-person and multiple-agents company doing multiple millions in revenue. If you want to watch the failures, wins, lessons, and everything in between, come hang out with me on X.
More from me
Local Development
For working on DevSpace itself:
npm install --include=dev
npm run dev
npm run typecheck
npm test
npm run build
npm run startThis server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Related MCP Servers
- AlicenseBqualityDmaintenanceSelf-hosted MCP server that enables ChatGPT to access and operate on local project files after OAuth authorization, without uploading the workspace elsewhere.38108MIT
- AlicenseNot gradedqualityCmaintenanceA self-hosted MCP server that gives ChatGPT a secure connection to your local machine, enabling it to read, edit, search, and run code in your projects.1,342 npmMIT
- AlicenseNot gradedqualityCmaintenanceA self-hosted MCP server that brings a Codex-style coding workflow to ChatGPT, allowing it to read, edit, search, and run code in your local projects.MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that bridges ChatGPT Web Pro to local tools, enabling file read/write, shell command execution, git operations, and search within a specified project directory.21MIT