Sandbox
@Waishnav/devspace

MCP server for local coding workspaces

DevSpace is a self-hosted MCP server that exposes approved local folders to an MCP-capable chat host. It handles workspace access, shell commands, git worktrees, agent profiles, and approval flow through its CLI and daemon.

4,629 stars525 forksTypeScriptUpdated 6d ago
Who it's for

Builders who want their agent to inspect, edit, and run commands in local repos through MCP.

What it delivers

You can let an agent work in your real project files with scoped access instead of pasting code back and forth.

What it does

Local workspace access

Lets the connected host open approved project folders and work inside them.

File and shell tools

Provides read, write, edit, search, directory, and command execution in the workspace.

Git worktree support

Creates isolated worktrees so parallel agent sessions do not step on each other.

Project instruction support

Follows instructions from `AGENTS.md` and `CLAUDE.md` in the workspace.

Skill discovery

Finds local agent skills from the configured skill folders.

Owner approval flow

Requires the printed Owner password before a client can connect.

How to get it

  1. 1Install the DevSpace CLI
    npm install -g @waishnav/devspace
  2. 2Then initialize DevSpace
    devspace init
  3. 3Or run it without a global install
    npx @waishnav/devspace init
  4. 4Use the public origin without /mcp during setup
    https://your-tunnel-host.example.com
  5. 5When the client connects, DevSpace opens an Owner password approval page. Enter the…
    ~/.devspace/auth.json

README

DevSpace logo

DevSpace

Bring a Codex-style coding workflow to ChatGPT.

npm CI License

DevSpace connected to ChatGPT

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.

The same /mcp endpoint serves the 2026-07-28 per-request protocol and automatically supports older 2025-era clients through stateless compatibility handling. There is no protocol mode to configure.

Sponsors and Special Thanks

DevSpace is open to new sponsors. Get in touch to become one.

Installation

DevSpace requires Node >=22.19 <27.

Install the DevSpace CLI:

npm install -g @waishnav/devspace

Then initialize DevSpace:

devspace init

Or run it without a global install:

npx @waishnav/devspace init

During setup, DevSpace asks for:

  • where you will use it: ChatGPT, Coding Agents, or both
  • which agents DevSpace may use as subagents

The first choice is where you invoke DevSpace from. The subagent choice is separate: ChatGPT or another coding agent can delegate work through DevSpace to the agents you select there.

If you select ChatGPT, setup also asks which local project folders it may open and for your public HTTPS base URL from Cloudflare Tunnel, ngrok, Pinggy, Tailscale Funnel, or another reverse proxy. A Coding Agents-only setup asks neither question: local commands use the current Git project, or the current directory outside a repository.

Use the public origin without /mcp during setup:

https://your-tunnel-host.example.com

You will configure your MCP client with the public /mcp URL after setup. Run devspace serve when using ChatGPT. For Coding Agents, setup prints a skills command and lets the Skills CLI handle installation.

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.json

Keep that password private.

Connect Your MCP Client

The default local endpoint is:

http://127.0.0.1:7676/mcp

Most users should connect through a public HTTPS tunnel:

https://your-tunnel-host.example.com/mcp

[!NOTE] Using 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.md and CLAUDE.md
  • discover local agent skills from your skill folders
  • show tool cards and optional change summaries in ChatGPT Apps-compatible hosts

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:

  1. Start your tunnel.
  2. Run devspace serve.
  3. Connect the MCP client to your public /mcp URL.
  4. Approve the connection with the Owner password.
  5. 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.

PlatformStatusNotes
LinuxSupportedRequires Node, npm, Git, and Bash.
macOSSupportedRequires Node, npm, Git, and Bash.
Windows with Git Bash, WSL, MSYS2, or Cygwin BashSupportedGit Bash is the simplest native Windows setup.
Windows PowerShell or cmd.exe onlyNot supported yetInstall Git Bash or use WSL.

Run this to inspect your local setup:

devspace doctor

Documentation

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 Artifacts is one example.

This year, I began my journey to build a one-person, multi-agent company capable of generating millions in revenue. If you want to follow the failures, wins, lessons, and everything in between, come hang out with me on X.

More from me

ProjectAbout
GitCMS
GitCMS
Modern CMS and tooling for markdown based content sites — built for agents and humans.

Visual editing, editorial workflow, and ChatGPT/Claude content agents, with every post and page stored as files in your repo. Learn more.

Local Development

For working on DevSpace itself:

Install pnpm 11.25.0, the version pinned in package.json, with npm install --global pnpm@11.25.0, then:

pnpm install --frozen-lockfile
pnpm dev:seed
pnpm dev
pnpm typecheck
pnpm test
pnpm build
pnpm start

dev:seed forks your normal DevSpace config and SQLite state into an ignored checkout-local .devspace-dev/ directory so source builds and migrations do not modify your normal installation. Use pnpm dev:reset to discard that QA state and fork it again. See Development and Manual QA for worktree switching, ChatGPT, and database-migration workflows.

Files in the repo

Repository payload22 top-level entries
  • .agents
  • .github
  • bin
  • docs
  • examples
  • schema
  • scripts
  • skills
  • src
  • test
  • .env.example
  • .gitignore
  • AGENTS.md
  • CONTRIBUTING.md
  • LICENSE
  • package.json
  • pnpm-lock.yaml
  • pnpm-workspace.yaml
  • README.md
  • tsconfig.build.json
  • tsconfig.json
  • vite.config.ts

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k
t8y2/dbxConnectors

20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。

19k