CodeMCP MCP server
Commit Nov 15, 2026Provides workspace-aware execution, context, and agent orchestration for AI clients through secure tunnels and local runtime control.
Also known as mewisme/codemcp
- Stars
- 4
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 15, 2026
- License
- MIT
What is CodeMCP MCP?
CodeMCP provides workspace-aware execution, context, and agent orchestration for AI clients through secure tunnels and local runtime control.
Summary generated from the project's README
About CodeMCP MCP server
Providing workspace-aware execution and agent orchestration for AI clients is the primary function of CodeMCP. It allows developers to grant AI models controlled access to specific projects through registered workspace scopes. By running locally on Linux, macOS, or Windows, it ensures that filesystem, shell, Git, and process operations remain constrained to authorized directories.
Users can connect ChatGPT via the OpenAI Secure MCP Tunnel, which uses an outbound connection to avoid the need for public inbound endpoints. This setup requires an OpenAI runtime key with Tunnels Read and Use permissions. For other generic MCP clients, the server supports local stdio or Streamable HTTP transports using either a Base profile or an OpenAI profile.
Control remains local through a variety of operator surfaces including a CLI, TUI, Browser Admin, and Telegram. This architecture ensures that approvals, secrets, and runtime policies are managed on the host machine even when the client projection changes. The system is extensible through integrations like CodeGraph, RTK, and various LLM providers.
What you can do with it
- 1Connect ChatGPT to local projectsSet up an outbound-only connection to ChatGPT using the Secure MCP Tunnel to interact with your local files.
- 2Restrict AI access to specific directoriesDefine workspace boundaries to ensure the AI only operates within registered project scopes.
- 3Manage AI agents via mobileUse Telegram as an operator surface to interact with the same application services running your MCP server.
- 4Use generic MCP clients locallyConnect standard MCP clients to your workspace using local stdio or HTTP transports.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 16, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemewisme/codemcp is public and reachablegithub.com/mewisme/codemcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/mewisme/codemcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCodeMCP
CodeMCP is a workspace-aware execution, context, and agent orchestration server for AI clients.
Single Go binary · OpenAI Secure MCP Tunnel · Linux, macOS, and Windows
Get started · MCP profiles · Security · Documentation
CodeMCP runs locally and gives supported AI clients controlled access to explicitly registered projects. For ChatGPT, the primary path is OpenAI Secure MCP Tunnel: the local runtime makes an outbound connection to OpenAI, so the MCP server does not need a public inbound endpoint. Generic MCP clients can use the same runtime through local stdio or Streamable HTTP.
Overview
One runtime owns canonical feature execution. Workspace scope and permissions constrain host access, while instruction context, approvals, local control surfaces, Telegram, and managed integrations feed the same runtime. MCP profiles only change the client-facing projection:
- OpenAI profile — used by OpenAI Secure MCP Tunnel and available to direct HTTP clients with
--profile openai. - Base profile — standards-oriented generic MCP projection and the default for direct local MCP transports.
See MCP profiles and transports.
Why CodeMCP
- Private OpenAI path — Secure MCP Tunnel keeps the default ChatGPT connection outbound-only from your machine.
- Workspace-bound execution — filesystem, shell, Git, process, context, memory, rules, skills, plans, and checkpoints operate against registered
ws_*scopes. - Local authority — approvals, control guards, secrets, and runtime policy remain local even when the client projection changes.
- Multiple operator surfaces — CLI, TUI, Browser Admin, and Telegram use the same application services.
- Extensible runtime — optional RTK, CodeGraph, TypeSafe/SystemOne, LLM providers, and upstream MCP servers extend the same runtime.
Install
The installed command is always cm. Pick one installation owner and keep using that owner for upgrades.
Managed direct install
Best when you want a per-user installation managed by CodeMCP itself. cm upgrade verifies, stages, activates, and can roll back managed-direct releases.
Linux / macOS
curl -fsSL get.mewis.me/codemcp.sh | sh
Windows PowerShell
irm https://get.mewis.me/codemcp.ps1 | iex
Windows setup executables
The setup executable bootstraps the same managed-direct layout as the PowerShell installer.
Homebrew
brew tap mewisme/mew
brew install --cask codemcp
Homebrew owns upgrades for this installation.
Scoop
scoop bucket add mew https://github.com/mewisme/scoop-mew
scoop install mew/codemcp
Scoop owns upgrades for this installation.
Debian packages
| Architecture | Package |
|---|---|
| amd64 | codemcp_linux_amd64.deb |
| arm64 | codemcp_linux_arm64.deb |
sudo apt install ./codemcp_linux_amd64.deb
Use the arm64 package on ARM64. Debian owns upgrades after package installation.
RPM packages
| Architecture | Package |
|---|---|
| amd64 | codemcp_linux_amd64.rpm |
| arm64 | codemcp_linux_arm64.rpm |
sudo dnf install ./codemcp_linux_amd64.rpm
Use the arm64 package on ARM64. RPM/DNF owns upgrades after package installation.
Manual release archives
Release asset filenames are stable; the Git tag carries the release version. Supported release targets are Linux x64/ARM64, macOS x64, and Windows x64.
| Platform | Architecture | Archive |
|---|---|---|
| Linux | amd64 / x64 | codemcp_linux_amd64.tar.gz |
| Linux | arm64 | codemcp_linux_arm64.tar.gz |
| macOS | amd64 / x64 | codemcp_darwin_amd64.tar.gz |
| Windows | amd64 / x64 | codemcp_windows_amd64.zip |
For an exact version, pin the tag while keeping the stable filename:
https://github.com/mewisme/codemcp/releases/download/vX.Y.Z/codemcp_linux_amd64.tar.gz
Release executable/package/setup assets are covered by codemcp_checksums.txt; its Sigstore bundle is codemcp_checksums.txt.sigstore.json.
5-minute OpenAI setup
Create the tunnel in OpenAI Platform → Tunnels, then use its tunnel_... ID below.
cm init
cm workspace register ~/projects/my-project
cm tunnel configure --enabled --id tunnel_...
cm tunnel key set
cm up
cm status
cm tunnel status
Use an OpenAI runtime key with Tunnels Read + Use. It is not an OpenAI Admin API key.
In ChatGPT developer mode, create a developer-mode app/plugin using Tunnel, select the same tunnel, scan tools, review the discovered surface, and enable it.
OpenAI's current Secure MCP Tunnel documentation is the source of truth for Platform permissions, workspace associations, and ChatGPT UI details: https://developers.openai.com/api/docs/guides/secure-mcp-tunnels.
Generic MCP clients
The Base profile is the default for direct local transports:
cm mcp stdio --workspace ~/projects/my-project
cm mcp http --workspace ws_...
A direct HTTP client can request the OpenAI projection explicitly:
cm mcp http --profile openai --workspace ws_...
Profiles do not bypass CodeMCP authentication, workspace scope, control guards, or approvals. See MCP profiles and transports.
Operate CodeMCP
cm status
cm logs -f
cm config verify
cm workspace list
cm tui
Use cm <command> --help for the installed binary's exact command and flag surface.
Security model
CodeMCP is an application-level workspace and control boundary, not a kernel sandbox. It canonicalizes workspace roots, uses root-anchored filesystem operations for sensitive paths, rejects unsafe symlink escapes, separates control-plane mutations from ordinary workspace work, and stores managed credentials outside normal plaintext structured config.
For isolation from hostile native code running as the same OS user, use an OS sandbox, container/VM, or separate operating-system identity.
Read Security before widening filesystem or network access.
Documentation
| Goal | Guide |
|---|---|
| Install and connect ChatGPT | Getting started |
| Understand OpenAI and Base MCP profiles | MCP profiles and transports |
| Scope projects and additional roots | Workspaces |
| Manage workspace/global Agent Skills and GitHub-backed skills | Skills |
| Run, inspect, update, and use operator UIs | Operations |
| Configure settings, auth, and secrets | Configuration |
| Configure RTK, CodeGraph, TypeSafe, LLM, and Telegram | Integrations |
| Understand trust boundaries and privacy | Security |
| Diagnose failures | Troubleshooting |
| Build, test, and contribute | Development |
See the documentation index for suggested reading paths.
Development
make bootstrap
make check
make test
See Development and CONTRIBUTING.md.
License
CodeMCP MCP questions
What operating systems are supported?
CodeMCP is available for Linux, macOS, and Windows.
Is CodeMCP a kernel sandbox?
No, it is an application-level workspace and control boundary. For isolation from hostile native code, you should use an OS sandbox, container, or VM.
Can I use it with generic MCP clients?
Yes, generic clients can use the runtime through local stdio or Streamable HTTP using the Base profile.