ryns-code-mcp
Provides tools for interacting with Git repositories, including checking status, viewing diffs, inspecting commit history, and querying branch information.
Provides tools for working on a Linux machine, including file operations, shell commands, process management, screenshots, desktop input, camera/screen recording, and system statistics.
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., "@ryns-code-mcprun the tests and show me what failed"
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.
ryns-code-mcp
An MCP server, written in Go, that lets an AI assistant work on your Linux machine: files, search, shell commands, long-running processes, git, screenshots, simple local spreadsheets, and more.
⚠️ Security warning
This server gives whoever can talk to it full control of the machine it runs on: arbitrary shell commands (
execute_command), reading/writing/deleting files, screenshots, clipboard, keyboard and mouse control, camera and screen recording.It has no authentication of its own. Never expose it directly to the internet. If you serve it over HTTP through a tunnel or reverse proxy, put real authentication in front of it (for example Cloudflare Access or an authenticating proxy). Stdio mode is the safe default. Use at your own risk.
Related MCP server: mcp-linux-ops
Tools
Area | Tools |
Shell & processes |
|
Files |
|
Desktop |
|
Git |
|
Local sheets |
|
Misc |
|
Some tools depend on external programs (screenshots, OCR, input control, camera
and recording, opencode, linters). They fail gracefully when those are missing.
Build and run
Requires Go 1.25+.
go build -o ryns-code-mcp .
# stdio (default): launch it from your MCP client
./ryns-code-mcp
# Streamable HTTP on 127.0.0.1:8799 (for use behind an authenticated tunnel)
./ryns-code-mcp --port 8799./run is a small wrapper that builds into .state/, tracks state, and loads
a local .env. See ./run --help.
In HTTP mode the server also serves /assets/ (static files from
<workspace>/assets, including recordings made by record_video) and
/api/save/<name> (used by the bundled sheet viewer). Treat both as public once
the server is reachable.
Connecting to Claude, ChatGPT or other remote clients
Clients that run in the cloud (Claude custom connectors, ChatGPT connectors, and
similar) cannot reach 127.0.0.1 on your machine. They need a public HTTPS URL
that points at the server's Streamable HTTP endpoint. To get one, run the server
in HTTP mode and forward the port with a tunnel such as
ngrok, Cloudflare Tunnel
(cloudflared), or a similar service (Tailscale Funnel, localtunnel, your own
reverse proxy, ...).
Start the server:
./ryns-code-mcp --port 8799Forward the port with the tunnel of your choice:
# ngrok ngrok http 8799 # Cloudflare quick tunnel (temporary URL, no account needed) cloudflared tunnel --url http://127.0.0.1:8799For a stable hostname, use a named Cloudflare tunnel or a reserved ngrok domain instead of a temporary URL.
Add the tunnel URL with
/mcpat the end as a remote MCP server / connector in your client, for examplehttps://your-tunnel.example.com/mcp.Set
RYNS_PUBLIC_BASE_URLto the tunnel URL (without/mcp) so links returned bysheet_urlandrecord_videowork from outside.
Before you do this, protect the URL. Anyone who has the tunnel URL can use every tool on your machine, because the server does not authenticate requests. Put authentication in front of the tunnel (Cloudflare Access, an authenticating reverse proxy, or your tunnel provider's auth features; check which methods your client supports), do not share the URL, and shut the tunnel down when you are not using it.
Configuration
Variable | Default | Purpose |
|
| Directory the tools operate in |
|
| Base URL used in links returned by |
Copy .env.example to .env to set these locally.
Repository layout
main.gois the current implementation.docs/holds the design notes written while adding each feature.src/index.tsis an earlier TypeScript prototype with a smaller tool set. It is kept for reference and is no longer maintained.
License
MIT, see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Linux VMs for AI agents: create VMs, run commands, edit files and open preview URLs.
Persistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides AI assistants with the ability to control Linux desktop environments through tools for file management, application launching, and system operations like clipboard access. It includes a multi-level security model to manage permissions for safe, elevated, and restricted actions.6MIT
- AlicenseBqualityDmaintenanceEnables LLMs to execute shell commands and perform file operations on a Linux system, exposing tools like execute_command, read_file, write_file, and more.10MIT
- AlicenseBqualityCmaintenanceEnables AI agents to remotely control Linux machines via SSH with 35 tools for session management, file transfer, system administration, Docker, and CTF operations.351MIT
- AlicenseNot gradedqualityAmaintenanceEnables tool-capable AI models to operate a private Linux desktop and headless browser, with terminal, file, and application controls, while keeping your physical mouse and keyboard separate.MIT