bash_toolLABSCO SUMMARY
The maintainers tell you where their attention went.
The README states plainly that the repository is maintained — fixes, dependency and security updates, support for the Open WebUI versions it targets — and that new features slow down because the team is building a different product. That is a useful thing to know before adopting it, and the licence conversion clause means what you install now cannot be pulled back later.
What it is
An MCP server that gives a model its own computer. Each chat session gets an isolated Docker container where it can install packages, write files, run servers and browse — and nothing leaks between sessions or users.
What you get
bash_tool— run bash inside the isolated container, with Python, Node.js and Java availableview,create_file,str_replace— read files and directories, create files, edit by text replacementsub_agent— delegate a task to an autonomous Claude Code agent with its own interactive terminal;SUBAGENT_CLIselects Claude Code, OpenAI Codex or OpenCode- A live browser: Playwright plus CDP streaming you can watch and click into while the model works
- Document skills for Word, Excel, PowerPoint and PDF, auto-injected, plus skills you write yourself
- One container per chat keyed by the
X-Chat-Idheader, withSINGLE_USER_MODEchoosing between one shared container and strict per-chat isolation - MCP primitives beyond tools: the handshake carries a per-chat system prompt in
InitializeResult.instructions, and the chat's uploads appear throughresources/listandresources/read
Requirements
Self-hosting. docker compose up --build — the first build takes around 15 minutes — after which the MCP endpoint is http://localhost:8081/mcp. OPENAI_API_KEY, or any OpenAI-compatible provider, goes in .env. MCP_API_KEY turns on Bearer authentication; leaving it empty means none. In Open WebUI, Function Calling has to be set to Native or the model will not call the tools at all. Licensed FSL-1.1-Apache-2.0, and every release converts to Apache-2.0 two years after publication. The managed endpoint is offline, so self-hosting is the supported path.
Setup effort
Run a container — build the image from the repository, then point your client at it
USE CASES
01
Letting a model actually run the code it writes
It installs what it needs, executes, reads the error, and iterates inside a container that is thrown away with the chat.
02
Producing a real document rather than markdown
Use the built-in skills to generate a styled Word, Excel, PowerPoint or PDF file, then download it from the session.
03
Handing off a long task and watching it
Delegate to the autonomous sub-agent and follow its interactive terminal while it works.
04
Running it for a team
Set strict multi-user mode so every request carries X-Chat-Id and each conversation gets its own container.
5 tools
Listed in project docs. Your client may show a different list.
viewcreate_filestr_replacesub_agentBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- Docker Engine 24+ with Docker Compose v2
- OPENAI_API_KEY (or any OpenAI-compatible provider's key) set in .env
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/Wide-Moat/open-computer-use.git
cd open-computer-use
cp .env.example .envEdit .env — set OPENAI_API_KEY (or any OpenAI-compatible provider)
Start Computer Use Server (builds workspace image on first run, ~15 min)
TERMINAL
docker compose up --buildMCP Clients
n8n
MCP Tool node → http://computer-use-server:8081/mcp
Open WebUI
OPEN WEBUI · TERMINAL
docker compose -f docker-compose.webui.yml up --buildOther routes
curl test
CURL TEST · TERMINAL
curl -X POST http://localhost:8081/mcp -H "Content-Type: application/json" -H "X-Chat-Id: test" -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'
