open-computer-use
by Wide-Moat
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_API_KEY | No | Bearer token for MCP endpoint | |
| DOCKER_IMAGE | No | Sandbox container image | open-computer-use:latest |
| MCP_TOKENS_URL | No | Settings Wrapper URL (optional) | |
| OPENAI_API_KEY | Yes | LLM API key (any OpenAI-compatible) | |
| VISION_API_KEY | No | Vision API key (for describe-image) | |
| COMMAND_TIMEOUT | No | Bash tool timeout (seconds) | 120 |
| PUBLIC_BASE_URL | No | Browser-reachable URL of the Computer Use server | http://computer-use-server:8081 |
| SINGLE_USER_MODE | No | true = one container, no chat ID needed; false = require X-Chat-Id; unset = lenient | |
| SUB_AGENT_TIMEOUT | No | Sub-agent timeout (seconds) | 3600 |
| MCP_TOKENS_API_KEY | No | Settings Wrapper auth key | |
| OPENAI_API_BASE_URL | No | Custom API base URL (OpenRouter, etc.) | |
| ANTHROPIC_AUTH_TOKEN | No | Anthropic key (for Claude Code sub-agent) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessSlow