OpenClaw MCP Server
by yves5581
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRUST_PROXY | No | Set to 1 when running behind a reverse proxy so rate limiting accepts the X-Forwarded-For header | 1 |
| AUTH_ENABLED | No | Enable OAuth 2.1 authentication (recommended for production / HTTP mode) | true |
| CORS_ORIGINS | No | Comma-separated list of allowed CORS origins (e.g. https://claude.ai). CORS is disabled unless set; use '*' to allow all origins | |
| OPENCLAW_URL | No | URL of the OpenClaw gateway to connect to (e.g. http://host.docker.internal:18789) | http://127.0.0.1:18789 |
| MCP_CLIENT_ID | No | OAuth client ID used by MCP clients (e.g. Claude.ai) to authenticate | openclaw |
| MCP_ISSUER_URL | No | Public HTTPS URL of this server, required when running behind a reverse proxy so OAuth metadata advertises the correct issuer instead of http://localhost:3000 | |
| OPENCLAW_MODEL | No | Model name used when talking to the OpenClaw gateway | openclaw |
| MCP_CLIENT_SECRET | No | OAuth client secret used by MCP clients to authenticate; generate with e.g. 'openssl rand -hex 32' | |
| MCP_REDIRECT_URIS | No | Comma-separated list of allowed OAuth redirect URIs so authorization codes can only be delivered to trusted callbacks | https://claude.ai/api/mcp/auth_callback,https://claude.com/api/mcp/auth_callback |
| OPENCLAW_AGENT_ID | No | OpenClaw agent ID to target | main |
| OPENCLAW_INSTANCES | No | JSON array defining multiple OpenClaw gateways to orchestrate from a single MCP server. Each entry has name, url, token and optional default, e.g. '[{"name": "prod", "url": "http://prod:18789", "token": "tok1", "default": true}, {"name": "staging", "url": "http://staging:18789", "token": "tok2"}]' | |
| OPENCLAW_TIMEOUT_MS | No | Request timeout in milliseconds for OpenClaw calls | 300000 |
| OPENCLAW_GATEWAY_TOKEN | No | Authentication token for the OpenClaw gateway |
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
ResponsivenessNo issues