OpenClaw MCP Server
by pZhou4304
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 (Caddy, nginx, Traefik, Cloudflare Tunnel, etc.) so the X-Forwarded-For header is trusted. | |
| AUTH_ENABLED | No | Enable OAuth 2.1 authentication for the HTTP transport ("true" or "false"). Defaults to false, but should always be enabled in production. | |
| CORS_ORIGINS | No | Comma-separated list of allowed CORS origins (e.g. https://claude.ai,https://your-app.com). CORS is disabled by default; set to * to allow all origins. | |
| OPENCLAW_URL | No | URL of the OpenClaw gateway HTTP API (e.g. http://127.0.0.1:18789). | |
| MCP_CLIENT_ID | No | OAuth client ID used when authentication is enabled (e.g. openclaw). | |
| MCP_ISSUER_URL | No | Public HTTPS URL of this server advertised in OAuth metadata (e.g. https://mcp.your-domain.com). Required when running behind a reverse proxy so clients can authenticate. | |
| OPENCLAW_MODEL | No | Model name to use (e.g. openclaw). | |
| MCP_CLIENT_SECRET | No | OAuth client secret used when authentication is enabled. Generate a secure value with `openssl rand -hex 32`. | |
| MCP_REDIRECT_URIS | No | Comma-separated list of allowed OAuth redirect URIs, e.g. https://claude.ai/api/mcp/auth_callback,https://claude.com/api/mcp/auth_callback. | |
| OPENCLAW_AGENT_ID | No | Agent ID to target on the OpenClaw gateway (e.g. main). | |
| OPENCLAW_INSTANCES | No | JSON array of OpenClaw instance configurations enabling multi-instance mode. Each entry has a name, url, token, and an optional default flag, 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 (e.g. 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