Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TRUST_PROXYNoSet to 1 (or use --trust-proxy 1) when running behind a reverse proxy, otherwise express-rate-limit rejects the proxy's X-Forwarded-For header and /token crashes.
AUTH_ENABLEDNoEnable OAuth 2.1 authentication (e.g. true). Always enable authentication in production.
CORS_ORIGINSNoComma-separated list of allowed CORS origins (e.g. https://claude.ai,https://your-app.com), or '*' to allow all. CORS is disabled unless this is set.
OPENCLAW_URLNoURL of the OpenClaw gateway HTTP API (e.g. http://127.0.0.1:18789 or http://host.docker.internal:18789). Used in single-instance mode.
MCP_CLIENT_IDNoOAuth client ID used by MCP clients to authenticate (e.g. openclaw).
MCP_ISSUER_URLNoPublic HTTPS URL of this server, used to advertise OAuth metadata. Must be set when running behind a reverse proxy, otherwise OAuth metadata advertises http://localhost:3000 and clients fail to authenticate.
OPENCLAW_MODELNoModel name to use when talking to the OpenClaw gateway (e.g. openclaw).
MCP_CLIENT_SECRETNoOAuth client secret used by MCP clients to authenticate. Generate with 'openssl rand -hex 32'.
MCP_REDIRECT_URISNoComma-separated list of allowed OAuth redirect URIs, e.g. https://claude.ai/api/mcp/auth_callback,https://claude.com/api/mcp/auth_callback. Matching is exact.
OPENCLAW_AGENT_IDNoAgent ID to route requests to (e.g. main).
OPENCLAW_INSTANCESNoJSON array describing multiple OpenClaw instances for multi-instance mode, e.g. '[{"name": "prod", "url": "http://prod:18789", "token": "tok1", "default": true}, {"name": "staging", "url": "http://staging:18789", "token": "tok2"}]'. Each instance has its own name, url, token and optional default flag. Used instead of OPENCLAW_URL/OPENCLAW_GATEWAY_TOKEN.
OPENCLAW_TIMEOUT_MSNoRequest timeout in milliseconds, e.g. 300000.
OPENCLAW_GATEWAY_TOKENYesAuth 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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Maintenance

ActivityMaintained
ResponsivenessNo issues