Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NODE_ENVNoEnvironment mode: 'development' or 'production'. Set to 'production' for security lockdown.development
MCP_PHYSICS_WS_PORTNoWeb physics WebSocket port.8080
MCP_PHYSICS_WS_TOKENNo256-bit cryptographic secret for WebSocket handshake. If unset, a secure token is auto-generated and written to data/.runtime_token.
MCP_PHYSICS_GRPC_PORTNoNative engine HTTP/2 gRPC streaming port.50051
MCP_PHYSICS_CORS_ORIGINSNoComma-separated list of allowed CORS origins. Default '*' in development, '' in production.*
MCP_PHYSICS_BYOK_PROVIDERNoBYOK LLM provider: mock, openai, anthropic, gemini, ollama.mock
MCP_PHYSICS_GRPC_WEB_PORTNoBrowser gRPC-Web proxy & metrics port.50052
MCP_PHYSICS_MAX_HTTP_BODYNoHTTP / gRPC-Web request body ceiling (10MB).10485760
MCP_PHYSICS_AUTHORITY_MODENoAuthority mode for state validation: 'playtest' or 'debug'.
MCP_PHYSICS_MAX_WS_CLIENTSNoMaximum concurrent WebSocket connections.128
MCP_PHYSICS_MAX_WS_PAYLOADNoWebSocket frame size limit (5MB).5242880

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