Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
addrNoAddress to listen on (default: ":3000"):3000
base-urlNoBase URL for SSE endpoints (auto-generated if not specified)
base-pathNoBase path for SSE endpoints (default: "/mcp")/mcp
statelessNoEnable stateless mode (default: false)false
transportNoTransport protocol: stdio, sse, or streamable. Default: sse.sse
keep-aliveNoKeep-alive interval in seconds (default: 30)30
endpoint-pathNoEndpoint path for Streamable HTTP (default: "/mcp")/mcp
workspace-rootNoConfine imports, local images, and saved files to named workspace roots. Format: name=path. Can be repeated. Default root is the server's current working directory.
heartbeat-intervalNoHeartbeat interval in seconds (default: 30)30
remote-asset-timeoutNoTimeout for remote assets (e.g., 30s).
remote-asset-max-bytesNoMaximum bytes for remote assets.

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