Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
hostNoHost to bind when using the SSE transport (default 127.0.0.1).
portNoPort to bind when using the SSE transport (default 8000).
specNoPath or URL to the OpenAPI 3.x specification to expose as an MCP server.
configNoPath to a YAML or JSON config file. The spec may be supplied here instead of positionally.
timeoutNoPer-operation timeout in seconds (default 30).
base_urlNoBase URL to use instead of the API host from the spec.
transportNoMCP transport to use: 'stdio' (default) or 'sse'.
server_nameNoName of the MCP server (default 'mcpforge').
max_response_bytesNoMaximum response size in bytes before truncation (default 1000000).
allow_private_hostsNoSet to true to allow requests to private, loopback, link-local, reserved, or multicast hosts.
MCPFORGE_AUTH_<SCHEME_NAME>NoCredentials for an OpenAPI security scheme. Replace <SCHEME_NAME> with the scheme name upper-cased and with non-alphanumeric characters replaced by underscores. For Basic auth use 'username:password'.

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