Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort for the HTTP server.5000
CORS_ORIGINNoAllowed CORS origin. Defaults to all origins.*
MONGODB_URINoMongoDB connection string for the audit log. When unset, an in-memory audit log is used.
LLM_MAX_CHARSNoMaximum number of characters sent to the LLM for detection.6000
ANALYSIS_MODELNoModel used by the /analyze endpoint. Defaults to the same as OPENROUTER_MODEL.
LLM_TIMEOUT_MSNoTimeout in milliseconds for OpenRouter LLM calls.30000
MCP_SERVER_URLNoThe URL of the upstream MCP server that MCP-Guard protects. Defaults to the dlptest public server.dlptest public server
OPENROUTER_MODELNoThe OpenRouter model used for AI detection. Defaults to a free tier model.openrouter/free
SOURCE_MAX_CHARSNoMaximum number of characters scanned from an HTTP response body.20000
SOURCE_MAX_LIMITNoMaximum allowed row or document limit for data source queries.200
SOURCE_TIMEOUT_MSNoTimeout in milliseconds for data source connector requests.15000
OPENROUTER_API_KEYNoAPI key for OpenRouter. When unset, the AI detection pass is skipped and /analyze returns 400.
ANALYSIS_TIMEOUT_MSNoTimeout in milliseconds for /analyze calls.30000
SOURCE_DEFAULT_LIMITNoDefault row or document limit for data source queries.20

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