Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_PORTNoServer port8000
LOG_LEVELNoLogging levelINFO
LLM_BACKENDNoBackend LLM provider: claude, ollama, or openai_compatibleclaude
CLAUDE_MODELNoAnthropic model IDclaude-sonnet-4-6
OLLAMA_MODELNoAny model pulled via ollama pullllama3.2
OPENAI_MODELNoModel name at the endpointgpt-4o-mini
LLM_MAX_TOKENSNoMax tokens for LLM completions2048
OPENAI_API_KEYNoRequired when LLM_BACKEND=openai_compatible
LLM_TEMPERATURENoGeneration temperature0.3
OLLAMA_BASE_URLNoOllama server URLhttp://localhost:11434
OPENAI_BASE_URLNoAny OpenAI-compatible endpoint URLhttps://api.openai.com/v1
RESPONSE_API_KEYNoBearer token for the response API (optional)
RESPONSE_API_URLNoNetwork management API for auto-execute (optional)
ANOMALY_THRESHOLDNoAttack confidence threshold (0.0–1.0)0.5
ANTHROPIC_API_KEYNoRequired when LLM_BACKEND=claude

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/core-ncsrd/5g-ddos-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server