Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GROQ_API_KEYNoGroq API key
OPENAI_API_KEYNoOpenAI API key
CODEWATCH_DATA_DIRNoSQLite storage location~/mcp-data/codewatch-memory/
CODEWATCH_LOG_LEVELNoLogging verbosityinfo
CODEWATCH_GROQ_MODELNoGroq model to usellama-3.3-70b-versatile
CODEWATCH_AUTO_REFLECTNoEnable auto-reflectiontrue
CODEWATCH_GOOGLE_MODELNoGoogle model to usegemini-2.5-flash
CODEWATCH_LLM_PROVIDERNoPrimary LLM provider (google, openai, groq)google
CODEWATCH_OPENAI_MODELNoOpenAI model to usegpt-4o-mini
CODEWATCH_MAX_COMPRESSIONNoMax compression level (0-3)3
CODEWATCH_FALLBACK_PROVIDERNoFallback LLM provider (google, openai, groq, none)openai
CODEWATCH_REFLECT_THRESHOLDNoAuto-reflect trigger threshold in tokens40000
GOOGLE_GENERATIVE_AI_API_KEYNoGoogle API key

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/KlausAndrade/codewatch'

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