Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | No | Groq API key | |
| OPENAI_API_KEY | No | OpenAI API key | |
| CODEWATCH_DATA_DIR | No | SQLite storage location | ~/mcp-data/codewatch-memory/ |
| CODEWATCH_LOG_LEVEL | No | Logging verbosity | info |
| CODEWATCH_GROQ_MODEL | No | Groq model to use | llama-3.3-70b-versatile |
| CODEWATCH_AUTO_REFLECT | No | Enable auto-reflection | true |
| CODEWATCH_GOOGLE_MODEL | No | Google model to use | gemini-2.5-flash |
| CODEWATCH_LLM_PROVIDER | No | Primary LLM provider (google, openai, groq) | |
| CODEWATCH_OPENAI_MODEL | No | OpenAI model to use | gpt-4o-mini |
| CODEWATCH_MAX_COMPRESSION | No | Max compression level (0-3) | 3 |
| CODEWATCH_FALLBACK_PROVIDER | No | Fallback LLM provider (google, openai, groq, none) | openai |
| CODEWATCH_REFLECT_THRESHOLD | No | Auto-reflect trigger threshold in tokens | 40000 |
| GOOGLE_GENERATIVE_AI_API_KEY | No | Google API key |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |