genetic-mcp
by andrasfe
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODEL | Yes | REQUIRED - Default model for idea generation (e.g., meta-llama/llama-3.2-3b-instruct) | |
| OPENAI_MODEL | No | OpenAI-specific model override (defaults to MODEL) | |
| COHERE_API_KEY | No | Optional API key for Cohere embeddings | |
| OPENAI_API_KEY | No | Optional API key for OpenAI embeddings | |
| VOYAGE_API_KEY | No | Optional API key for Voyage AI embeddings | |
| ANTHROPIC_MODEL | No | Anthropic-specific model override (defaults to MODEL) | |
| EMBEDDING_MODEL | No | Model for the chosen embedding provider | |
| GENETIC_MCP_GPU | No | Enable GPU acceleration (true/false) | false |
| OPENROUTER_MODEL | No | OpenRouter-specific model override (defaults to MODEL) | |
| WORKER_POOL_SIZE | No | Number of parallel LLM workers | 5 |
| ANTHROPIC_API_KEY | No | Optional API key for Anthropic LLM provider | |
| GENETIC_MCP_DEBUG | No | Enable debug logging (true/false) | false |
| EMBEDDING_PROVIDER | No | Embedding backend (openai, cohere, sentence-transformer, voyage, dummy). Default depends on configuration. | |
| OPENROUTER_API_KEY | Yes | Required API key for LLM generation via OpenRouter | |
| SESSION_TTL_SECONDS | No | Session timeout in seconds | 3600 |
| GENETIC_MCP_LOG_FILE | No | Optional log file path for persistent logging | |
| GENETIC_MCP_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) | INFO |
| GENETIC_MCP_MEMORY_DB | No | Path to memory database | genetic_mcp_memory.db |
| GENETIC_MCP_TRANSPORT | No | Transport mode (stdio for MCP, http for web) | stdio |
| GENETIC_MCP_MEMORY_ENABLED | No | Enable memory & learning system (true/false) | true |
| GENETIC_MCP_OPTIMIZATION_LEVEL | No | Optimization level (basic, enhanced, gpu, full) | enhanced |
| GENETIC_MCP_OPTIMIZATION_ENABLED | No | Enable advanced optimization features (true/false) | true |
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
| 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 | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues