Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Ollama host URL (required when using Ollama provider) | http://127.0.0.1:11434 |
| MILVUS_TOKEN | No | Your Zilliz Cloud API key or Milvus token for vector database access | |
| GEMINI_API_KEY | No | Your Gemini API key (required when using Gemini provider) | |
| MILVUS_ADDRESS | No | Your Zilliz Cloud public endpoint or Milvus address | |
| OPENAI_API_KEY | No | Your OpenAI API key (required when using OpenAI provider) | |
| EMBEDDING_MODEL | No | The embedding model to use. Default varies by provider (e.g., text-embedding-3-small for OpenAI, voyage-code-3 for VoyageAI, gemini-embedding-001 for Gemini, nomic-embed-text for Ollama) | |
| GEMINI_BASE_URL | No | Custom API base URL for Gemini (for custom endpoints) | https://generativelanguage.googleapis.com/v1beta |
| OPENAI_BASE_URL | No | Custom API base URL for OpenAI (for Azure OpenAI or other compatible services) | https://api.openai.com/v1 |
| VOYAGEAI_API_KEY | No | Your VoyageAI API key (required when using VoyageAI provider) | |
| CUSTOM_EXTENSIONS | No | Additional file extensions to include beyond defaults (e.g., .vue,.svelte,.astro,.twig) | |
| EMBEDDING_PROVIDER | No | The embedding provider to use. Supported providers: OpenAI, VoyageAI, Gemini, Ollama | OpenAI |
| EMBEDDING_BATCH_SIZE | No | The embedding batch size to optimize the performance of the MCP server, depending on your embedding model throughput | 100 |
| CUSTOM_IGNORE_PATTERNS | No | Additional ignore patterns to exclude files/directories (e.g., temp/**,*.backup,private/**,uploads/**) |
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 | |