Tea Rags MCP
by artk0de
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug timing logs ('true' or '1'). | false |
| HTTP_PORT | No | Port for HTTP transport. | 3000 |
| QDRANT_URL | No | Qdrant server URL. | http://localhost:6333 |
| COHERE_API_KEY | No | API key for Cohere. | |
| OPENAI_API_KEY | No | API key for OpenAI. | |
| QDRANT_API_KEY | No | API key for Qdrant authentication. | |
| TRANSPORT_MODE | No | Transport mode: 'stdio' or 'http'. | stdio |
| VOYAGE_API_KEY | No | API key for Voyage AI. | |
| CODE_BATCH_SIZE | No | Number of chunks to embed in one batch. | 100 |
| CODE_CHUNK_SIZE | No | Maximum chunk size in characters for code indexing. | 2500 |
| CODE_ENABLE_AST | No | Enable AST-aware chunking using tree-sitter. | true |
| EMBEDDING_MODEL | No | The model name for embeddings. Provider-specific defaults apply if omitted. | |
| DELETE_BATCH_SIZE | No | Paths per delete batch. | 500 |
| CODE_CHUNK_OVERLAP | No | Overlap between chunks in characters. | 300 |
| CODE_CUSTOM_IGNORE | No | Additional ignore patterns (comma-separated). | |
| CODE_DEFAULT_LIMIT | No | Default search result limit for code search. | 5 |
| DELETE_CONCURRENCY | No | Parallel delete requests. | 8 |
| EMBEDDING_BASE_URL | No | Custom API URL for the embedding provider. | |
| EMBEDDING_PROVIDER | No | The embedding provider to use: 'ollama', 'openai', 'cohere', or 'voyage'. | ollama |
| MAX_IO_CONCURRENCY | No | Maximum parallel file I/O operations during cache sync. | 50 |
| EMBEDDING_DIMENSION | No | Vector dimensions (auto-detected from model if possible). | |
| PROMPTS_CONFIG_FILE | No | Path to prompts configuration JSON. | prompts.json |
| EMBEDDING_BATCH_SIZE | No | Number of texts per embedding request. | 64 |
| EMBEDDING_CONCURRENCY | No | Parallel embedding requests (useful for multiple GPUs). | 1 |
| EMBEDDING_RETRY_DELAY | No | Initial retry delay in milliseconds. | 1000 |
| QDRANT_BATCH_ORDERING | No | Ordering mode: 'weak', 'medium', or 'strong'. | weak |
| CODE_CUSTOM_EXTENSIONS | No | Additional file extensions (comma-separated) for indexing. | |
| HTTP_REQUEST_TIMEOUT_MS | No | Request timeout for HTTP transport in milliseconds. | 300000 |
| CODE_ENABLE_GIT_METADATA | No | Enrich chunks with git blame information (author, dates, tasks). | false |
| EMBEDDING_RETRY_ATTEMPTS | No | Number of retry attempts for embedding requests. | 3 |
| QDRANT_FLUSH_INTERVAL_MS | No | Auto-flush buffer interval for Qdrant (0 to disable). | 500 |
| EMBEDDING_MAX_REQUESTS_PER_MINUTE | No | Rate limit for embedding requests. |
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
ActivityActive
ResponsivenessNo issues