turbovec-mcp
by potatofacee
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TURBOVEC_BIT_WIDTH | No | turbovec quantization bits (2 or 4) | 4 |
| TURBOVEC_DOC_PREFIX | No | prefix for documents (nomic: `search_document: `) | |
| TURBOVEC_CHUNK_LINES | No | lines per chunk | 60 |
| TURBOVEC_EMBED_MODEL | No | model name sent in the request | nomic-embed-text-v1.5.Q8_0.gguf |
| TURBOVEC_MAX_FILE_MB | No | skip files larger than this | 2 |
| TURBOVEC_QUERY_PREFIX | No | prefix for queries (nomic: `search_query: `) | |
| TURBOVEC_CHUNK_OVERLAP | No | overlap between chunks | 12 |
| TURBOVEC_EMBED_API_KEY | No | bearer token (unused locally, must be non-empty) | sk-local |
| TURBOVEC_EMBED_ENDPOINT | No | OpenAI-compatible base URL | http://127.0.0.1:8081/v1 |
| TURBOVEC_EXTRA_SKIP_DIRS | No | comma list of extra dirs to skip | |
| TURBOVEC_EXTRA_EXTENSIONS | No | comma list of extra extensions to index |
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 | |
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/potatofacee/turbovec-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server