zvec-mcp
by cluster2600
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | Required when using OpenAI backend. | |
| ZVEC_MCP_DATA_DIR | No | Root directory for vector database collections. | ~/.zvec-mcp |
| ZVEC_MCP_HTTP_DIM | No | Embedding dimension for HTTP backend (must match your model). | 768 |
| ZVEC_MCP_HTTP_URL | No | OpenAI-compatible embedding endpoint for HTTP backend. | http://127.0.0.1:1234/v1/embeddings |
| ZVEC_MCP_EMBEDDING | No | Embedding backend: local, openai, or http. | local |
| ZVEC_MCP_CHUNK_SIZE | No | Characters per chunk for knowledge ingestion. | 512 |
| ZVEC_MCP_HTTP_MODEL | No | Model name sent to the HTTP endpoint. | text-embedding-nomic-embed-text-v1.5@f16 |
| ZVEC_MCP_OPENAI_DIM | No | Embedding dimension for OpenAI backend. | 1536 |
| ZVEC_MCP_HTTP_API_KEY | No | Bearer token for HTTP backend (optional). | |
| ZVEC_MCP_OPENAI_MODEL | No | OpenAI model name. | text-embedding-3-small |
| ZVEC_MCP_CHUNK_OVERLAP | No | Overlap between consecutive chunks. | 64 |
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/cluster2600/zvec-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server