MCP Service Integration — Vectorize
By leveraging the Vectorize capability of the MCP protocol, retrieval or deep research can be performed based on the RAG pipeline configured on Vectorize.
Vectorize helps you build AI applications faster and more easily. It automatically extracts data, uses RAG evaluation to find the optimal vectorization strategies, and enables you to quickly deploy real-time RAG pipelines for unstructured data. Your vector search indexes are always kept up-to-date, and it integrates with your existing vector databases, giving you full control over your data. Vectorize handles the heavy lifting, allowing you to focus on building powerful AI solutions without getting bogged down in data management.
Vectorize RAG Pipeline Diagram
Environment Variables
- You need to set VECTORIZE_ORG_ID to your Organization ID on the Vectorize platform
- You need to set VECTORIZE_PIPELINE_ID to the RAG pipeline ID you created on the Vectorize platform
- You need to set VECTORIZE_TOKEN to your Token on the Vectorize platform
Usage Instructions
Vectorize MCP Server Reference Documentation
🗺️ Feature List
Tool Identifier | Function Description | Core Parameters |
---|---|---|
retrieve | Perform vector retrieval and return the document content most relevant to the query. | question (query text), k (number of documents to return) |
extract | Extract text content from files and convert it to Markdown format. | base64document (Base64-encoded file content), contentType (file type) |
deep-research | Generate private in-depth research content with support for web search. | query (query text), webSearch (whether to enable web search) |
Repository URL
https://github.com/vectorize-io/vectorize-mcp-server