# Vectorize MCP server

> Lets an AI client run vector retrieval, extract and chunk documents into Markdown, and generate deep research reports from a Vectorize pipeline.

- Repository: https://github.com/vectorize-io/vectorize-mcp-server
- Page: https://hostedmcp.org/servers/vectorize-io/vectorize-mcp-server
- Transport: —
- Stars: 116
- License: MIT

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `VECTORIZE_ORG_ID` | no | no |  |
| `VECTORIZE_PIPELINE_ID` | no | no |  |
| `VECTORIZE_TOKEN` | no | no |  |

## FAQ

### How do I configure the Vectorize MCP server?

Set the VECTORIZE_ORG_ID, VECTORIZE_TOKEN and VECTORIZE_PIPELINE_ID environment variables and run the package with npx. The same env block can be added to a claude/windsurf/cursor/cline mcpServers config.

### Can the Vectorize MCP server search my pipeline and return documents?

Yes, the retrieve tool performs vector search and retrieves documents for a question, with a k parameter for the number of results.

### Can it convert documents to Markdown?

Yes, the extract tool extracts text from a document and chunks it into Markdown format, taking a base64 document and its content type.

### Does Vectorize support deep research queries?

Yes, the deep-research tool generates a private deep research report from your pipeline, optionally with web search enabled.

### What authentication does the server need?

It needs a Vectorize token along with your organization ID and pipeline ID, passed as environment variables.
