Vectorize

Vectorize MCP Server

A Model Context Protocol (MCP) server implementation that integrates with Vectorize for advanced Vector retrieval and text extraction.

Installation

Running with npx

1export VECTORIZE_ORG_ID=YOUR_ORG_ID
2export VECTORIZE_TOKEN=YOUR_TOKEN
3export VECTORIZE_PIPELINE_ID=YOUR_PIPELINE_ID
4
5npx -y @vectorize-io/vectorize-mcp-server@latest

Configuration on Claude/Windsurf/Cursor/Cline

1{
2  "mcpServers": {
3    "vectorize": {
4      "command": "npx",
5      "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
6      "env": {
7        "VECTORIZE_ORG_ID": "your-org-id",
8        "VECTORIZE_TOKEN": "your-token",
9        "VECTORIZE_PIPELINE_ID": "your-pipeline-id"
10      }
11    }
12  }
13}

Tools

Retrieve documents

Perform vector search and retrieve documents (see official API):

1{
2  "name": "retrieve",
3  "arguments": {
4    "question": "Financial health of the company",
5    "k": 5
6  }
7}

Text extraction and chunking (Any file to Markdown)

Extract text from a document and chunk it into Markdown format (see official API):

1{
2  "name": "extract",
3  "arguments": {
4    "base64document": "base64-encoded-document",
5    "contentType": "application/pdf"
6  }
7}

Deep Research

Generate a Private Deep Research from your pipeline (see official API):

1{
2  "name": "deep-research",
3  "arguments": {
4    "query": "Generate a financial status report about the company",
5    "webSearch": true
6  }
7}

Development

1npm install
2npm run dev

Contributing

Fork the repository
Create your feature branch
Submit a pull request

Contents