📌Overview

Purpose: To provide an efficient Model Context Protocol (MCP) server that integrates with Vectorize for advanced vector retrieval and text extraction capabilities.

Overview: The Vectorize MCP Server is designed to enhance data management by facilitating sophisticated document retrieval and text extraction processes. By using Vectorize's infrastructure, the server enables users to perform efficient searches and conversions, supporting a variety of document formats seamlessly.

Key Features:

Vector Retrieval: Enables users to perform vector searches and retrieve relevant documents efficiently, enhancing data accessibility and informed decision-making.
Text Extraction and Chunking: Facilitates the extraction of text from various file types and converts it into Markdown format, making it easier to manage and utilize content.
Deep Research Capability: Allows users to generate comprehensive research reports from their pipelines, incorporating web search functionality for enriched results.

Vectorize MCP Server

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

Features

Advanced vector retrieval
Text extraction and chunking
Deep research capabilities

Installation

Running with npx

export VECTORIZE_ORG_ID=YOUR_ORG_ID
export VECTORIZE_TOKEN=YOUR_TOKEN
npx -y @vectorize-io/vectorize-mcp-server

Configuration on Claude/Windsurf

{
  "mcpServers": {
    "vectorize": {
      "command": "npx",
      "args": ["-y", "@vectorize-io/vectorize-mcp-server"],
      "env": {
        "VECTORIZE_ORG_ID": "your-org-id",
        "VECTORIZE_TOKEN": "your-token"
      }
    }
  }
}

Tools

Retrieve Documents

Perform vector search and retrieve documents. See official API:

{
  "name": "retrieve",
  "arguments": {
    "pipeline": "your-pipeline-id",
    "question": "Financial health of the company",
    "k": 5
  }
}

Text Extraction and Chunking

Extract text from a document and chunk it into Markdown format. See official API:

{
  "name": "extract",
  "arguments": {
    "base64document": "base64-encoded-document",
    "contentType": "application/pdf"
  }
}

Deep Research

Generate a Private Deep Research from your pipeline. See official API:

{
  "name": "deep-research",
  "arguments": {
    "pipelineId": "your-pipeline-id",
    "query": "Generate a financial status report about the company",
    "webSearch": true
  }
}

Development

# Install dependencies
npm install

# Build
npm run build

Contributing

Fork the repository
Create your feature branch
Submit a pull request