An MCP server that integrates with Vectorize.io for advanced vector search, text extraction from any file formats into Markdown, and private deep research capabilities.

Installation

NPX

export VECTORIZE_ORG_ID=YOUR_ORG_ID
export VECTORIZE_TOKEN=YOUR_TOKEN
export VECTORIZE_PIPELINE_ID=YOUR_PIPELINE_ID

npx -y @vectorize-io/vectorize-mcp-server@latest

From Source

npm install
npm run dev

Configuration

Manual VS Code Configuration

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "org_id",
        "description": "Vectorize Organization ID"
      },
      {
        "type": "promptString",
        "id": "token",
        "description": "Vectorize Token",
        "password": true
      },
      {
        "type": "promptString",
        "id": "pipeline_id",
        "description": "Vectorize Pipeline ID"
      }
    ],
    "servers": {
      "vectorize": {
        "command": "npx",
        "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
        "env": {
          "VECTORIZE_ORG_ID": "${input:org_id}",
          "VECTORIZE_TOKEN": "${input:token}",
          "VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"
        }
      }
    }
  }
}

Claude/Windsurf/Cursor/Cline

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

VS Code Workspace Configuration

{
  "inputs": [
    {
      "type": "promptString",
      "id": "org_id",
      "description": "Vectorize Organization ID"
    },
    {
      "type": "promptString",
      "id": "token",
      "description": "Vectorize Token",
      "password": true
    },
    {
      "type": "promptString",
      "id": "pipeline_id",
      "description": "Vectorize Pipeline ID"
    }
  ],
  "servers": {
    "vectorize": {
      "command": "npx",
      "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
      "env": {
        "VECTORIZE_ORG_ID": "${input:org_id}",
        "VECTORIZE_TOKEN": "${input:token}",
        "VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"
      }
    }
  }
}

Available Tools

Tool	Description
retrieve	Performs vector search and retrieves documents from the pipeline
extract	Extracts text from any document format and chunks it into Markdown format
deep-research	Generates a private deep research report from your pipeline with optional web search

Features

• Advanced vector search and document retrieval
• Text extraction and chunking from any file format into Markdown
• Private deep research generation
• Integration with Vectorize.io pipelines
• Web search integration for deep research
• One-click installation for VS Code

Environment Variables

Required

• VECTORIZE_ORG_ID - Your Vectorize organization ID
• VECTORIZE_TOKEN - Your Vectorize authentication token
• VECTORIZE_PIPELINE_ID - Your Vectorize pipeline ID

Usage Examples

Financial health of the company

Generate a financial status report about the company

Extract text from a PDF document

Retrieve 5 most relevant documents about a topic

Notes

The server provides one-click installation for VS Code and VS Code Insiders. It supports configuration at both the user and workspace levels. For development, you can clone the repository and use npm commands. The release process includes updating the version in package.json and creating git tags.