Vectorize MCP Server

Vector DatabasesTypeScript

Vector search and document retrieval for AI applications

Available Tools

retrieve

Perform vector search and retrieve documents from your Vectorize pipeline

questionk

extract

Extract text from a document and convert it to Markdown format

base64documentcontentType

deep-research

Generate a comprehensive research report from your pipeline data

querywebSearch

Vectorize MCP Server provides seamless integration with Vectorize's vector database and document processing capabilities. It enables advanced vector search, document retrieval, text extraction, and deep research functionality directly within your AI applications. With this MCP, you can enhance your AI assistants with powerful knowledge retrieval from your own data sources.

Overview

Vectorize MCP Server connects your AI applications to Vectorize's powerful vector database and document processing platform. This integration allows your AI assistants to search through your documents, extract meaningful information, and generate comprehensive research reports based on your data.

Prerequisites

Before using the Vectorize MCP Server, you'll need:

A Vectorize account with an Organization ID
A Vectorize API token
A configured Pipeline ID in your Vectorize account

You can sign up and get these credentials at vectorize.io.

Installation Options

Option 1: Running with npx

The simplest way to run Vectorize MCP Server is using 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

Option 2: VS Code Integration

For VS Code users, you can add the following configuration to your User Settings (JSON) file:

{
  "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}"
        }
      }
    }
  }
}

Option 3: Workspace Configuration

To share the configuration with your team, create a .vscode/mcp.json file in your workspace with the same configuration as above.

Client Configuration

To use Vectorize MCP Server with AI clients like Claude, Windsurf, Cursor, or Cline, add the following configuration:

{
  "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"
      }
    }
  }
}

Usage Examples

Once configured, your AI assistant can use Vectorize's capabilities through the provided tools. Here are some examples of how to use each tool:

Document Retrieval

Ask your AI assistant to search for specific information in your documents: "Find information about our company's financial health in Q2 2023."

Text Extraction

Ask your AI assistant to extract and summarize content from a document: "Extract the key points from this financial report." (with an attached document)

Deep Research

Ask your AI assistant to perform comprehensive research on a topic: "Generate a detailed report on our company's market position compared to competitors."