MCP Connector

Integrate Vectorize for Advanced Research and Data Extraction

An MCP server for Vectorize offering vector search, document extraction, and deep-research generation.

Works with vectorize.io

90
Spark score
out of 100
Updated last month
Version 0.4.3
Models
universal

Add to Favorites

Why it matters

Leverage Vectorize.io's advanced capabilities for sophisticated vector search, extracting text from any file format into Markdown, and conducting private deep research with optional web search integration.

Outcomes

What it gets done

01

Perform vector search and retrieve relevant documents.

02

Extract text from various file formats and convert to Markdown.

03

Generate private deep research reports, optionally including web search results.

04

Integrate seamlessly with Vectorize.io pipelines for enhanced data analysis.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-vectorize | bash

Capabilities

Tools your agent gets

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

Overview

Vectorize MCP Server

An MCP server for Vectorize offering vector search, document-to-Markdown extraction, and deep-research report generation. Use it when an MCP client needs to search, extract, or research against your own Vectorize pipeline.

What it does

An MCP server that integrates with Vectorize for vector retrieval, document text extraction, and deep research: it lets an MCP client perform vector search against a Vectorize pipeline, extract and chunk any document into Markdown, and generate a private deep-research report from that pipeline's data.

When to use - and when NOT to

Use this when an MCP client needs to search a Vectorize knowledge pipeline for relevant documents, convert an uploaded file (e.g. a PDF) into chunked Markdown text, or generate a synthesized research report grounded in your own pipeline data - for example "Generate a financial status report about the company" with web search enabled. It requires an existing Vectorize organization, an access token, and a configured pipeline - it is not itself a standalone vector database, but rather a connector to Vectorize's already-hosted pipelines and their indexed content.

Capabilities

  • retrieve: vector search against a pipeline, e.g. {"question": "Financial health of the company", "k": 5} to get the top 5 most relevant matching documents from the pipeline.
  • extract: text extraction and chunking of any document into Markdown, given a base64document and its contentType (e.g. application/pdf), useful for turning uploaded files into pipeline-ready text.
  • deep-research: generates a Private Deep Research report from the pipeline, with an optional webSearch flag to include live web search alongside the pipeline's own indexed data in the synthesis.

How to install

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

For Claude, Windsurf, Cursor, or 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 has one-click install buttons, or a manual mcp block in User Settings (JSON) or a shared .vscode/mcp.json, prompting for the organization ID, token, and pipeline ID as password-masked input fields rather than plain hardcoded values.

Who it's for

Developers who already have a Vectorize pipeline and want an MCP client (Claude, Cursor, Windsurf, Cline, or VS Code) to run vector search, extract and chunk documents, or generate deep-research reports directly against that pipeline's data. Each tool maps directly to one of Vectorize's own hosted APIs - retrieval, extraction, and deep research - so behavior and result quality match what the same request would return through Vectorize's own API documentation, just callable as an MCP tool instead of a raw HTTP request.

Source README

Vectorize MCP Server

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

Vectorize MCP server

Installation

Running with 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

VS Code Installation

For one-click installation, click one of the install buttons below:

Install with NPX in VS Code Install with NPX in VS Code Insiders

Manual Installation

For the quickest installation, use the one-click install buttons at the top of this section.

To install manually, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).

{
  "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}"
        }
      }
    }
  }
}

Optionally, you can add the following to a file called .vscode/mcp.json in your workspace to share the configuration with others:

{
  "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}"
      }
    }
  }
}

Configuration on 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"
      }
    }
  }
}

Tools

Retrieve documents

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

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

Text extraction and chunking (Any file to Markdown)

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": {
    "query": "Generate a financial status report about the company",
    "webSearch": true
  }
}

Development

npm install
npm run dev

Release

Change the package.json version and then:

git commit -am "x.y.z"
git tag x.y.z
git push origin
git push origin --tags

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.