Vectorize MCP Server

Vectorize MCP Server

What is Vectorize MCP Server about?

Vectorize MCP Server implements a Model Context Protocol (MCP) server that enables advanced vector retrieval, text extraction, and private deep‑research workflows by delegating calls to the Vectorize platform.

How to use Vectorize MCP Server?

1. Set the required environment variables:

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

2. Start the server with a single npx command:

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

3. Configure your AI client (Claude, Windsurf, Cursor, Cline, etc.) to point to the running MCP server using the JSON snippet provided in the README.

Key features of Vectorize MCP Server

• Vector Retrieval – Search a Vectorize index and return the top k relevant documents.
• Document Extraction & Chunking – Convert any file (e.g., PDF) to Markdown chunks via base‑64 upload.
• Private Deep Research – Generate a pipeline‑driven deep‑research report, optionally enriched with web search.
• One‑click VS Code installation – Pre‑filled mcp.json configuration for rapid setup.
• Simple npm‑based deployment – No build steps required; run directly with npx.

Use cases of Vectorize MCP Server

• Building RAG (retrieval‑augmented generation) assistants that need fast vector look‑ups.
• Automating document ingestion pipelines that require text extraction and chunking.
• Creating internal research bots that produce private, citation‑rich reports.
• Integrating Vectorize capabilities into IDE‑based AI assistants (e.g., VS Code Copilot extensions).

FAQ from the Vectorize MCP Server

Q: Do I need to install anything locally? A: Only Node.js (for npx). The server runs directly from the npm package.

Q: Which environment variables are mandatory? A: VECTORIZE_ORG_ID, VECTORIZE_TOKEN, and VECTORIZE_PIPELINE_ID.

Q: Can I customize the server name? A: Yes, the mcpServers key can be renamed; the example uses vectorize.

Q: How do I update the server after a new release? A: Re‑run the npx command; it will fetch the latest version automatically.

Q: Is there a way to run the server in development mode? A: Clone the repo, run npm install then npm run dev for hot‑reloading.

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

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:

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

Contributing

1. Fork the repository
2. Create your feature branch
3. Submit a pull request