Vectorize MCP Server

What is Vectorize MCP Server about?

Enables MCP‑compatible services that connect to Vectorize’s retrieval and extraction APIs, allowing AI applications to search across vector databases, convert files to markdown, and generate private deep‑research reports.

How to use Vectorize MCP Server?

1. Set environment variables for your Vectorize organization, token, and pipeline:

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

2. Run the server with a single npx command (no global installation required):

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

3. Optionally add the VS Code MCP configuration shown in the README to launch the server directly from the editor.
4. Once running, LLMs can invoke the defined tools (retrieve, extract, deep‑research) via MCP.

Key Features

• Vector search – retrieve the most relevant documents using a query and k results.
• Text extraction & chunking – convert any supported file (e.g., PDF) to base64, extract its content, and output markdown chunks.
• Deep research tool – generate a private, citation‑rich research report with optional web search.
• One‑click VS Code integration – install and launch from the editor using built‑in MCP UI.
• Simple development workflow – npm install + npm run dev for local testing.
• Release automation – version bump, tag, and push via standard Git commands.

Use Cases

• Augmenting LLM agents with up‑to‑date domain knowledge stored in Vectorize.
• Building retrieval‑augmented generation (RAG) pipelines for enterprise documents.
• Converting PDFs, Word files, or other uploads into searchable markdown for downstream AI processing.
• Creating private research briefs that combine proprietary data with web results.
• Rapid prototyping of AI‑enabled search interfaces within VS Code.

FAQ

Q: Do I need to install anything globally? A: No. The server runs via npx, which fetches the latest package on demand.

Q: Which environment variables are required? A: VECTORIZE_ORG_ID, VECTORIZE_TOKEN, and VECTORIZE_PIPELINE_ID must be set before starting the server.

Q: Can I customize the server name in MCP configurations? A: Yes. The README uses vectorize as the server identifier, but any name can be used as long as the MCP client points to the correct command and args.

Q: What Node.js version is supported? A: The package follows the standard Node.js LTS releases; using the latest LTS (e.g., 20.x) is recommended.

Q: Is the source code open source? A: Yes, the repository is public under the MIT license on GitHub.

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