drio
Open app

Vectorize

Source

Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.

Catalog onlyCatalog onlySTDIO

Overview

Vectorize is a Model Context Protocol (MCP) server designed for advanced vector retrieval, private deep research, and converting various file formats into Markdown.

To use Vectorize, set up your environment with your organization ID and API key, then run the MCP server using npx. You can perform document retrieval, text extraction, and deep research through its API.

  • Advanced vector search capabilities for document retrieval - Text extraction and chunking into Markdown format - Private deep research generation from specified pipelines
  1. Retrieving relevant documents based on specific queries.
  2. Extracting text from various file types and converting them into Markdown.
  3. Conducting in-depth research on topics using private pipelines.

Add to your AI client

Use these steps to connect Vectorize in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "vectorize-vectorize-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-vectorize-vectorize-mcp-server"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "vectorize-vectorize-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-vectorize-vectorize-mcp-server"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "vectorize-vectorize-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-vectorize-vectorize-mcp-server"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "vectorize-vectorize-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-vectorize-vectorize-mcp-server"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "vectorize-vectorize-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-vectorize-vectorize-mcp-server"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "vectorize-vectorize-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-vectorize-vectorize-mcp-server"
      ]
    }
  }
}

FAQ

What types of documents can Vectorize process?

Vectorize can process various document types, including PDFs and other text formats.

Is there a limit to the number of documents I can retrieve?

The limit depends on the configuration of your pipeline and the parameters set during the retrieval process.

How secure is the data processed by Vectorize?

Vectorize ensures that all data processed is handled securely, especially during private deep research.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":2337,"uuid":"fb504079-5b5b-4f20-87a2-e8d24bfbdf13","name":"Vectorize","title":"Vectorize","description":"Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.","avatar_url":null,"created_at":"2025-03-11T10:22:16.234Z","updated_at":"2025-03-12T13:28:02.232Z","status":"created","author_name":"vectorize-mcp-server","author_avatar_url":null,"tags":"vectorize,mcp-server,text-extraction","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/vectorize-io/vectorize-mcp-server/","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":null,"user_uuid":"abf6620e-7715-411c-93e7-bd7087e4c63a","tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data