Vectorize MCP Server

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

Local serverstdio

What is the Vectorize MCP server?

Vectorize becomes available to MCP clients through the vectorize mcp server. Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.

What Vectorize does

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

Tools it exposes

Once connected, the assistant can call these 2 tools directly:

  • Release — Change the package.json version and then: bash 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

Installing the vectorize mcp server

The server is distributed via npm as @vectorize-io/vectorize-mcp-server, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 6 environment variables: VECTORIZE_ORG_ID, VECTORIZE_TOKEN, VECTORIZE_PIPELINE_ID, YOUR_ORG_ID, YOUR_TOKEN, YOUR_PIPELINE_ID. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Vectorize sits in that group, and the shape of its toolset — Release, Contributing — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the vectorize mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
ReleaseChange the package.json version and then: bash git commit -am "x.y.z" git tag x.y.z git push origin git push origin --tags
Contributing1. Fork the repository 2. Create your feature branch 3. Submit a pull request

How to install the Vectorize MCP server

{
  "mcpServers": {
    "vectorize": {
      "command": "npx",
      "args": ["-y", "@vectorize-io/vectorize-mcp-server"],
      "env": {
        "VECTORIZE_ORG_ID": "your-value",
        "VECTORIZE_TOKEN": "your-value",
        "VECTORIZE_PIPELINE_ID": "your-value",
        "YOUR_ORG_ID": "your-value",
        "YOUR_TOKEN": "your-value",
        "YOUR_PIPELINE_ID": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
VECTORIZE_ORG_IDConfiguration value read at startup.Optional
VECTORIZE_TOKENCredential the server authenticates with.Yes
VECTORIZE_PIPELINE_IDConfiguration value read at startup.Optional
YOUR_ORG_IDConfiguration value read at startup.Optional
YOUR_TOKENCredential the server authenticates with.Yes
YOUR_PIPELINE_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use Vectorize to Release.
  • Use Vectorize to Contributing.

Frequently asked questions

It connects Vectorize to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Release, Contributing) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Vectorize directly.