Skip to content
Model Context Protocol

Use Quality Screener from your AI assistant.

The open-source MCP server lets Claude, ChatGPT, Cursor, and other MCP clients screen companies, apply your quality criteria, and read the same data you see in the web app — acting as you, with your account.

Endpoint

The hosted server address.

Point any streamable-HTTP MCP client at this URL. You need a Quality Screener account. On first connect the client opens a browser window so you can sign in; after that, the assistant inherits exactly your access. No API token is required when the client supports OAuth.

MCP endpoint
https://mcp.qualityscreener.io/mcp
What it can do

The same tools as the dashboard.

Screen and filter

Run the scored universe with the same quality measures and filters you use in the dashboard.

Custom quality scores

Build or apply a transparent scoring system and inspect how each company earned its score.

History and saved work

Look at score history, manage saved scoring systems, and generate shareable screen links.

Connect a client

Add it to Claude, ChatGPT, or Cursor.

Cursor

  1. Open Cursor Settings and go to MCP.
  2. Add a new MCP server and paste the configuration below into .cursor/mcp.json (or your global MCP config).
  3. Save. On first use, Cursor opens the Quality Screener sign-in page. Approve once and the assistant stays connected.
.cursor/mcp.json
{
  "mcpServers": {
    "qscreener": {
      "url": "https://mcp.qualityscreener.io/mcp"
    }
  }
}

Claude

  1. In Claude (claude.ai or Claude Desktop), open Settings → Connectors.
  2. Add a custom connector and set the server URL to the endpoint below.
  3. Complete the Quality Screener sign-in when prompted. Claude will then be able to call the same tools as your dashboard.
Connector URL or MCP config
{
  "mcpServers": {
    "qscreener": {
      "type": "streamable-http",
      "url": "https://mcp.qualityscreener.io/mcp"
    }
  }
}

ChatGPT

  1. In ChatGPT, enable Developer mode (or use a plan that supports custom MCP connectors).
  2. Open Settings → Connectors (sometimes listed as Apps & connectors) and add a new MCP server.
  3. Use the endpoint URL below. ChatGPT will ask you to sign in to Quality Screener on first connect.
MCP server URL
https://mcp.qualityscreener.io/mcp

Full tool reference, local stdio setup, and configuration options are in the MCP server README. For questions, email info@qualityscreener.io.