JetBrains IDEs + pdfmcp: setup guide

Add pdfmcp to JetBrains AI Assistant via its MCP settings.

What you need: a free pdfmcp API key — sign in with your email (no password) and copy the key shown at first login. Then replace pdfmcp_live_YOUR_KEY in the config below.

Where it goes: Settings → Tools → AI Assistant → Model Context Protocol (MCP)

{
  "mcpServers": {
    "pdfmcp": {
      "url": "https://mcp.pdfmcp.org/mcp",
      "headers": {
        "X-API-Key": "pdfmcp_live_YOUR_KEY"
      }
    }
  }
}

Steps

Get a free API key from the pdfmcp dashboard and replace pdfmcp_live_YOUR_KEY in the JSON.
Open Settings → Tools → AI Assistant → Model Context Protocol (MCP) → Add.
Choose the remote/HTTP server option and paste the JSON above (or enter the URL and X-API-Key header in the form fields).
Apply and restart the IDE's AI chat; pdfmcp tools will be listed.
Try: “Use pdfmcp to extract text from this PDF”.

Menu names vary slightly between JetBrains IDE versions (IntelliJ IDEA, PyCharm, WebStorm…). The endpoint and header are the same everywhere.

Troubleshooting

401 / unauthorized: the key header is missing or mistyped. The header name is exactly X-API-Key (Claude Code uses Authorization: Bearer … — both work).
Tools don't appear: fully restart the client after editing its config; most clients only load MCP servers at startup.
Server unreachable: check the public status page — and your network's outbound HTTPS to mcp.pdfmcp.org.

Try it with

On-devicePDF info & metadataPage count, page sizes, metadata, encryption status as JSON.On-deviceMerge PDFsCombine multiple PDF files into one, in upload order.On-devicePDF to textExtract plain text, one form-feed separated section per page.

More clients: Claude Desktop MCP setup · Claude Code MCP setup · ChatGPT MCP setup · All MCP setup guides · REST API quickstart