Skip to main content
Add Firecrawl to AI Assistant in IntelliJ IDEA, PyCharm, WebStorm, and the other JetBrains IDEs. AI Assistant starts the Firecrawl MCP server as a local process, using your API key.

​
Requirements

  • A JetBrains IDE with AI Assistant 2025.1 or newer. MCP client support arrived in that release.
  • Node.js 22 or newer on your PATH, because the server runs through npx.
  • A Firecrawl API key.

​
Quick setup

  1. Open Settings, then Tools, then AI Assistant, then Model Context Protocol (MCP).
  2. Select Add.
  3. Paste this JSON, replace the key, and set Server level to global or the current project:
  1. Select OK, then Apply. The Status column shows the connection, and its tool icon lists the Firecrawl tools.
  2. Enable Automatically enable new and changed MCP servers if you want the server to start on its own.
The current AI Assistant documentation also lists Streamable HTTP servers, configured with a url entry in the same JSON. It does not document request headers or a browser sign-in flow, so use the local setup above for Firecrawl unless your IDE shows those options.
See Run MCP locally for the full list of environment variables.

​
Try it

​
What you can do

Search

Find current information and read the content of relevant results.

Scrape

Turn URLs into clean markdown or structured data.

Interact

Navigate, click, and fill forms to reach the data you need.

Alexandria

Discover structured data tools, inspect inputs and pricing, then run them through Firecrawl.

​
Troubleshooting

  • The status stays red: run node --version in a terminal and confirm it prints 22 or newer. Restart the IDE after installing Node.js so it sees the new PATH.
  • spawn npx ENOENT: the IDE cannot find npx. Start the IDE from a shell where npx works, or use the full path to npx as the command.
  • The server shows 401: replace the value of FIRECRAWL_API_KEY and select Apply again.
  • Logs: the MCP settings page links to the log folder, which holds one log per server.