How to use Firecrawl with GitHub Copilot
You want Firecrawl inside GitHub Copilot so it can research a technical question across documentation, extract structured records from a website, audit a website before an agent uses it, and investigate issues and research papers — without you copy-pasting between tabs. Here is the whole setup, once.
Create your Firecrawl gateway
The gateway is the thing GitHub Copilot connects to, and it is where you decide which Firecrawl tools an agent may use. You create it once and every client reuses it.
-
Create an Arcade account
Sign up and open the dashboard. The free tier is enough to follow this through.
-
Create an MCP Gateway and select your Firecrawl tools
In the dashboard, create a gateway and pick the Firecrawl tools you want to expose. The gateway is what your client connects to, and it is where tool access is decided.
-
Copy your gateway URL
Every client below needs it.
https://api.arcade.dev/mcp/<YOUR-GATEWAY-SLUG>
Connect the gateway to GitHub Copilot
JetBrains IDEs do not support remote MCP servers with Dynamic Client Registration — configure the gateway as “Arcade Headers” in the dashboard first. Setup also differs on Visual Studio, Eclipse and Xcode; check the docs for yours.
-
In VS Code
Copilot picks up MCP servers configured in VS Code automatically, so follow the VS Code steps and you are done.
-
In JetBrains IDEs
Copilot icon → Open Chat → Agent mode → tools icon → “+ Add More Tools…”, which opens mcp.json.
-
Add the gateway with Arcade Headers
{ "servers": { "mcp-arcade": { "url": "https://api.arcade.dev/mcp/<YOUR-GATEWAY-SLUG>", "requestInit": { "headers": { "Authorization": "Bearer {arcade_api_key}", "Arcade-User-ID": "{arcade_user_id}" } } } } }
Full GitHub Copilot guide in the docs steps verified 2026-08-13
Try these web research prompts
GitHub Copilot can now act on your Firecrawl account. Click a prompt to copy it.
Set policy on CrawlWebsite, ExtractData, and CancelCrawl, and require approval before an agent starts a broad crawl or stops one in progress. Pair it with Contextual Access policies so untrusted page content cannot trigger those actions without a policy check.