Browser Automation
Firecrawl MCP
Firecrawl combines scraping with LLM-ready data extraction. Cleans HTML into structured markdown, removing ads and navigation noise.
0% Pass ❌Key Required 🔑Tested 📅
0% (0/0 tasks)View on GitHubby Mendable
Benchmark results
Pass Rate0% (0/0 tasks)
0%(5 tasks)
SpeedN/A
Tested OnJun 8, 2026Could not discover tools
| Metric | Value |
|---|---|
| Tools discovered | Could not discover tools |
| Scope | Local only |
| Pricing | Freemium |
| Auth requirement | Requires FIRECRAWL_API_KEY |
| Verdict | Requires FIRECRAWL_API_KEY. Not independently tested |
Install config
Claude Desktop (macOS)
{"mcpServers": {"firecrawl": {"command": "npx", "args": ["-y", "firecrawl-mcp@latest"]}}}Cursor
{"mcpServers": {"firecrawl": {"command": "npx", "args": ["-y", "firecrawl-mcp@latest"]}}}VS Code
// .vscode/mcp.json
{
"servers": {
"firecrawl": {
"command": "npx",
"args": ["-y", "firecrawl-mcp@latest"]
}
}
}Pros
- +Package installs successfully
Cons
- −Requires configuration/credentials
- −Could not evaluate without setup
Best for
Knowledge base ingestion, RAG pipelines, content migration
Related servers in Browser Automation
Frequently asked questions
How do I install Firecrawl MCP?▼
Copy the config above into your AI assistant's MCP settings file:
- Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json - Cursor: Settings → MCP → Add Server
- VS Code:
.vscode/mcp.json
Does it require an API key?▼
Yes. You need to set the FIRECRAWL_API_KEY environment variable. We could not test this server without credentials, so our evaluation is based on documentation and community reports.
How were these results measured?▼
We run each server through a standardized test harness that:
- Installs the server via
npxin a fresh environment - Discovers available tools using the MCP SDK
- Executes real tasks (navigate, click, screenshot, etc.)
- Validates outputs with semantic assertions (not string matching)
- Measures latency percentiles and pass rate
All test scripts are open source on GitHub.