What it does

Scrapes, crawls, and maps sites, returning clean Markdown with JavaScript already executed. Handles the pages a plain fetch cannot: infinite scroll, client-rendered SPAs, PDFs. Paid API behind it, with a free allowance to evaluate.

Install

Terminal

npx -y firecrawl-mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ]
    }
  }
}

When to use it

Reach for this when the task needs scraping inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude