KosmoKrator

ai

Firecrawl MCP Integration for Claude Agent SDK

Connect Firecrawl to Claude Agent SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

6 functions 6 read 0 write API key auth
Submit Firecrawl feedback View package source

Connect Firecrawl to Claude Agent SDK

Give Claude Agent SDK workflows access to KosmoKrator integrations through a local MCP server.

Add a KosmoKrator stdio MCP server to the Claude Agent SDK options. The gateway is local, scoped to this integration, and starts with --write=deny so Claude Agent SDK can inspect read-capable tools without receiving write access by default.

Firecrawl MCP Config for Claude Agent SDK

Use a narrow integration list so the agent does not load unrelated tools.

{
  "mcpServers": {
    "kosmokrator-firecrawl": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=firecrawl",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=firecrawl --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Firecrawl instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Firecrawl Tools Visible to Claude Agent SDK

Claude Agent SDK sees stable MCP tool names generated from the Firecrawl integration catalog.

MCP toolSource functionTypeDescription
integration__firecrawl__firecrawl_scrape firecrawl.firecrawl_scrape Read Scrape a single URL and extract its content. Returns the page content in the requested format (markdown by default). Supports actions like waiting for JavaScript, taking screenshots, and extracting specific elements.
integration__firecrawl__firecrawl_crawl firecrawl.firecrawl_crawl Read Start a crawl job to scrape all pages from a website starting at the given URL. Returns a crawl job ID — use firecrawl_get_crawl_status to check progress and retrieve results.
integration__firecrawl__firecrawl_get_crawl_status firecrawl.firecrawl_get_crawl_status Read Check the status and retrieve results of a crawl job. Returns the current status (scraping, completed, failed, cancelled) and all scraped data once complete.
integration__firecrawl__firecrawl_map firecrawl.firecrawl_map Read Map a website to discover all linked URLs. Returns a list of all URLs found on the site without scraping full content. Useful for understanding site structure before crawling.
integration__firecrawl__firecrawl_extract firecrawl.firecrawl_extract Read Extract structured data from one or more URLs using AI. Provide a prompt describing what to extract, or a JSON schema for the expected output format. Ideal for pulling specific data points from web pages.
integration__firecrawl__firecrawl_get_current_user firecrawl.firecrawl_get_current_user Read Get the authenticated user's account information, including plan details and usage statistics. Useful for verifying API key validity and checking remaining credits.

Related Firecrawl Pages

Firecrawl CLIUse direct JSON commands instead of MCP discovery. Firecrawl MCPFull gateway reference and MCP tool names. KosmoKrator for Claude Agent SDKClient-level gateway setup.