CodepitWeb, docs and paper search for Claude
Connects Claude to Firecrawl's hosted search server, so it can search the web, read pages, and look up developer docs, US government publications and scientific papers, with sources cited.
Scan in CodepitScan checks all of firecrawl/firecrawl-claude-plugin on your computer, before anything installs.
Codepit runs on your computer. Open this page there to scan it before installing.
FirecrawlMade by firecrawl
253Stars on GitHubStars
MITLicense
25 OctLast update
What Claude gets
firecrawl_searchSearch the web and get ranked results with excerpts. Billed per requestfirecrawl_scrapeRead a page at a known URL. Billed per URLfirecrawl_developer_searchFind passages in indexed repositories and documentation. Billed per requestfirecrawl_gov_searchSearch US statutes, regulations, court opinions and other government publications. Freefirecrawl_research_search_papersFind scientific papers; related tools read passages and follow citations. Billed per requestfirecrawl_find_toolsFind structured data providers for a question. Free
What you get
Short commands in Claude Code. Plain requests work too; the skills pick the tool.
- /firecrawl:setup
- /firecrawl:search
- /firecrawl:scrape
- /firecrawl:map
- /firecrawl:crawl
- /firecrawl:agent
Before you start
A Firecrawl account. After installing, run /mcp, pick firecrawl and finish the sign-in in your browser. No API key or CLI needed.
Worth knowing
Your search queries, page URLs and any inputs for data providers are sent to Firecrawl. Firecrawl suggests including only what the task needs.
Searches and page reads are billed to your Firecrawl account: web, developer and paper searches per request, page reads per URL. Government search and provider discovery are free.
Comes with 13 skills
Three core search and research skills, plus workflows for specific jobs.
- firecrawl
- firecrawl-deep-research
- firecrawl-developer-index
- firecrawl-research-index
- read-docs
- seo-audit
- and 7 more
