Install Firecrawl Local

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

npm install
npm run build

claude mcp add firecrawl-local -- node /absolute/path/to/firecrawl-local-mcp/dist/index.js

Replace any placeholder paths in the command with the real path on your machine.

Environment Variables

Set these before running Firecrawl Local.

VariableDescriptionRequired

FIRECRAWL_URLThe URL of your self-hosted Firecrawl instanceNo

Once configured, Firecrawl Local gives your AI agent access to:

firecrawl_scrapeScrape a single webpage and return its content in markdown format.

urlformatsonlyMainContentincludeTagsexcludeTags

firecrawl_crawlCrawl a website starting from a URL and return content from multiple pages.

urlincludesexcludesmaxDepthlimitallowBackwardLinksallowExternalLinks

firecrawl_crawl_statusCheck the status of a crawl job.

jobId

firecrawl_mapMap a website to get a list of all accessible URLs.

urlsearchignoreSitemapincludeSubdomainslimit

After setup, try these prompts with your AI agent:

→Scrape the content from https://example.com and summarize it for me.

→Crawl the documentation site at https://docs.example.com with a depth of 3.

→Map all the URLs on https://example.com to see the site structure.

→Check the status of my recent crawl job with ID abc123.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Node.js 18+ with npm/npx installed

Save the docs, env vars, and workflow around Firecrawl Local in Conare so Claude Code, Codex, and Cursor remember it next time.