firecrawl/firecrawl-mcp-server
Firecrawl Mcp Server
Firecrawl MCP Server is a Model Context Protocol tool server that exposes the full suite of Firecrawl’s web scraping, crawling, and automation capabilities as tools that large language models can invoke directly. It acts as a proxy to the Firecrawl cloud platform, which manages headless browser orchestration, async job queues, and rate limiting behind the scenes.
The server distinguishes itself by packaging autonomous web agents — both a research agent that browses and collects structured data from multiple pages, and a general web agent that performs multi-step browsing and extraction tasks — as callable MCP tools. It also provides LLM-guided structured extraction, allowing users to define a schema and have a language model parse unstructured web content into precise fields. Beyond scraping, the server supports live page interaction (clicking, typing, scrolling via natural language or code), web change monitoring with webhook notifications, and recursive crawling that discovers and indexes linked pages up to a configurable depth.
The broader capability surface includes single and batch URL scraping with output in markdown, HTML, JSON, or screenshot format, parsing of non-HTML documents such as PDFs and Office files, web search that returns structured results, and site link mapping to reveal page structure. All of these are registered as MCP tools, enabling any compatible language model client to orchestrate web data collection and automation tasks through a unified interface.
Setup requires installing the server (via npm or from source) and configuring it with a Firecrawl API key; the server then registers its tools with the MCP client, making each Firecrawl action available for use in prompts and agent workflows.
Features
- MCP Servers - The server registers each Firecrawl capability as a Model Context Protocol tool, enabling language models to invoke web scraping and browsing actions directly.
- Autonomous Web Agents - Firecrawl's autonomous web agent that searches and extracts data from multiple web pages to fulfill a given request.
- Multi-Step Workflows - Firecrawl's multi-step agent workflow capability that orchestrates autonomous tasks on the web using credits per session.
- Autonomous Web Researchers - Running an AI agent that browses multiple web pages, searches, and collects data to fulfill a research request.
- Autonomous Web Research Agents - An AI-powered agent that searches, browses, and extracts structured data from multiple web pages to fulfill complex research requests.
- Web Crawling - Provides recursive website crawling that follows links to extract content from discovered pages up to a configurable depth.
- Recursive Content Crawlers - Starting from a seed URL, the system automatically discovers and visits linked pages up to a configurable depth, building a site map.
- Structured Data Extraction - Uses a language model to extract specific fields like prices or names from web pages based on a schema.
- LLM-to-Structured Data Converters - A language model parses web content according to a user-defined schema to extract precise fields from unstructured pages.
- Web Scraping - Extracts content from a single URL as markdown, HTML, JSON, or screenshot, including JavaScript-rendered pages.
- API Proxies - Requests are forwarded to Firecrawl's API endpoints, which manage actual browser instances, crawl state, and rate limiting.
- Asynchronous Extraction Job Management - Long-running crawl and agent tasks are assigned session IDs, allowing clients to poll for completion and retrieve results later.
- Recursive Crawlers - Discovering site structure or crawling pages for bulk data extraction and producing a sitemap.
- Website Crawlers and Scrapers - A tool that recursively retrieves content from all pages of a website, handling navigation and converting pages to structured formats.
- Web Change Monitors - A service that periodically checks web pages for changes and triggers notifications or webhooks when updates are detected.
- Headless Browser Orchestrators - Firecrawl's backend spins up headless Chromium instances to render JavaScript-heavy pages and execute user interactions.
- Programmatic Page Interactions - Performs browser actions such as clicking, typing, and scrolling on live web pages using natural language or code.
