firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
Firecrawl MCP server integrates web scraping, search, and interaction capabilities into MCP-compatible AI clients through the Firecrawl API. This server enables AI agents to search the web, scrape websites into LLM-ready markdown or structured data, crawl entire domains, and interact with pages using AI prompts. It provides tools for converting web content into clean, token-efficient formats that agents can process directly. The MCP server acts as a bridge between AI assistants and Firecrawl's hosted web data API, handling authentication and exposing scraping operations as callable functions.
Key Features
Use Cases
- 01Enabling Claude Desktop or other MCP clients to search and extract web data in real-time
- 02Building AI agents that gather competitive intelligence by crawling competitor websites
- 03Automating research workflows by having AI assistants scrape documentation sites
- 04Creating chatbots that answer questions using live web content rather than stale training data
- 05Powering autonomous agents that navigate e-commerce sites to extract pricing information
- 06Generating structured datasets from web sources for machine learning pipelines
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
firecrawl — FAQ
What is the Firecrawl MCP server?+
It's an MCP server that connects AI clients like Claude Desktop to the Firecrawl web scraping and search API. It exposes web data extraction as callable tools that agents can use during conversations.
How do I install the Firecrawl MCP server?+
Add the server configuration to your MCP client's settings file (e.g., claude_desktop_config.json), specifying 'npx -y firecrawl-mcp' as the command and your Firecrawl API key in the environment variables. Restart your client after saving the configuration.
Which AI clients support this MCP server?+
Any MCP-compatible client works, including Claude Desktop, Cline, and other tools that implement the Model Context Protocol. The README specifically mentions Claude Code, Antigravity, and OpenCode as compatible platforms.
Do I need a Firecrawl API key?+
Yes, you must sign up at firecrawl.dev to obtain an API key. The hosted cloud service requires this key for authentication, though the open-source version can be self-hosted without the cloud API.
Is the Firecrawl MCP server free to use?+
The MCP server code itself is open source, but it connects to Firecrawl's cloud API which has paid pricing tiers. You can also self-host the entire Firecrawl stack under the AGPL-3.0 license to avoid API costs.
What output formats does the scraper support?+
Firecrawl can return scraped content as clean markdown (optimized for LLMs), raw HTML, screenshots, or structured JSON validated against custom schemas. The markdown output is designed to minimize token usage while preserving semantic structure.
How do I install firecrawl?+
Open the source repository on GitHub and follow its README. firecrawl is a mcp server — MCP Agents Market links you directly to the official repo.
Is firecrawl free?+
firecrawl is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.