Firecrawl MCP Server

Enables AI agents to scrape and crawl websites through the Model Context Protocol using Firecrawl. Converts web pages into clean, LLM-friendly markdown format, handling JavaScript rendering, pagination, and anti-bot measures. Ideal for extracting structured content from websites at scale.

Security Assessment

Level	safe
Permissions	read:web_content
Data Exposure	none
Requires Supervisor	No
Risk Notes	Read-only web scraping and crawling. Converts pages to markdown.

Integration

Type	`mcp-server`
Package	`firecrawl-mcp`
Auth	api-key

Capabilities

Actions	scrape_url, crawl_site, extract_content, convert_to_markdown
Input Types	url, text
Output Types	text, markdown, json
When to Use	When the agent needs to scrape web pages and convert them to clean markdown for processing.
When NOT to Use	When interactive browser automation is needed; use puppeteer-mcp or playwright-mcp instead.

Category: content · Free tier: Yes · Firecrawl offers a free tier with limited pages; paid plans for higher volume. · Source

Collected: 2026-03-15 from https://github.com/mendableai/firecrawl-mcp-server