Firecrawl was the fastest MCP for web search and extraction with 7-second average run time and 83% accuracy. 64.8% success on browser automation tasks.
Firecrawl MCP Server
activeOfficial Firecrawl MCP for scraping, extraction, and deep research workflows. 95K+ GitHub stars (main repo), 1.23M combined weekly downloads, backed by $14.5M Series A. ScrapeOps 10/10.

Where it wins
Official provider support
Strong extraction and scraping shape
Best fit when research means real web pages, not just search snippets
Where to be skeptical
Not the system of record itself
Needs a downstream workspace if you want operating memory
AGPL-3.0 license may complicate enterprise adoption
Editorial verdict
#1 in product-business-development by volume and evidence. 5,809 stars, 50.6K npm/wk (highest in category), 83% benchmark accuracy (AIMultiple), F1 0.638 (SearchMCP). Morph confirms 89% recall, 95.3% success rate. Four independent sources confirm extraction superiority.
Videos
Reviews, tutorials, and comparisons from the community.
Turn Any Website Into LLM Ready Data INSTANTLY
Firecrawl MCP = Effortless Web Scraping
Scrape ANY Website With AI For FREE with Firecrawl! Best AI Web Scraper (Opensource)
Related
Product / Business Development
Structured web extraction, competitive research, lead enrichment, content ingestion into agent pipelines
Search & News
Web scraping, structured extraction, turning messy pages into LLM-ready content — the research/extraction workhorse

Crawl4AI
93Free, open-source web scraping (Apache-2.0). 62K stars, 6,353 forks (nearly matches Firecrawl), actively maintained (v0.8.5, 2026-03-18), 384K weekly PyPI downloads. Best open-source alternative to Firecrawl.

SearXNG
88Privacy-first, self-hosted meta-search engine aggregating 70+ upstream engines. Zero cost, zero API keys, full data sovereignty.
Exa MCP Server
87Official Exa MCP for fast web search and crawling when the workflow is search-first rather than page-ops-first.
Notion MCP Server
86Official Notion MCP server with hosted OAuth, token-optimized Markdown responses, and 22 tools for page/database/search operations.
Public evidence
YC-backed, $14.5M Series A (Aug 2025). 350K+ developers using API. Returns clean markdown optimized for LLMs.
Agent Score 14.58 (#2 of 8). Statistically tied with Brave (#1) and Exa (#3). Only tool combining search + scrape + agent in one platform.
94K+ stars is exceptional — 50% more than the next competitor (Crawl4AI at 62K). Community has voted with their stars. Active daily commits as of 2026-03-18.
Parallel agent execution for thousands of simultaneous queries. Spark-1-pro for complex multi-domain research, spark-1-mini 60% cheaper. Browser Sandbox with Playwright for interactive automation. 3+ major features in Feb alone.
Three independent sources reaching the same conclusion: Firecrawl wins on ease of use, enterprise compliance, combined search+scrape. Crawl4AI wins on license, cost, control. Strong signal validating both tools' positioning.
F1 0.638 vs Exa's 0.508 — a 25% gap. Third independent source (alongside AIMultiple and multiple review sites) confirming Firecrawl's extraction superiority.
Direct BD workflow mapping: competitive pricing analysis, product launch monitoring, market campaign tracking. B2B SaaS case study: identified market opportunities 2-3 weeks ahead.
10/10 rating, 'Firecrawl is the best tool you can get.' $666/million pages. Independent hands-on testing confirms quality and ease of use.
89.0% recall at retrieval depth 5, 6.8% noise ratio, 16 pages/second, 95.3% overall success rate. Confirms strong extraction quality from a non-Firecrawl source.
Single-page scrape: 2-6s static, 5-15s JS-heavy. Honest limitations noted: no built-in scheduling, 500 lifetime free credits is stingy. Recent independent practitioner-level review.
Top-tier MCP server by traffic. Ranked #32 out of 10,000+ MCP servers. Remote endpoint via SSE at mcp.firecrawl.dev. 5.8K GitHub stars.
Raw GitHub source
GitHub README peek
Constrained peek so you can sanity-check the source material without leaving the site.
Firecrawl MCP Server
A Model Context Protocol (MCP) server implementation that integrates with Firecrawl for searching, scraping, and interacting with the web.
Big thanks to @vrknetha, @knacklabs for the initial implementation!
Features
- Search the web and get full page content
- Scrape any URL into clean, structured data
- Interact with pages — click, navigate, and operate
- Deep research with autonomous agent
- Cloud browser sessions with agent-browser automation
- Automatic retries and rate limiting
- Cloud and self-hosted support
- SSE support
Installation
Running with npx
env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
Manual Installation
npm install -g firecrawl-mcp
Running on Cursor
Configuring Cursor 🖥️ Note: Requires Cursor version 0.45.6+ For the most up-to-date configuration instructions, please refer to the official Cursor documentation on configuring MCP servers: Cursor MCP Server Configuration Guide
To configure Firecrawl MCP in Cursor v0.48.6
- Open Cursor Settings
- Go to Features > MCP Servers
- Click "+ Add new global MCP server"
- Enter the following code:
{ "mcpServers": { "firecrawl-mcp": { "command": "npx", "args": ["-y", "firecrawl-mcp"], "env": { "FIRECRAWL_API_KEY": "YOUR-API-KEY" } } } }
To configure Firecrawl MCP in Cursor v0.45.6
- Open Cursor Settings
- Go to Features > MCP Servers
- Click "+ Add New MCP Server"
- Enter the following:
- Name: "firecrawl-mcp" (or your preferred name)
- Type: "command"
- Command:
env FIRECRAWL_API_KEY=your-api-key npx -y firecrawl-mcp
If you are using Windows and are running into issues, try
cmd /c "set FIRECRAWL_API_KEY=your-api-key && npx -y firecrawl-mcp"
Replace your-api-key with your Firecrawl API key. If you don't have one yet, you can create an account and get it from https://www.firecrawl.dev/app/api-keys
After adding, refresh the MCP server list to see the new tools. The Composer Agent will automatically use Firecrawl MCP when appropriate, but you can explicitly request it by describing your web scraping needs. Access the Composer via Command+L (Mac), select "Agent" next to the submit button, and enter your query.
Running on Windsurf
Add this to your ./codeium/windsurf/model_config.json:
{
"mcpServers": {
"mcp-server-firecrawl": {
"command": "npx",
"args": ["-y", "firecrawl-mcp"],
"env": {
"FIRECRAWL_API_KEY": "YOUR_API_KEY"
}
}
}
}
Running with Streamable HTTP Local Mode
To run the server using Streamable HTTP locally instead of the default stdio transport:
env HTTP_STREAMABLE_SERVER=true FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp
Use the url: http://localhost:3000/mcp
Installing via Smithery (Legacy)
npx -y @smithery/cli install @mendableai/mcp-server-firecrawl --client claude
Running on VS Code
For one-click installation, click one of the install buttons below...
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "apiKey",
"description": "Firecrawl API Key",
"password": true
}
],
"servers": {
"firecrawl": {
"command": "npx",
"args": ["-y", "firecrawl-mcp"],