//
Used by over 1.25M developers
//
Trusted by 150,000+
companies of all sizes
companies of all sizes
[ 01 / 04 ]
·
Features
Perfect for
Research without leaving Claude: company research and product comparisons answered from current sources, with citations
Read a page you name and pull out the main points
Turn a pricing or product page into a table of fields
Answer a programming question from issues, pull requests, and docs
Run a literature review: find papers, read key passages, and follow citations
Get financial news and company data from data providers in Firecrawl Alexandria
Key Features
Search the web and get ranked results with the most relevant excerpts
Scrape any URL into clean markdown, or into JSON fields with a schema
Find data tools in Firecrawl Alexandria and check their inputs and price before running them
Pull structured records from 400+ data providers
Search research papers and check a paper's details
Read full-text passages and find related papers through citations
Search repositories, issues, pull requests, and API docs with the Developer Index
Sign in with your Firecrawl account, with no API key to copy
[ 02 / 04 ]
·
Installation
How do I add web search to Claude and Claude Code?
To add web search to Claude, install the official Firecrawl connector from Claude's connector directory, connect your Firecrawl account and turn it on in a chat. The connector works in Claude on the web, Claude Desktop, Cowork and the Code tab, with no code or API key. For Claude Code in a terminal, add the hosted Firecrawl MCP server with one command.
1
Install the Firecrawl connector
Click Add to Claude on this page to open the Firecrawl connector in Claude. In Claude Desktop, you can also go to Customize > Connectors and search for Firecrawl, or find it in the Claude connector directory.
2
Connect your Firecrawl account
Select Connect. Claude opens Firecrawl in your browser, where you sign in, choose a team, and approve access. No account yet? You can create one for free in the same flow.
3
Turn on Firecrawl in a chat
In a conversation, open the + menu, go to Connectors, and enable Firecrawl. Then ask Claude to use it. For example:
Prompt
Use Firecrawl to search for the latest Next.js release notes and summarize the sources.4
Add the same web search to Claude Code
Run this command in a terminal to add the hosted Firecrawl MCP server to Claude Code. Then enter /mcp in Claude Code, choose firecrawl and sign in through your browser. For setup with an API key instead, see the Firecrawl in Claude Code guide.
Terminal
claude mcp add --transport http firecrawl https://mcp.firecrawl.dev/v2/mcp-oauthHow do I get Claude to extract structured data from a list of URLs?
To get Claude to extract structured data from a list of URLs, turn on the Firecrawl connector, paste the URLs, and name the fields you want. Claude scrapes each URL with Firecrawl, which renders JavaScript pages, and returns one row per page as a table, JSON or CSV.
1
Turn on Firecrawl in the chat
Add the connector with the steps above, then open the + menu, go to Connectors, and enable Firecrawl for the conversation.
2
Paste the URLs and name the fields
Put one URL per line and list the fields to pull from each page. Name Firecrawl in the prompt so Claude reads the pages through the connector. In this example, replace the example.com URLs with your own:
Prompt
Use Firecrawl to scrape each of these URLs and extract the product name, price, currency and stock status. Return one row per URL as a table, and leave a field empty when the page doesn't show it.
https://example.com/products/trail-shoe
https://example.com/products/rain-jacket
https://example.com/products/day-pack3
Get the table, then export it
Ask Claude for the same rows as JSON or CSV, or add a field and run the prompt again. Each scraped page costs 1 Firecrawl credit, plus 4 Firecrawl credits per page when the scrape uses Firecrawl's JSON format. Reformatting Claude's answer costs nothing extra. For hundreds of URLs, use the Firecrawl batch scrape API, which runs the whole list as one job.
[ 03 / 04 ]
·
What Our Customers Say
//
Community
//
People love
building with Firecrawl
Discover why developers choose Firecrawl every day.
Firecrawl is an open-source framework that takes a URL, crawls it, and conver..."
Upload a CSV of emails and..."
Firecrawl is an open-source framework that takes a URL, crawls it, and conver..."
Upload a CSV of emails and..."
//
FAQ
//
Frequently
asked questions
Everything you need to know about this integration.
General
It is Firecrawl's official connector in the Claude directory. It lets Claude search the web, read pages from URLs you give, search developer sources such as issues, pull requests, and docs, and search research papers. It can also find and run data providers in Firecrawl Alexandria.
The connector gives Claude eight Firecrawl tools: web search, page scraping, Firecrawl Alexandria tool discovery, Developer Index search, and four research tools for searching papers, inspecting a paper, reading its full text, and finding related papers. You do not need to set up an MCP server separately.
Technical
Open the Firecrawl connector in the Claude directory and select Connect. Sign in to Firecrawl, choose a team, and approve access. Then open the + menu in a chat, go to Connectors, and enable Firecrawl.
Firecrawl ships one as the Firecrawl connector, which is listed in Claude's connector directory and runs on Firecrawl's hosted MCP server. One sign-in makes Firecrawl web search available in Claude Desktop chat, Cowork and the Code tab. Firecrawl also maintains the open-source Firecrawl MCP server for local setups and other MCP clients.
Integration
Turn on the Firecrawl connector alongside Claude's own web search and ask Claude to use Firecrawl. Firecrawl search returns ranked results with the passages that match your query, and Firecrawl can then scrape any result into clean Markdown, including pages built with JavaScript.
You need a Firecrawl account, and you can create one for free when you connect. You do not need to copy an API key. The connector uses your team's plan.
Advanced
Turn on Research from the + menu and enable the Firecrawl connector in the same chat. Claude's Research mode searches the web and every connector turned on for the chat, so it can run Firecrawl searches, read full pages from the results, and search research papers. Research needs a paid Claude plan with web search on, and it uses connectors in Claude on the web and Claude Desktop but not in the mobile app.
Claude's own page fetch often can't. In Glenn Gabe's GSQI retest on October 19, 2026, Claude got back only the header, navigation and footer of pages whose main content was built with JavaScript. With the Firecrawl connector, Claude reads those pages through Firecrawl's scrape tool, which renders JavaScript and returns the visible content as Markdown.
More Questions 1
Check that Firecrawl is enabled for the chat in the + menu under Connectors. If sign-in did not finish, open the connector in Claude and connect your Firecrawl account again.
Firecrawl Alexandria is Firecrawl's library of data for AI agents, with 400+ data providers alongside Firecrawl's own indexes. When you ask for data the open web covers poorly, Claude searches Firecrawl Alexandria for a tool that fits, checks what the tool needs, then runs it and returns structured data from the source. Some providers require your organization to accept their terms first, which an admin can do in the Firecrawl dashboard.
More Questions 2
Remove the connector in Claude, or review and revoke connections from MCP settings in your Firecrawl dashboard.
Why Firecrawl?
The world's most comprehensive web data API. Our custom browser stack and semantic index deliver superior data quality across any website, handling more content types and edge cases than any competitor.
JavaScript rendering, dynamic content, and robust request handling built-in.
Process millions of pages with automatic rate limiting, caching, and distributed infrastructure.
Optimized scraping engine with parallel processing and smart caching for instant results.
Comprehensive docs, SDKs for all major languages, and dedicated support to help you succeed.
[ 04 / 04 ]
·
Pricing
Flexible pricing
Start for free, then scale as you grow.Are you an AI agent? See pricing
Free Plan
A lightweight way to get started.
No cost, no card, no hassle.
$0
/month
500 searches or 1,000 pages scraped
2 concurrent requests
Low rate limits
Hobby
Great for side projects and small tools.
Fast, simple, no overkill.
$16
/month
Billed yearly
Save $382,500 searches or 5,000 pages scraped
5 concurrent requests
Basic support
$9 per extra 1.5k credits
StandardMost popular
Perfect for scaling with less effort.
Simple, solid, dependable.
$83
/month
Billed yearly
Save $19850,000 searches or 100,000 pages scraped
25 concurrent requests
Standard support
$47 per extra 35k credits
Growth
Built for high volume and speed.
Firecrawl at full force.
$333
/month
Billed yearly
Save $798250,000 searches or 500,000 pages scraped
50 concurrent requests
Priority support
$177 per extra 175k credits
Scale Plans
High-volume plans for teams that need more power and dedicated support. Get access to higher rate limits, more concurrent browsers, and priority support. Scale checks out instantly, no sales call needed.
Need more? Contact usAlso on AWS Marketplace and Google Cloud Marketplace.
Scale
For teams scaling their data pipelines
1,000,000 credits / month
$599/month
Billed yearly
Save $1,798500,000 searches or 1,000,000 pages scraped
100 concurrent requests
Priority support
$397 per extra 350k credits
//
Get started
//
Give Claude live web data
Add the Firecrawl connector and connect your account in under a minute.
Are you an AI agent? See setup options