Firecrawl for Claude Code plugin
The official Firecrawl plugin for finding sources, reading web pages and researching companies in Claude Code
- 259 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- Queries and retrieved material reach external services and the model context
- Contact-research skills can process personal information and client data
- Paid tools consume the connected account’s allowance
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/firecrawl-for-claude-codeDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Queries and retrieved material reach external services and the model context
- Contact-research skills can process personal information and client data
- Paid tools consume the connected account’s allowance
This is third-party code. Review the repository files before installing.
What it does
The Firecrawl plugin connects Claude Code to a hosted MCP server and adds 13 skills for web research. The agent chooses general search, developer documentation or research papers based on the task. Search returns excerpts and links; reading a full page requires a separate request. The skills organize these tools into research workflows. Some gather brand and company information, while others cover job postings, business contacts or SEO audits. Research tools provide paper search, metadata, citation relationships and relevant passages. The `/firecrawl:map` and `/firecrawl:crawl` commands also exist, but combine search with reading individual pages. Their results can be incomplete. Full site crawling is available through the separate Firecrawl CLI distribution.
Who it is for. For Claude Code users who need fresh information from the web, library documentation or research papers with cited sources.
Good fit when
- You need fresh sources on a topic summarized briefly with links
- You need to read a specific page and pull out given data
- A programming question whose answer sits in indexed repositories and documentation
- You need to find research papers and read the passages that answer a question
- You need company and business-contact information from web sources with traceable links
Not a fit when
- You need a complete site export: the plugin’s composite commands are limited to pages found through search and individual reads
- You need search and content fetching in one call: search here does not accept the scrapeOptions parameter
- Queries and client information must stay inside your infrastructure: the plugin uses Firecrawl’s server
Example request
Use Firecrawl to find three fresh sources on new Next.js features and summarize them briefly with linksLimitations
A connected Firecrawl account is required. The official pricing page on October 31, 2026 charges credits for web search and ordinary page reading, while the four Research Index paper tools are free. Third-party tools follow their providers’ pricing. Check the operation you need at firecrawl.dev/pricing before use. Queries, URLs and tool inputs reach external services, so exclude confidential information from client research.
How to disable. Disable or remove the Firecrawl plugin through `/plugin`, then disconnect its account in the MCP settings.
FAQ
How do I finish setting up Firecrawl in Claude Code?
After the installation commands, open `/mcp` and connect your account. After an update, run `/reload-plugins` or start a new session. The plugin does not require a separate CLI installation.
What if Firecrawl is installed from two marketplaces?
Keep one installation source. Disable the earlier distribution before switching to avoid duplicate skills and connections.
Can the Firecrawl CLI skills stay installed too?
Yes, but some skill names overlap. Check which version the agent selects: one calls MCP tools and the other runs CLI commands.
What is the Alexandria catalog?
Tool discovery lets the agent find structured-data providers suited to a task. Browsing the catalog and executing a discovered tool have different billing rules.
Does the plugin work in Claude.ai and Cowork?
These clients have a separate setup route: upload the plugin ZIP under Customize, then connect Firecrawl through Connectors. Claude Code installation commands do not apply to that workflow.
Discussion
No questions or reviews yet.
Related
PluginsFirecrawl skills catalog for Claude Code, Cursor and Codex: web search, scraping, crawling, page interaction and API integration
The Firecrawl command-line client with agent skills: web search, scraping, crawling, URL mapping and page interaction
Official Firecrawl MCP server: web search, page scraping to Markdown, site crawling and in-page actions
Ready-made Firecrawl workflows: sourced research, SEO audits, site QA, knowledge bases and company contact lists
Five skills that teach an agent to wire Firecrawl search, scraping and page interaction into the code of your own application
An open-source crawler that turns websites into clean Markdown for AI agents: install from PyPI, run in Docker and connect to Claude Code over MCP
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Firecrawl for Claude Code (this card) | yes | 259 | ||
| Firecrawl MCP Server | yes | API key | 7,809 | the official Firecrawl MCP server with site crawling and page actions |
| Firecrawl CLI | no | 684 | the Firecrawl command-line client with skills for crawling, URL mapping and page interaction |
README in short
The repository is generated from Firecrawl’s main plugin package, so a later release replaces edits made to the generated copy. Developers can validate the plugin structure with Claude Code.