firecrawl — Claude Code plugin: scraping and search over MCP
Pulls web pages into clean markdown, finds sources and returns structured data. Handy when your agent needs fresh material from the web.
/plugin install firecrawl@claude-plugins-official
/plugin marketplace add anthropics/claude-plugins-community
/plugin install firecrawl@claude-community
/plugin marketplace add anthropics/claude-plugins-officialWhat firecrawl does
The plugin wires Claude to Firecrawl's hosted MCP server. It ships three skills: firecrawl, firecrawl-developer-index and firecrawl-research-index. The first reads single pages and searches the web, the second works against indexed repositories and docs, the third covers scientific papers and US government publications.
Configuration lives in .mcp.json, and you connect your Firecrawl account from the /mcp menu. Skip that step and the tools stay dead: the skills report connection and authentication failures, so you go back to /mcp and sign in again. After an update, run /reload-plugins or start a new session.
Version 2.0.0 moved to MCP and dropped the Firecrawl CLI. No CLI install or authentication is needed anymore, and the CLI commands — map, crawl, interact, monitor, agent and the rest — left the plugin for the CLI's own skill distribution. Install both and Claude lists two sets of skills under the same names. Keep one Firecrawl installation: if you switch from the official marketplace to this repository, disable the previous plugin first.
What it helps with
- read a page and pull the fields you need
- find recent sources on a topic and cite them
- answer a programming question from indexed repos and docs
- locate scientific papers and the passages that matter
- search US government publications and get structured data
Example prompts for the agent
- find recent sources on this API and summarize them with citations
- read the page at this URL and extract the pricing table
- find papers on this topic and show the relevant passages
How to install firecrawl
Plugin marketplace
/plugin install firecrawl@claude-plugins-official/plugin marketplace add anthropics/claude-plugins-community/plugin install firecrawl@claude-community/plugin marketplace add anthropics/claude-plugins-officialStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about firecrawl
How do I install firecrawl in Claude?
Add the repository as a marketplace: /plugin marketplace add firecrawl/firecrawl-claude-plugin, then install the plugin: /plugin install firecrawl@firecrawl. Finish by opening /mcp and connecting your Firecrawl account.
What does firecrawl do?
It gives Claude access to Firecrawl's hosted MCP server for page reading, web search, indexed documentation and scientific publications. The three skills split the source types between them.
How is 2.0.0 different from 1.x?
It runs over MCP instead of the Firecrawl CLI, so there is nothing to install or authenticate on the CLI side. The CLI commands were removed from the plugin and now live in the CLI's own skill distribution.
Source text
SKILL.md · MIT
# Firecrawl for Claude Code Search the web, read source pages, retrieve structured data, and research developer documentation, government publications, and scientific papers using Firecrawl's hosted MCP tools. This plugin includes three skills: `firecrawl`, `firecrawl-developer-index`, and `firecrawl-research-index`. It connects to Firecrawl's hosted MCP server (configured in `.mcp.json`). Connect your Firecrawl account through Claude Code's `/mcp` menu before using the tools. ## Install In Claude Code, open `/plugin`, search for **firecrawl**, and install it. The official marketplace controls which release is available there. You can also add this repository directly as a marketplace: ```text /plugin marketplace add firecrawl/firecrawl-claude-plugin /plugin install firecrawl@firecrawl ``` Choose one installation of Firecrawl. If switching from the official marketplace to this repository, disable the previous Firecrawl plugin first. After an update, run `/reload-plugins` or start a new session, then use `/mcp` to complete the account connection. ## Upgrading from 1.x Version 2.0.0 connects to Firecrawl's hosted MCP server instead of the Firecrawl CLI. You no longer need to install or authenticate the CLI for this plugin; connect your account with `/mcp` instead. The CLI skills (map, crawl, interact, monitor, agent, parse, download and the other CLI commands) are no longer part of this plugin. To keep using them, install them from the CLI's own skill distribution, either with: ```sh npx skills add firecrawl/cli ``` or as a Claude Code plugin from the Firecrawl skills catalog: ```text /plugin marketplace add firecrawl/skills /plugin install firecrawl@firecrawl-skills ``` The CLI skills and this plugin both include skills named `firecrawl`, `firecrawl-developer-index` and `firecrawl-research-index`. The CLI versions run CLI commands and the versions here call MCP tools. If you install both, Claude Code lists both. ## Use - Find recent sources on a topic and summarize them with citations. - Read a supplied webpage and extract the requested information. - Research a programming question using indexed repositories and documentation. - Find scientific papers and read passages relevant to a question. - Search US government publications and retrieve structured provider data. The skills report connection and authentication failures so you can reconnect through `/mcp`. ## Development This repository is a generated distribution of the Firecrawl MCP plugin package. Edits here are replaced by the next package release. To validate a local checkout: ```sh claude plugin validate . claude --plugin-dir . ``` ## Resources - [Firecrawl documentation](https://docs.firecrawl.dev) - [Firecrawl](https://www.firecrawl.dev) - [Report a problem](https://github.com/firecrawl/firecrawl-claude-plugin/issues) ## License MIT. See [LICENSE](LICENSE).
© firecrawl · MIT · firecrawl/firecrawl-claude-plugin
