Firecrawl MCP Server is a Model Context Protocol server that connects AI agents to Firecrawl’s tools for searching, scraping, and interacting with live websites. It is used by coding agents and other compatible language-model clients that need web content in structured, agent-ready form.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/firecrawl/firecrawl-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/firecrawl/firecrawl-mcp-server/gemini-extension)<a href="https://agentmods.dev/plugins/firecrawl/firecrawl-mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/firecrawl/firecrawl-mcp-server/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/firecrawl/firecrawl-mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/firecrawl/firecrawl-mcp-server/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
firecrawl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "firecrawl",
"version": "3.30.1",
"description": "Official Firecrawl MCP for web search, scraping, crawling, and structured data extraction.",
"mcpServers": {
"firecrawl": {
"command": "npx",
"args": ["-y", "firecrawl-mcp"],
"env": {
"FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}"
}
}
},
"settings": [
{
"name": "Firecrawl API Key",
"description": "Your Firecrawl API key. Get one at https://firecrawl.dev/app/api-keys",
"envVar": "FIRECRAWL_API_KEY",
"sensitive": true
}
]
}
What ships with it
1 file beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed c7fb86f8382a
- 2d ago Changed 96f1e1c9fc8b
- 7d ago Changed 241e008e66de
- 9d ago Changed c75f19c6fce6
- 13d ago Changed 1375fb9cc976
- 14d ago Changed fb82fc8090fd
- 15d ago Changed 8971343e6ceb
- 16d ago Changed 452f722bae78
- 17d ago First seen · 23 lines scan A bc6a9442d30f
firecrawl is a plugin published in the GitHub repository firecrawl/firecrawl-mcp-server (7,610 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
Other plugins, from other repositories
firecrawl
Search the web, developer sources, and scientific papers with Firecrawl.
firecrawl-lean
Web scraping, search, crawling, and browser interaction via Firecrawl CLI.
firecrawl
The context API for AI agents. Search the live web, scrape any page into clean Markdown or structured data, and interact with dynamic pages, plus crawl, map, monitor, and Alexandria data providers. Runs on the hosted Firecrawl MCP server with browser sign-in, no API key to paste.
firecrawl
Search the web, developer sources, and scientific papers with Firecrawl.
claude-crawl
Web search, fetch, and crawl via Jina AI, Cloudflare Browser Rendering, and Firecrawl.
build-information
MCP configuration declaring 1 server: build-information.