How to integrate Firecrawl MCP with Pi

Pi is a minimal, self-extensible coding agent that lives in your terminal — one agent loop over Claude, GPT-5, Gemini, Grok, DeepSeek, and 20+ other providers, with maximum extension surface and minimum product opinion. Its core ships four tools (read, write, edit, bash) and self-extends at runtime through skills, extensions, and packages.

This guide explains the easiest and most robust way to connect your Firecrawl account to Pi. You can do this through either Composio Connect CLI or Composio Connect MCP. Because Pi already runs shell commands as first-class tools and ships no built-in MCP, the CLI is the recommended path — it's faster to set up, needs no server config, and chains multi-step tasks more reliably. The MCP path is also fully supported through Pi's official pi-mcp-adapter extension.

What is Composio Connect?

Composio Connect is a consumer offering that lets anyone plug 1,000+ applications directly into their agent harness — including Pi. It can:

• Search and load tools from relevant toolkits on-demand, reducing context usage.
• Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM.
• Manage app authentication end-to-end with zero manual overhead.

Prerequisites: Install Pi

Pi needs Node.js 18+ (Node 22 recommended). Install the agent globally with npm:

The Firecrawl MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Firecrawl account. It provides structured and secure access to automated web crawling, scraping, and data extraction, so your agent can perform actions like indexing sites, extracting structured content, mapping URLs, and searching the web on your behalf.

• Automated web crawling and indexing: Let your agent launch and manage web crawl jobs to gather content or index entire websites efficiently.
• Structured data extraction: Instruct your agent to extract targeted data from web pages using custom prompts or schemas, turning unstructured sites into actionable information.
• URL mapping and discovery: Have the agent explore and map all URLs within a website, including options for subdomain inclusion, sitemap processing, or search-based discovery.
• On-demand scraping and content retrieval: Enable your agent to scrape specific URLs, retrieve page content, and even extract structured JSON using LLM-powered methods.
• Integrated web search and data collection: Task your agent with running web searches, scraping top result pages, and returning relevant details—all in one workflow.

Way Forward

With Firecrawl connected, Pi can now act on your behalf whenever you ask it to.

From here, you can extend Pi further:

• Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Pi can do for you.
• Build workflows across tools: Once multiple apps are connected, Pi can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft.
• Lean into Pi's extension surface: Wrap common Firecrawl flows as Pi skills or prompt templates so recurring tasks become one-line commands, and use directTools in the MCP adapter to promote your most-used Firecrawl tools into Pi's tool list directly.

If you run into trouble or want to share what you've built, join the community or check out the Docs for deeper configuration options.