"firecrawl" matching MCP servers:

A Model Context Protocol server for web scraping and searching, with automatic fallback from Tavily to Firecrawl for fetching web content.

Enables scraping and comparing LLM inference pricing from multiple providers using Firecrawl, storing results in SQLite for analysis.

An open-source MCP server providing AI agents with neural web search via Exa and tiered web fetch (Exa, local browser, Firecrawl) as a drop-in replacement for built-in web tools, preserving provenance and guarding against SSRF.

Web search for AI agents across 6 engines (Serper, Brave, Exa, Tavily, Firecrawl, Perplexity) through one search tool. Routes each query to the cheapest engine that clears a quality bar and caches repeats. Hosted, streamable-HTTP, BYOK supported.

Enables AI agents to fetch web pages with token estimation, caching, and routing to appropriate fetchers (Trafilatura, Jina, FireCrawl, pypdf) for clean Markdown output.

13 MCP tools for AI agents: scrape, extract, crawl, map, search, academic papers (arXiv + Crossref), batch scrape, deep research, monitor page changes, persistent browser session, cache control. 3-tier auto-fallback ladder with free Cloudflare bypass, no API keys. Self-hosted Firecrawl alternative. uvx pyrecrawl serve

A dual-path web search MCP server for Claude Code that cross-validates results via Tavily/Firecrawl and Google, explicitly returning sources to reduce hallucinations.

MCP server for web page fetching (converting to Markdown/text with automatic fallback between Tavily and Firecrawl) and web search via Tavily.

A Grok-first multi-source search MCP for AI agents that integrates Grok, Tavily, AnySearch, and Firecrawl to provide unified search results, cross-verification, and web content fetching.

Enables fetching and extracting web content as markdown using Firecrawl API, with support for single or multiple concurrent URL fetches and web search capabilities.

Free, open-source, token-efficient local alternative to Firecrawl with a native Model Context Protocol (MCP) server. Achieves >73% token reduction by pruning web noise before Markdown extraction, uses Playwright with stealth fingerprint patches to bypass anti-bot challenges.

Lightweight MCP server for web scraping, search, and crawling. Uses local trafilatura/DuckDuckGo by default with optional Firecrawl fallback for transport-blocked pages.

Enables freelancers and agencies to run eight back-office workflows across Stripe, Google Drive, Linear, Google Calendar, Gmail, GitHub, Google Docs, Granola, Google Sheets and Firecrawl, covering client onboarding, invoices from calendar and commits, status reports, scope-creep detection, site audits and overdue invoice chasers. Reads run freely, while anything that creates, sends, changes or deletes is shown for approval first, with credentials kept in your own OS keychain and no proxying through any third-party server.

Runs twelve agent workflows over Shopify, Google Sheets, Gmail, Slack, Firecrawl, Linear and Stripe — drafting supplier reorders, answering order-status emails, posting daily sales digests, importing supplier catalogues into the store, handling cancellations and wholesale orders, flagging fulfillment exceptions, and consolidating revenue from multiple payment sources. Each workflow is a slash-command prompt backed by only the tools it needs, with reads running freely and any write shown for approval first.

Local MCP service recommendations for BrowserAct, SearchApi, PDF.co, Make, Apify and Firecrawl. Install resultgate-pilot 0.3.1 with --referrals for six recommendation and evidence tools. Existing, local and free options take priority; BrowserAct affiliate links are disclosed. No provider execution, purchases or credential collection. Hosted /mcp is a separate authenticated simulation gateway.

Enables AI-powered competitor pricing analysis by scraping LLM inference pricing websites via Firecrawl, storing the data in SQLite, and answering cost comparison queries through natural language.

An MCP server that turns CI failures, pull requests, security alerts, and Slack threads into Linear issues, Slack posts, changelogs, docs, and reports with evidence attached, through 25 agent-run workflows over 59 tools spanning GitHub, Linear, Slack, Notion, Google Docs, Google Calendar, Google Sheets, Firecrawl, and Tavily. It also handles credential setup in the OS keychain and pauses for approval before any create, send, change, or delete call.

Runs 13 agent slash-command workflows across Linear, GitHub, Google Docs, Slack, Firecrawl, Sheets, Tavily, Forms, Calendar, Gmail, Stripe, Granola and Notion — turning shipped features into blog and social drafts and handling competitor pricing, mention monitoring, SEO gaps, webinars, newsletters and launch-day tracking. Every credential is your own, kept in the OS keychain or client config, and anything that writes, sends or deletes is shown for approval first.

Enables agents to run eight recruiting and onboarding workflows — filing applications with CVs into a candidate sheet, booking interview panels, summarising interviewer debriefs, researching a candidate's public work, provisioning a new hire's day one, running pulse surveys, drafting offer letters, and writing market-benchmarked job posts. It spans Gmail, Google Drive, Sheets, Calendar, Forms and Docs, plus Granola, Notion, Slack, GitHub, Linear, Tavily and Firecrawl, with read-only calls running freely and any write, send or delete shown for approval first.

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.