M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionTrvlReal travel search for your AI assistant — flights, hotels, trains, cars, ferries, no API keys, single Go binary.Firecrawl MCP ServerFirecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
FMRS55 / 100 · C75 / 100 · B
Reliability8 / 2013 / 20
Security and permissions10 / 2012 / 20
Maintenance10 / 2016 / 20
Documentation14 / 2017 / 20
Setup experience13 / 2017 / 20
Best for
  • Personal users who already plan trips with AI assistants and want real data.
  • Developers who need travel search in their apps without expensive APIs.
  • Users who value no-API-key, local-first, privacy-conscious tools.
  • Scenarios needing clean, structured web context fed to an AI assistant
  • Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
Not for
  • Users who just want to book on a website (e.g., Google Flights).
  • Teams needing a hosted product with accounts and dashboards.
  • Commercial or internal use without a separate license due to PolyForm Noncommercial license.
  • Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
  • Sites that explicitly disallow automated access (robots.txt)
Required permissions
  • Reads browser cookies (automatic, to access bot-protected APIs)
  • Accesses local filesystem (reads/writes state files under ~/.trvl)
  • Sends anonymous telemetry (can be disabled)
  • Optionally reads credential managers (only for AFKLM, explicitly requested)
  • Optionally writes to Google Calendar (via calendar helper)
  • Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
  • firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
Risks and side effects
  • Automated access to some providers may violate their Terms of Service; user responsible for compliance.
  • Browser cookie reading may raise privacy concerns; it's enabled by default but can be disabled via environment variable.
  • Telemetry sends anonymous usage data, but can be turned off.
  • Prices and availability may be inaccurate or change; always verify before booking.
  • Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
  • firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
Supported clientsClaude Desktop, Claude Code, Cursor, Windsurf, Codex, VS Code, Zed, Gemini, Amazon Q, LM StudioClaude Desktop, VS Code, Cursor, Windsurf, Zed, Amp
Tools111