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.

DimensionTradingView MCPMarket data and technical analysis MCP server for AI assistantsFirecrawl MCP ServerFirecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
FMRS65 / 100 · C75 / 100 · B
Reliability9 / 2013 / 20
Security and permissions14 / 2012 / 20
Maintenance13 / 2016 / 20
Documentation15 / 2017 / 20
Setup experience14 / 2017 / 20
Best for
  • Users conducting market research through AI assistants
  • Developers who want a free, self-hosted MIT-licensed server
  • Researchers prototyping technical-analysis, screening, and backtesting workflows
  • 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 seeking automated trade execution or money management
  • Users seeking investment, legal, tax, or accounting advice
  • Professional trading workflows requiring guaranteed accurate, complete, or latency-free data
  • 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
  • No TradingView account or API key is required, and the server does not log into or automate TradingView sessions
  • Marketaux API access is optionally required for news and sentiment features
  • Self-hosting requires a local Python/uv environment and dependencies
  • 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
  • Outputs are for educational and research purposes and are not financial advice
  • Third-party market data may be delayed, inaccurate, or incomplete
  • Upstream services may rate-limit requests or fail temporarily
  • Users must comply with applicable laws and the terms of connected data sources
  • 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, ChatGPT, Cursor, GitHub Copilot, Codex, OpenClawClaude Desktop, VS Code, Cursor, Windsurf, Zed, Amp
Tools2211