← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionTradingView MCP BridgeAI-assisted TradingView chart analysis and Pine Script development via Chrome DevTools ProtocolHevy MCPManage your Hevy workout data from AI assistants via MCP.Firecrawl MCP ServerFirecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
FMRS53 / 100 · D77 / 100 · B75 / 100 · B
Reliability8 / 2012 / 2013 / 20
Security and permissions11 / 2016 / 2012 / 20
Maintenance9 / 2016 / 2016 / 20
Documentation14 / 2018 / 2017 / 20
Setup experience11 / 2015 / 2017 / 20
Best for
  • Individual traders/researchers with a paid TradingView subscription who run TradingView Desktop
  • Developers who want AI assistance writing and debugging Pine Script
  • Researchers studying human-AI collaboration on professional financial interfaces
  • Claude Code users who want chart automation on their own machine
  • Hevy PRO users who want AI assistants to directly access their workout data
  • People who prefer using MCP clients like Claude, Cursor, Codex for fitness tracking
  • Anyone needing summaries and insights from their training data
  • 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
  • Use cases requiring TradingView's official APIs or cloud services
  • Automated trading bots or algorithmic order execution
  • Commercial redistribution or resale of TradingView market data
  • Users without a paid TradingView subscription or the Desktop app installed
  • Production environments needing a stable, officially supported API rather than an undocumented interface that can break on updates
  • Users without a Hevy PRO subscription (API key required)
  • Users who want to use the server without an API key
  • Those needing delete workflows (Hevy API does not expose delete endpoints)
  • 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
  • Requires TradingView Desktop to be explicitly launched with `--remote-debugging-port=9222`, opening a local debug port
  • Requires Node.js 18+ and local filesystem access to clone and run the MCP server
  • Requires an active, logged-in TradingView subscription
  • The MCP server itself communicates with Claude Code over stdio and is not exposed to the network
  • Requires HEVY_API_KEY environment variable for Hevy API authentication
  • Can create, update, and replace workouts, routines, folders, templates, and body measurements via tools
  • Read operations can fetch workouts, routines, folders, templates, history, and user info
  • 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
  • Relies on undocumented internal TradingView Electron/CDP interfaces that can change or break without notice on updates
  • Opening the local debug port means other processes on the same machine could theoretically access it
  • Automated reading/processing of TradingView data may conflict with TradingView's Terms of Use restrictions on automated data collection — usage compliance is the user's responsibility
  • Not affiliated with or supported by TradingView Inc., so long-term compatibility is not guaranteed
  • The README explicitly warns against redistributing data or circumventing paywalls; misuse could risk account suspension
  • API key can be misused if leaked; do not expose in URLs, logs, or screenshots
  • Create operations may produce duplicates on retry; update operations replace existing records
  • The server sends data to the Hevy API and may send telemetry to external services unless disabled
  • 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 CodeClaude Desktop, Cursor, Codex, Google AntigravityClaude Desktop, VS Code, Cursor, Windsurf, Zed, Amp
Tools622611