tradingview-mcp
AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation
The TradingView MCP server connects AI assistants like Claude to your locally-running TradingView Desktop application for automated chart analysis and workflow assistance. Using Chrome DevTools Protocol, it provides 78 tools that enable AI agents to read indicator values, navigate charts, develop Pine Script code, manage layouts, control replay mode, and capture screenshots. All data processing occurs locally on your machine without connecting to TradingView's servers, requiring an active TradingView Desktop subscription and Node.js 18+.
Key Features
Use Cases
- 01AI-assisted Pine Script indicator and strategy development with real-time compilation feedback
- 02Automated chart analysis workflows reading indicator values, price levels, and annotations
- 03Multi-symbol dashboard setup with automated pane layouts and symbol switching
- 04Replay mode practice sessions with AI guidance for entry/exit timing
- 05Chart annotation and drawing management through natural language commands
- 06Local monitoring scripts that stream live quote and indicator data for custom alerts
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
tradingview-mcp — FAQ
What is the TradingView MCP server?+
It's an MCP server that connects AI assistants like Claude to your locally-running TradingView Desktop application via Chrome DevTools Protocol. It provides 78 tools for chart analysis, Pine Script development, and workflow automation, processing all data locally without connecting to TradingView's servers.
How do I install and connect it to Claude Code?+
Clone the repository, run npm install, launch TradingView Desktop with the --remote-debugging-port=9222 flag (using provided scripts), and add the server configuration to your Claude Code MCP config file at ~/.claude/.mcp.json. Use tv_health_check to verify the connection.
Which AI clients does it work with?+
It works with Claude Code and any MCP-compatible client. It also provides a standalone CLI (`tv` command) for terminal-based workflows and scripting.
What are the prerequisites and is it free?+
Requires Node.js 18+, TradingView Desktop with an active paid subscription (for real-time data), and an MCP-compatible AI client. The MCP server itself is free and open-source under MIT license, but you must have your own TradingView subscription.
Does this connect to TradingView's servers or redistribute data?+
No, it only connects to your locally-running TradingView Desktop application via Chrome DevTools Protocol on localhost port 9222. All data processing occurs on your machine, and no market data is transmitted, stored, or redistributed externally.
Is this affiliated with TradingView or Anthropic?+
No, this is an independent open-source project not affiliated with, endorsed by, or associated with TradingView Inc. or Anthropic. Users are solely responsible for ensuring compliance with TradingView's Terms of Use.
How do I install tradingview-mcp?+
Open the source repository on GitHub and follow its README. tradingview-mcp is a mcp server — MCP Agents Market links you directly to the official repo.
Is tradingview-mcp free?+
tradingview-mcp is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.