# tradesdontlie/tradingview-mcp

Source: [GitHub](https://github.com/tradesdontlie/tradingview-mcp)  
Feed7 permalink: https://feed7.dev/p/tradingview-mcp-1qplbet  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

This MCP server gives Claude Code local chart, Pine Script, alert, and screenshot controls through TradingView Desktop, but depends on undocumented internals and may conflict with platform terms.

## Source Summary

The project connects Claude Code to TradingView Desktop through an MCP server, local **CDP port 9222**, and **84 MCP tools**. It supports chart navigation, indicator reads, Pine Script iteration, drawings, alerts, replay, screenshots, layouts, and JSONL monitoring.

## Practical Implication

It is a useful reference for making a stateful Electron application legible to an agent: expose compact structured reads before screenshots, keep commands available through both MCP and CLI, and add explicit health checks and tool-selection guidance.

## Agent-Ready Context

The project connects Claude Code to TradingView Desktop through an MCP server, local **CDP port 9222**, and **84 MCP tools**. It supports chart navigation, indicator reads, Pine Script iteration, drawings, alerts, replay, screenshots, layouts, and JSONL monitoring.

It is a useful reference for making a stateful Electron application legible to an agent: expose compact structured reads before screenshots, keep commands available through both MCP and CLI, and add explicit health checks and tool-selection guidance.

It requires a valid TradingView subscription and deliberate debug-port activation. The integration uses undocumented internal interfaces that may break, cannot execute trades, and its programmatic data access may conflict with TradingView terms or market-data licenses.

## Connected Context

Feed7 judgment across 812 accumulated Signals:

TradingView MCP makes a stateful desktop application agent-readable through compact structured operations, CLI parity, health checks, and selective screenshots. It specializes the browser-control pattern into a deep application harness, but also exposes a sharper adoption boundary: useful automation depends on a debug port, undocumented internals, subscription access, and acceptable terms and data-license use, while trade execution remains out of scope.

- [ChromeDevTools/chrome-devtools-mcp](https://feed7.dev/p/chrome-devtools-mcp-0ow49x2) — Both use DevTools access to turn live application state into an agent feedback loop; TradingView MCP specializes that general browser interface into domain-specific reads and actions for an Electron application.
- [citrolabs/ego-lite](https://feed7.dev/p/ego-lite-1i7kk2j) — ego lite emphasizes isolated authenticated browser sessions, whereas TradingView MCP attaches through an explicitly enabled local debug port, making session exposure and process isolation separate controls implementers must address.
- [Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex](https://feed7.dev/p/full-workshop-setting-yourself-up-for-success-jason-liu-openai-codex-13uegzi) — The workshop’s requirement for explicit computer-use boundaries applies directly here because the integration can manipulate charts, scripts, alerts, and layouts even though it cannot execute trades.

## Context Map

- Layer: tools
- Domains: coding, data
- Topics: coding-agents, mcp, computer-use

## Uncertainty

- It requires a valid TradingView subscription and deliberate debug-port activation. The integration uses undocumented internal interfaces that may break, cannot execute trades, and its programmatic data access may conflict with TradingView terms or market-data licenses.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.