automation

tradingview-mcp: Automate Chart Insights with AI‑Assisted Analysis

Name: tradingview-mcp: Automate Chart Insights with AI‑Assisted Analysis
Author: tradesdontlie

Founder-friendly AI links Claude Code to TradingView Desktop, delivering automated chart reads for faster trading decisions. 6.8k+ GitHub stars.

From the repo · “AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation”

6,908 stars+72★ this week2,841 forksJavaScriptGuide quality 8/10 · reviewed Oct 9Updated 10/21/2026100% free · open source

What it does

TradingView MCP is an AI-assisted tool that automates your TradingView chart analysis by connecting Claude Code to your TradingView Desktop for personal workflow automation

When to use it

•You need to automate repetitive tasks on your TradingView charts
•You want to integrate AI-driven insights into your trading decisions
•You're looking to streamline your workflow with custom scripts and automation

Ready-to-paste prompt

tv-mcp --script='console.log("Hello World");' --symbol='AAPL' --interval='1m'

Heads up: Make sure you have a valid TradingView API key and that you've correctly configured your `config.json` file with the API credentials and other settings, as the tool will not work without this

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/tradingview-mcp && curl -fsSL https://workflowstacks.com/api/skills/tradingview-mcp/claude-skill -o ~/.claude/skills/tradingview-mcp/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How tradingview-mcp: Automate Chart Insights with AI‑Assisted Analysis works

Codeflow

Free to inspect

Tradingview-mcp: Automate Chart Insights with AI‑Assisted Analysis is a medium JavaScript project (~7.1k lines across 57 code files, plus 9 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit 2 months ago, Other license, has a test suite.

Size

Medium codebase

~7.1k lines · 57 code files · 59 min skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Node.js

No API keys detected

JavaScript 98%Shell 1%Batchfile 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
src/server.js
Where the program starts running
4
package.json
Dependencies and the commands it exposes
5
src/cli/index.js
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic52 files

skills/Prompts, skills & agent definitions5 files

agents/Prompts, skills & agent definitions1 files

scripts/Helper scripts6 files

tests/Tests — proof it works9 files

.github/CI / automation (GitHub Actions)1 files

READMEHas testsDocumentedCI checksOther licenseUpdated 2 mo ago

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/tradingview-mcp && curl -fsSL https://workflowstacks.com/api/skills/tradingview-mcp/claude-skill -o ~/.claude/skills/tradingview-mcp/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

tradesdontlie

Language

JavaScript