tradinview-mcp
A TradingView-style market research and charting MCP server that provides tools for market data, indicators, watchlists, and local HTML chart rendering without scraping TradingView.
README
tradinview-mcp
Provider-based TradingView-style market research and charting MCP server.
This project does not scrape TradingView, does not use undocumented TradingView APIs, and does not execute trades. It exposes MCP tools for market-data research, indicator calculation, watchlists, and local chart HTML rendering.
Quick Start
pnpm install
cp .env.example .env
pnpm dev
The default provider is mock, so the server works without API keys.
For the ChatGPT/Vercel-style remote endpoint locally:
pnpm dev:http
Endpoint:
http://localhost:3000/api/mcp
Real Provider Mode
mock is the safe offline default. To use real public crypto market data, enable Binance:
ENABLE_BINANCE=true
DEFAULT_PROVIDER=binance
BINANCE_BASE_URL=https://data-api.binance.vision
To make sure the server never starts accidentally with mock data:
REQUIRE_REAL_PROVIDER=true
Then run:
pnpm dev
Use the verify_provider MCP tool with:
{ "provider": "binance", "symbol": "BTCUSDT", "interval": "1h" }
That tool performs real quote and OHLCV calls and returns realProvider: true when the selected provider is not mock.
MCP Client Config
After building:
pnpm build
Add a stdio MCP server entry similar to:
{
"mcpServers": {
"tradinview-mcp": {
"command": "node",
"args": ["C:/Users/mobol/Downloads/tradinview-mcp/dist/index.js"],
"env": {
"DEFAULT_PROVIDER": "mock"
}
}
}
}
ChatGPT via Vercel
Deploy the remote MCP endpoint:
npx vercel --prod
Set Vercel env vars for real Binance data:
ENABLE_BINANCE=true
DEFAULT_PROVIDER=binance
REQUIRE_REAL_PROVIDER=true
BINANCE_BASE_URL=https://data-api.binance.vision
WATCHLIST_PATH=/tmp/watchlist.json
Then connect ChatGPT Developer Mode to:
https://your-project.vercel.app/api/mcp
See Setup for the full ChatGPT connection flow.
For development, use:
{
"mcpServers": {
"tradinview-mcp": {
"command": "pnpm",
"args": ["dev"],
"cwd": "C:/Users/mobol/Downloads/tradinview-mcp"
}
}
}
Tools
search_symbols: search configured providers.get_quote: get latest normalized quote.get_ohlcv: get OHLCV bars.calculate_indicators: calculate SMA, EMA, RSI, MACD, and Bollinger Bands.render_chart_html: render safe local Lightweight Charts HTML from supplied bars.get_watchlist: read local watchlist.add_to_watchlist: add or update a watchlist symbol.remove_from_watchlist: remove a watchlist symbol.verify_provider: perform a provider quote/OHLCV smoke check.
Example tool inputs:
{ "query": "BTC", "provider": "mock" }
{ "symbol": "BTCUSDT", "interval": "1h", "limit": 100, "provider": "mock" }
{
"bars": [
{ "time": "2026-06-23T00:00:00.000Z", "open": 100, "high": 105, "low": 99, "close": 103, "volume": 1000 }
],
"indicators": [{ "type": "SMA", "period": 20 }]
}
Resources
market://schemamarket://provider-statusmarket://compliance-notes
Prompts
analyse_symbolcompare_assetsbuild_watchlist
Optional Binance Provider
Binance is disabled unless configured:
ENABLE_BINANCE=true
DEFAULT_PROVIDER=binance
Only public crypto spot market data endpoints are used. The default Binance URL is https://data-api.binance.vision, Binance's market-data-only base endpoint.
Verification
pnpm typecheck
pnpm test
pnpm build
Run the live provider smoke test only when you want an internet-backed check:
pnpm test:live
More details:
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.