Skillget

tv-mcp

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This MCP server provides a programmatic interface for scraping historical price data, technical indicators, and market news from TradingView. It is designed to integrate automated market research and data pipelines directly into AI workflows.

Security Assessment
Overall Risk: Medium
The tool does not request dangerous system permissions or execute local shell commands, and the codebase was scanned for dangerous patterns with none found. However, it inherently makes external network requests to scrape TradingView. It also requires highly sensitive credentials (`TRADINGVIEW_COOKIE` and `TV_CLIENT_KEY`), which poses a risk if exposed, especially since it defaults to listening on `0.0.0.0` (publicly accessible). While it supports OAuth, improper deployment could expose your TradingView session to unauthorized users.

Quality Assessment
Overall Quality: Low to Moderate
The project is actively maintained, having received updates very recently. It is properly licensed under the standard MIT license. However, community visibility and trust are extremely low, indicated by only 5 GitHub stars. Being an early-stage project means it might contain unpatched bugs or undocumented behaviors.

Verdict
Use with caution—ensure you secure your API keys, bind the server to localhost unless deployment is strictly necessary, and be aware that using scraped data may violate TradingView's terms of service.
SUMMARY

A high-performance FastMCP server for programmatically scraping TradingView market data. The server provides unified endpoints for retrieving historical price data, computing technical indicators, and extracting market-relevant news. It is designed for automated research workflows, trading systems, and data-driven analytics pipelines.

README.md

TradingView MCP Server

FastMCP server for TradingView data with an authenticated SSE endpoint for remote clients.

This repository is configured for SSE-first deployment on Vercel.

Quick Start

git clone https://github.com/smitkunpara/tradingview-mcp.git
cd tradingview-mcp
uv sync
cp .env.example .env

Set required values in .env:

  • TRADINGVIEW_COOKIE
  • TV_CLIENT_KEY

Run Local SSE Server

export TV_CLIENT_KEY="your-client-key"
uv run tradingview-mcp-sse

Defaults:

  • Host: 0.0.0.0
  • Port: 8000
  • SSE endpoint: /sse
  • Health endpoint: /health

Optional overrides:

export MCP_HTTP_HOST="0.0.0.0"
export MCP_HTTP_PORT="8000"
export MCP_SSE_PATH="/sse"

Authentication headers accepted on SSE endpoint:

  • X-API-Key: <TV_CLIENT_KEY>
  • X-Client-Key: <TV_CLIENT_KEY>
  • Authorization: Bearer <TV_CLIENT_KEY>

Optional OAuth mode:

  • Set TV_OAUTH_JWKS_URL (and optional issuer/audience/scope settings) to validate JWT bearer tokens.
  • API key authentication remains available as fallback.

Smoke Test (Vercel)

uv run python scripts/vercel_sse_smoke_test.py --url https://tradingview-mcp.vercel.app --client-key "$TV_CLIENT_KEY"

Available Tools

Category Tools
Market Data get_historical_data, get_all_indicators
News get_news_headlines, get_news_content
Community get_ideas, get_minds
Options get_option_chain_greeks, get_option_chain_oi

Documentation

Guide Description
Configuration Reference Environment variables and runtime configuration
Deployment Guide SSE deployment on Vercel

License

MIT — see LICENSE.

Yorumlar (0)

Sonuc bulunamadi