tradingview-mcp-codex
A Codex-first MCP server that bridges TradingView Desktop via Chrome DevTools Protocol, enabling launch, symbol/timeframe control, and health checks from Codex CLI.
README
tradingview-mcp-codex
Codex-first TradingView MCP bridge for TradingView Desktop via Chrome DevTools Protocol.
This project adapts ideas and workflows from tradesdontlie/tradingview-mcp for Codex:
- same local TradingView Desktop CDP model
- Codex-friendly MCP setup
- thin shared core for CLI and MCP tools
- clearer Codex install and workflow docs
Status
Current scaffold ships working base pieces:
- CLI:
tvx launchtvx statustvx symbol <SYMBOL>tvx timeframe <TF>
- MCP tools:
tvx_launchtvx_health_checktvx_set_symboltvx_set_timeframetvx_chart_state
It does not yet expose full upstream feature parity. Use vendor/tradingview-mcp as feature reference while growing this Codex-first server.
Goals
- keep MCP server small and readable
- share logic across CLI and MCP tools
- document Codex setup better than Claude-only examples
- make feature parity work incremental and explicit
Prerequisites
- Node.js 18+
- TradingView Desktop installed
- valid TradingView subscription for your own local app usage
- Codex CLI with MCP support
Install
npm install
Run locally
Start MCP server:
npm start
Use CLI:
npm run launch
npm run health
node src/cli/index.js symbol BBCA
node src/cli/index.js timeframe 1
Add to Codex
Register global MCP entry:
codex mcp add tradingview-codex -- node /Users/you/Projects/tradingview-mcp-codex/src/server.js
Check config:
codex mcp list
codex mcp get tradingview-codex
Restart Codex session after adding server so tool list refreshes.
Quick verification
- Launch TradingView with CDP:
npm run launch
- Check CLI connection:
npm run health
- In fresh Codex session, call MCP tool:
tvx_health_check
Documentation
- Codex setup:
docs/CODEX_SETUP.md - Feature mapping from upstream reference:
docs/FEATURE_PARITY.md - Skill port plan:
docs/SKILLS.md
Reference source
Primary reference used while shaping this project:
- upstream repo:
vendor/tradingview-mcp/README.md - upstream setup:
vendor/tradingview-mcp/SETUP_GUIDE.md - upstream Claude workflows:
vendor/tradingview-mcp/CLAUDE.md
Upstream project:
- https://github.com/tradesdontlie/tradingview-mcp
Design notes
- keep shared TradingView logic in
src/core - keep CLI wrappers thin in
src/cli - keep MCP wrappers thin in
src/tools - prefer explicit, JSON-friendly outputs
- port upstream features one workflow at time instead of blind copy
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.