AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Data Processing/
tradingview-mcp
tradingview-mcp logo

tradingview-mcp

Active·★ 5.1k·MIT·Updated 2026-10-24

TradingView MCP presents itself as an AI trading intelligence framework: a multi-agent MCP server that turns Claude, or any MCP client, into a financial analysis desk. It splits trading analysis into three roles: a Technical Analyst that evaluates price action with a Bollinger Band rating from -3 to +3, RSI and MACD; a Sentiment and Momentum Analyst that looks at recent momentum, MACD crossovers and RSI trends; and a Risk Manager that assesses volatility through Bollinger Band width and mean-reversion risk against SMA20 and EMA200. The agents debate and output one decision (strong buy, buy, hold, sell or strong sell) with a confidence level.

The tools include multi_agent_analysis for the full three-agent debate, coin_analysis for a raw technical deep dive, real-time screening (top gainers and losers, Bollinger Band squeeze scans, rating filters) and candlestick pattern scans such as consecutive candles and multi-timeframe patterns, across crypto exchanges and stocks. Setup takes about five minutes through Claude Desktop. The README carries a disclaimer: the framework is for research, performance varies with the LLM, market conditions and parameters, and it is not financial, investment or trading advice. The code is MIT licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
MIT
Latest release
No GitHub releases
Last commit
2026-10-16
Contributors
23
Forks
1,020
Open issues and PRs
9
First published
2025-08-08

Source: GitHub, npm and PyPI public APIs.

#claude-desktop#cryptocurrency#mcp-server#mcp-servers#mcp-tools#stock-market#trading-mcp#trading-strategies
$ Install
$ git clone https://github.com/atilaahmettaner/tradingview-mcp.git && cd tradingview-mcp && uv sync
↗ Visit site★ GitHub
01

Features

01Multi-Agent Architecture for specialized financial analysis (Technical, Sentiment, Risk).
02Consensus-driven trading decisions with calculated confidence levels.
03Real-time market screening for top gainers/losers and specific patterns.
04Advanced pattern recognition across multiple timeframes.
05Zero API keys required for market data.
02

Why choose it

+Combines technical, sentiment and risk views in one multi-agent analysis that outputs a decision with a confidence level.
+Real-time screening tools: top gainers and losers, Bollinger Band squeeze scans and rating filters across exchanges.
+Candlestick pattern scans, including consecutive candles and multi-timeframe patterns.
+Short Claude Desktop setup, MIT licensed, with a clear research-only disclaimer.
03

Trade-offs

!The README says it is for research only and not financial or investment advice, and results depend on the LLM, market conditions and parameters.
!The analysis rests on a few technical indicators (Bollinger Bands, RSI, MACD, moving averages), so it does not cover fundamentals.
!The "debate" between agents is generated by an LLM, so decisions are not backtested guarantees, and acting on them risks real money.
05

Maintenance check

ActiveChecked: 2026-10-24
Last commit
2026-10-24
Commits, last 90 days
50
Releases, last 90 days
0
Latest release
—
Open issues
6
Recent issues with at least one comment
6/13
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 6, 0, 0, 14, 4, 0, 0, 0, 0, 8, 7, 7

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #76 Error contract is half-migrated: 5 tools return structured envelopes, ~95 return sites still return strings3 comments · 2026-07-10
  • #101 Heads-up: a copy of this repo is distributing a malicious npm dependency1 comments · 2026-09-28
  • #93 MCP spec conformance: 7 requirement(s) violated (via @hasmcp/mcp-spec-test) — spec 2026-07-280 comments · 2026-08-24
  • #87 [FEATURE] Range intervals0 comments · 2026-08-08

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You want market screening (top gainers and losers, Bollinger Band squeezes, rating filters) inside Claude or another MCP client.
  • You want a technical view that combines three agent roles into one rating with a confidence level.
  • You want analysis only: the README describes research, not placing orders.
Look elsewhere if
  • You need fundamentals: the analysis rests on Bollinger Bands, RSI, MACD and moving averages.
  • You want backtested signals: the agents' debate is generated by an LLM, not a tested strategy.
  • You need order execution: use a broker server instead.
06

How it differs

FinnewsHunter logovs FinnewsHunter★ 1.5k

FinnewsHunter analyses Chinese financial news for A-shares. TradingView MCP works from price indicators across exchanges.

Full comparison →
07

Compatibility

Claude Desktop
Recommended AI Client
Verified via docs
Model Context Protocol
Native MCP Server
Verified via docs
Python
Runtime Environment (3.10+)
Verified via docs
macOS
Compatible OS
Verified via docs
Windows
Compatible OS
Verified via docs
Linux
Compatible OS
Verified via docs
08

Quick start

1
$ git clone https://github.com/atilaahmettaner/tradingview-mcp.git
2
$ cd tradingview-mcp
3
$ uv sync
09

Use cases

↳Execute multi-agent analyses on assets (e.g., stocks, crypto) across various exchanges and timeframes.
↳Rapidly identify top-performing or declining assets based on real-time market conditions.
↳Scan for specific technical patterns, such as Bollinger Band squeezes or consecutive bullish/bearish candles.
10

Alternatives

⚡Top VS:
VSFinnewsHunter★1.5k→VSmcp★435→VSslackdump★2.8k→VStrainingpeaks-mcp★185→
FinnewsHunter logo
FinnewsHunter★ 1.5k
FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.
VSCompare→
mcp logo
mcp★ 435
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.
VSCompare→
slackdump logo
slackdump★ 2.8k
Save or export your private and public Slack messages, threads, files, and users locally without admin privileges.
VSCompare→
trainingpeaks-mcp logo
trainingpeaks-mcp★ 185
TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language.
VSCompare→
ddgs logo
ddgs★ 3.0k
A metasearch library that aggregates results from diverse web search services
VSCompare→
mcp-claude-spotify logo
mcp-claude-spotify★ 53
An integration that allows Claude Desktop to interact with Spotify using the Model Context Protocol (MCP).
VSCompare→
strava-mcp logo
strava-mcp★ 19
Personal MCP server for Strava with OAuth authentication, beautiful dashboard, and personal MCP URLs for AI assistants
VSCompare→
fathom-mcp-server logo
fathom-mcp-server★ 16
An mcp server built for fathom and works in claude.
VSCompare→
See all alternatives →

Featured in these lists

  • Open-Source AI Trading and Finance Tools

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
atilaahmettaner /
tradingview-mcp
↗

MCP server that screens markets and runs a three-agent technical analysis debate

5.1k1.0kMIT
Last commit1d ago
StatusActive
CategoryData Processing
Contributors23
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.