What is tradingview-mcp-py AGENTS.md?

Repository instructions for a Python MCP server that provides stock-analysis tools through the Model Context Protocol, a standard way for AI clients to call tools.

Orienting contributors who need to run, inspect, or test the TradingView, finance, market-data, backtesting, and risk-analysis server.

They explain the project’s entry point, dependencies, data sources, supported protocol version, and tests so an agent can work in the repository correctly.

How CenblueOne/tradingview-mcp-py configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to CenblueOne/tradingview-mcp-py. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CenblueOne/tradingview-mcp-py/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/CenblueOne/tradingview-mcp-py

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cenblueone/tradingview-mcp-py/agents-md.svg)](https://agentmods.dev/instructions/cenblueone/tradingview-mcp-py/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cenblueone/tradingview-mcp-py/agents-md"><img src="https://agentmods.dev/badge/instructions/cenblueone/tradingview-mcp-py/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,238 This file is loaded in full into every session.

When invoked 1,238 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01238	$0.01238
Opus 5	$0.00619	$0.00619
Sonnet 5	$0.00248	$0.00248
Haiku 4.5	$0.00124	$0.00124

Measured 7d ago against content hash 7c36767e1dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tradingview-mcp-py AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — tradingview-mcp-py

This file is the authoritative orientation for AI agents (Claude Code, Hermes, opencode, Cursor, Grok, etc.) working with this repository.

What this is

A Model Context Protocol (MCP) stdio server exposing 30 stock-analysis tools: TradingView Screener technical analysis, Yahoo Finance prices/history, Indonesia Stock Exchange (IDX/BEI) helpers, backtesting, news sentiment, and trade/risk math.

No TradingView Desktop / Chrome needed — headless / VPS-compatible.
No API keys required — all data comes from public endpoints.
MCP 1.x only — server uses mcp.server.fastmcp.FastMCP; mcp 2.x breaks it.

Entry points

File	Purpose
`server.py`	THE MCP server — single entry point. Run: `<venv-python> server.py` (stdio JSON-RPC on stdin)
`services/`	Pure-Python analysis modules (`indicators.py` stock score/Fibonacci, `backtest_service.py`, `proxy_manager.py` optional Webshare proxy)
`tests/`	pytest suite (13 tests, offline)
`install.bat`	Windows one-time installer (creates `venv/`, installs pinned deps)
`main.py`	Removed — it was a stub; `server.py` is the real entry point

How to run

python3 -m venv venv
venv/bin/pip install -r requirements.txt   # Windows: venv\Scripts\pip ...
venv/bin/python server.py                  # waits for MCP JSON-RPC on stdin

Windows: command: <REPO_DIR>/venv/Scripts/python.exe, args: ["<REPO_DIR>/server.py"]
Linux/macOS: command: <REPO_DIR>/venv/bin/python, args: ["<REPO_DIR>/server.py"]

How to test

venv/bin/pip install pytest
venv/bin/python -m pytest        # 13 passed, no network needed

conftest.py inserts repo root into sys.path so import server works.

Tool inventory (30)

Technical Analysis (6): get_ta, get_ta_bulk, get_mtf, get_candlestick, get_bollinger, screen_stocks — require exchange + screener (IDX → exchange="IDX", screener="indonesia")
Yahoo Finance (4): yf_price, get_market_cap, market_snapshot, yf_ohlcv
IDX/BEI (11): idx_price, idx_ta, idx_mtf, idx_market, idx_screener, idx_signals, idx_backtest, idx_deep_analysis, morning_brief_idx, combined_analysis, financial_news — take bare codes (BBRI), never BBRI.JK
Backtesting (3): backtest_strategy, compare_strategies, walk_forward_backtest — strategies: rsi|ema_cross|bollinger|macd|supertrend|donchian|rsi_pullback|triple_ema|keltner_breakout
Sentiment (1): market_sentiment — naive keyword scoring of Yahoo news
Trade utilities (5): position_size, rr_calc, journal_add, journal_list (local JSONL at ~/.tradingview-sessions/journal.jsonl), market_sessions (WIB/UTC+7)

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 83 lines · 1,238 tokens per session scan A 7c36767e1dbf

Subscribe to this mod's changes

tradingview-mcp-py AGENTS.md is an instructions file published in the GitHub repository CenblueOne/tradingview-mcp-py (0 stars, last pushed 28d ago), licensed MIT. It adds 1,238 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

tradingview-mcp-py: Instructions file for Codex