What is tradingview-mcp CLAUDE.md?

A project guide that gives Claude Code the current architecture, files, tools, setup notes, and design rules for a TradingView market-data project.

Use it to resume development, locate important code, understand the available market-analysis tools, and follow the project’s backtesting constraints.

It prevents each new coding session from starting without the project’s background or repeating work. It also clarifies that the backtests use local price files rather than live broker connections.

How btanaji/tradingview-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to btanaji/tradingview-mcp. 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/btanaji/tradingview-mcp/main/CLAUDE.md

Clone the repo

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

Made for: Claude Code.

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/btanaji/tradingview-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/btanaji/tradingview-mcp/claude-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/btanaji/tradingview-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/btanaji/tradingview-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,707 This file is loaded in full into every session.

When invoked 5,707 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	$0.05707	$0.05707
Opus 5	$0.02854	$0.02854
Sonnet 5	$0.01141	$0.01141
Haiku 4.5	$0.00571	$0.00571

Measured 8d ago against content hash 8464421e2231, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tradingview-mcp CLAUDE.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 8d 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.

CLAUDE.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tradingview-mcp-custom — Project State

This file is auto-loaded by Claude Code at the start of any session rooted here. It summarizes the current architecture, what's been built, known gaps, and where a follow-up session should pick up. A companion PDF (TradingView_MCP_Session_Knowledge.pdf, delivered to the user separately) covers the ICT/SMC concepts and case studies in more depth with diagrams — this file is the engineering/state summary.

Architecture: 3 independent backtest engines, one shared cost/metrics layer

All strategy files are .txt. All engines read local CSV OHLCV data only — no live network/broker calls (config: TV_MCP_CSV_DATA_DIR, default ~/Claude/data; symbol currently used throughout: XAUUSD, data from 2020-01-02 to present across M1/M5/M15/M30/H1/H4/D1).

Generic proxy (custom_strategy_service.py) — swing-pivot zone detector (_find_swings), used only when a .txt file's NAME doesn't match the ICT registry.
ICT registry (ict_strategies.py + ict_detectors.py) — 26 hand-coded Python zone providers (18 original + 8 added this session: CRT_Turtle_Soup, HTF_POI_Stop_Raid, FVG_Inducement, Full_Confluence, Consolidation_Box, IFVG_Reversal), matched by file NAME via STRATEGY_REGISTRY. Files live in ~/Claude/strategies/.
pine_lite (pine_lite/ + pine_strategy_service.py) — a CONSTRAINED Pine Script subset transpiler (tokenizer → parser → validator → evaluator). Files live in ~/Claude/pine_strategies/ (config: TV_MCP_PINE_STRATEGIES_DIR). NOT a full Pine interpreter — no request.security, for/while, var/varip, arrays, user-defined types/methods, native strategy.entry/exit. The validator collects EVERY unsupported construct before any evaluation is attempted — never partial/silent execution. See pine_lite/__init__.py for the exact supported subset.

Shared foundation: backtest_service.py's _apply_costs/_calc_metrics/ _buy_and_hold_return — same metrics shape from every tool.

Read the full file on GitHub · 328 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.

8d ago First seen · 328 lines · 5,707 tokens per session scan A 8464421e2231

Subscribe to this mod's changes

tradingview-mcp CLAUDE.md is an instructions file published in the GitHub repository btanaji/tradingview-mcp (1 stars, last pushed 22d ago), licensed MIT. It adds 5,707 tokens to every session, about $0.0285 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: Instructions file for Claude Code