Trading Factors for Claude, Cursor, ChatGPT & agents

TradeLoop's canonical Factors catalog, served over MCP — the single source of truth (one JSON file) that the desktop FactorsLibrary AND any MCP caller share

curl -fsSL https://tradeloop.top/install.sh | sh

What it does

TradeLoop's canonical Factors catalog, served over MCP — the single source of truth (one JSON file) that the desktop FactorsLibrary AND any MCP caller share. A Factor is one trading signal/input TradeLoop reasons over: technicals (moving-average stack, RSI, MACD, ADX, Bollinger, TTM squeeze…), the analyze synthesis (confluence score, regime, named setups, divergences, relative strength, higher-timeframe alignment), plus fundamentals, macro, crypto, options and positioning context. Each factor carries a `source` saying where its value really comes from — `analyze` (computed live by indicators.analyze), `scanner` (the scanner/monitor, e.g. relative volume), or a data skill (`cot`, `fred`, `finnhub`, `edgar`, `coingecko`, `options`, `x-search`) — and a `paid` flag when it needs a paid data tier (e.g. Polygon Options). So callers know exactly which factors are live in the deep-read vs which need another skill. list() returns the whole catalog (it's small); get(id) returns one factor; categories() lists the families present. Pure local content — no API keys, no network.

The Trading Factors skill is one of 40+ pre-wired TradeLoop integrations that any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Codex CLI, and ChatGPT desktop — can call out of the box. You don't configure MCP servers or copy API keys into a JSON file; the TradeLoop daemon discovers the skill at startup and exposes its tools to whichever AI client is running.

Sample prompts

Once TradeLoop is installed and Trading Factors is connected, ask your agent something like:

• “List from Trading Factors.”
• “Get from Trading Factors.”
• “Categories from Trading Factors.”

Tools available (3)

• factors__list

  [TradeLoop · Trading Factors] Lean factor catalog for discovery — every factor's id, name, category, icon, blurb, source (and paid when true), WITHOUT the long detail/formula/reads fields (the full catalog is ~87K chars and would blow the tool-output budget). Call get(id) for one factor in full.

• factors__get

  Return one factor object in full (id, name, category, icon, blurb, reads, source, and paid when true). Use `source` to know where the value comes from before relying on it — e.g. analyze = computed live by indicators.analyze, scanner = the scanner/monitor, fred/finnhub/edgar/coingecko/cot/options/x-search = fetch from

• factors__categories

  List the distinct factor categories present, in reading order: Trend, Momentum, Volatility, Flow, Relative strength, Setups, Fundamentals, Macro, Crypto, Options, Context. Browse the catalog by family.

How to connect

Trading Factors is a no-auth skill — there's nothing to connect. Once TradeLoop is installed, your agent can call its tools immediately.

1. Run curl -fsSL https://tradeloop.top/install.sh | sh on macOS / Linux (or the PowerShell command on Windows).
2. Run tradeloop login to create your account and a device-bound encryption key.
3. Run tradeloop update to sync the skill + credentials to every installed AI client.

Pricing

Free at every TradeLoop tier. Connect your account once at /connect; the OAuth or API-key credential stays encrypted on your machine and syncs to your other devices via the TradeLoop vault.

See the full TradeLoop pricing breakdown — Free $0/mo, Pro $29/mo, Ultra $99/mo — on the homepage.