Trading Playbooks for Claude, Cursor, ChatGPT & agents

TradeLoop's trading-skill playbook library, served over MCP — the same ~22 opinionated, step-by-step playbooks the desktop app ships (vet a breakout, enter on a trend pullback, fade the extreme, po...

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

What it does

TradeLoop's trading-skill playbook library, served over MCP — the same ~22 opinionated, step-by-step playbooks the desktop app ships (vet a breakout, enter on a trend pullback, fade the extreme, position sizing & stops, scan for squeezes, pre-market / weekend prep, journaling that compounds…). A companion copy-paste PROMPT catalog (prompts_list / prompts_get) spans 77 ready-made prompts from one-line quotes to deep single-name work — including three-scenario intrinsic valuation and a simple DCF (bull/base/bear fair value), full institutional-style equity research reports, quality/moat and GARP checks, peer comparison, and monitoring loops. list() returns lean metadata for discovery; get(id) returns the full markdown body. Each playbook declares the Factors it uses (the `factors` field — ids from the indicators.analyze / FactorsLibrary catalog) so a caller can preload exactly the right numbers (e.g. via indicators.analyze) before working the checklist. Pure local content — no API keys, no network.

The Trading Playbooks 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 Playbooks is connected, ask your agent something like:

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

Tools available (6)

• playbooks__list

  List every playbook's metadata — id, name, description, category, icon, and the factors it uses — with NO body (lean, for discovery). Call this first to find the playbook you want, then get(id) for the full text.

• playbooks__get

  Return one playbook in full: its metadata plus the markdown body (the checklist / routine). The `factors` array lists the indicators.analyze factor ids the playbook leans on, so you can preload those numbers before working through it. Unknown id returns an error with a hint to call list().

• playbooks__categories

  List the distinct categories across the playbook library (e.g. Setups, Risk, Screening, Research, Routines, Process) so you can browse by theme.

• playbooks__prepare

  ONE-CALL PRELOAD: returns a playbook PLUS its declared factors computed for a symbol. Runs indicators.analyze once (covering every analyze-sourced factor) and returns that read under `analyze`; non-analyze factors (COT / macro / options / fundamentals) are listed under `other_factors` with the skill that provides each,

• playbooks__prompts_list

  [TradeLoop · Trading Playbooks] Copy-paste PROMPT catalog, lean (id, tier 1-4, title, one-liner, tools) — ready-made prompts a user pastes into Claude/Cursor/ChatGPT. Tiers: 1 Starter (one tool, one question), 2 Daily (multi-tool routines), 3 Pro (setups & risk), 4 Autopilot (monitor rules + recurring loops). Filter by

• playbooks__prompts_get

  [TradeLoop · Trading Playbooks] One copy-paste prompt in full: the ready-to-paste text (self-contained natural language with [PLACEHOLDER] tokens + defaults), the linked playbook id for the deeper 'why', and the expected output shape.

How to connect

Trading Playbooks 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.