ai.marketintell/marketintell
Description and use
AI analyst desk for stocks, options & crypto with sourced trade setups and a public accuracy record.
Compatible agents
- Claude Desktop
- Claude Code
- Hermes
- Codex CLI
Capabilities
MarketIntell — 30-day accuracy: Inline UI rendered alongside the signal_performance tool. Shows the rolling 30-day win rate by trade timeframe (15m/1H/4H) plus an overall rollup so users can audit signal quality without leaving the chat.
MarketIntell — Alpha signals feed: Inline UI rendered alongside the alpha_signals tool. Renders the recent signals as a compact, scroll-friendly list with direction, impact, and timestamp.
alpha_signals: Fetch recent alpha signals — automated market intelligence. Crypto signals every ~10 min; equities (Beta) every ~30 min during US market hours. Filter by domain to narrow.
billing_status: Return the authenticated key's plan, daily quota usage, monthly LLM-cost-cents, and cap. Mirrors GET /v1/billing/status.
chat: Run a query through MarketIntell's brain (auto-routes to T1 fast agent or T2 CoT pipeline based on intent). Returns synthesized analysis with citations and trade setup when relevant.
chat_deep: Run a query through MarketIntell's T3 supervisor — parallel specialists across technical/derivatives/macro/social/onchain/etc. plus synthesis. Slower (~25-40s) and costlier than chat. Pro tier only.
execute_approve_intent: Approve a pending trade intent and place the order at the broker. Returns the executed_order audit row. Requires trade scope.
execute_list_intents: List the caller's recent trade intents (pending, executed, rejected). Requires trade scope.
execute_propose_intent: Propose a trade intent to the user's connected broker. Writes a pending row the user reviews + approves. Requires trade scope. Use this when an agent wants to act on a signal without placing the order itself.
execute_read_portfolio: Read the caller's connected broker account snapshot — equity, cash, buying power, open positions. Requires trade scope.
health: MarketIntell system health — uptime, cache stats, memory, provider circuit-breaker states.
portfolio_analyze: Compute PnL + risk assessment for a portfolio you own. Returns per-holding pnl, risk_assessment, and top_risks.
portfolio_create: Create a new portfolio for the authenticated key. Holdings are token symbol + amount (+ optional entry_price and notes).
portfolio_list: List all portfolios owned by the authenticated key. Returns id, name, holdings, timestamps.
register: Step 2 of MCP self-signup. Submit the challenge id + solved nonce to provision a fresh Free-tier API key. The key is shown ONCE — store it. Pro upgrades go through Stripe checkout; this tool only issues Free keys.
register_challenge: Step 1 of MCP self-signup. Returns a proof-of-work challenge. Solve locally (find a nonce whose sha256 has the required leading zero hex chars), then call register with { challenge_id, nonce, name }.
screener: Token screening — find trending tokens, top gainers, and top losers. Use this to discover what's moving in the market right now.
sessions_list: List the authenticated key's recent chat sessions. Useful to resume prior conversations.
signal_performance: Realized signal accuracy — rolling 30-day win rate over CLOSED trade signals, where a win is a real take-profit / in-profit expiry (net positive after fees & leverage) and a loss is a real stop-loss / losing expiry. Win-rate is over resolved signals only; flat (break-even) and cancelled/no-fill/ambiguous signals are reported but excluded from the rate. Broken down by timeframe and direction.
sse: Transport declared by the upstream MCP registry.
streamable-http: Transport declared by the upstream MCP registry.
Installation
npx -y [email protected]
Limitations and review notes
Discovered metadata only; install commands are stored for review but never executed by AtlasRepo.
- Source: Official MCP Registry
- Category: mcp
- Record date: 2026-08-28T08:31:12.352Z