Sharpe Terminal vs
SimpleFunctions.

Sharpe Terminal is a trader-facing UI cockpit — a professional dashboard for monitoring and managing Polymarket and Kalshi positions. SimpleFunctions is the API, CLI, and MCP layer beneath such tools: programmatic access, a causal thesis system, autonomous portfolio autopilot, computed indicators, and a 56-tool MCP server. They serve different buyers: Sharpe Terminal targets human traders; SimpleFunctions targets builders, researchers, and AI agents that need to consume or act on prediction-market data programmatically.

Based on publicly available information as of 2026-04, Sharpe Terminal does not list a public REST or HTTP API for programmatic access. It is positioned as a UI-first terminal product. SimpleFunctions, by contrast, is built API-first: every capability — prices, orderbook depth, cross-venue pairs, thesis creation, calibration, world snapshot — is available via REST, CLI, or MCP with no special agreement required for read operations.

POST /api/thesis/create with any natural-language claim. The system decomposes it into a causal tree of testable sub-claims, maps each node to matching Kalshi and Polymarket contracts, propagates implied probabilities up and down the chain, and starts an evaluation heartbeat — recurring cycles of news scan, price refresh, milestone check, LLM evaluation, and confidence update. You can inject external signals at any point via /api/thesis/{id}/signal. Public theses are forkable. No comparable product exposes this workflow.

Portfolio Autopilot is SF's autonomous trading agent. It uses a 1M-context LLM drawing on 13 data sources — market prices, calibration scores, thesis confidence, regime labels, and more. Before any execution, a 7-gate risk cascade runs: kill switch check, position-limit verification, drawdown gate, regime classification, liquidity score, overround filter, and a final LLM conviction threshold. All gates must pass. The result is a system that can run unattended without relying on a single threshold rule as the only safety layer.

Yes. Run: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. That registers 56 tools in one step — covering price lookup, orderbook depth, cross-venue arbitrage pairs, thesis creation and signal injection, calibration scores, world snapshot, and trade ideas. Any MCP-compatible client works: Claude Code, Cursor, or a custom agent loop. Sharpe Terminal does not list a public MCP server.

Yes. GET /api/calibration returns SF's own Brier scores broken out by venue, market category, and price bucket, computed on the past 90 days of resolved contracts. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h prices. Sharpe Terminal does not publicly publish calibration or Brier score data. Auditing your data provider's accuracy before deploying capital is a basic risk-management step; SF makes it a verifiable public endpoint rather than a marketing claim.

Sharpe Terminal. It is explicitly designed as a Bloomberg-style cockpit for professional traders monitoring Polymarket and Kalshi — live positions, portfolio view, P&L tracking, and a UI built around the manual trading workflow. SimpleFunctions does not ship a pre-built trading UI. SF's value is the programmatic and agent layer: if you want to build automation or feed data into an AI pipeline, SF is the tool; if you want to trade manually from a polished interface, Sharpe Terminal is the stated product fit.

SF pre-computes six indicator classes across 48K+ active contracts: implied yield (annualised return on a YES position held to settlement), cliff risk index (probability mass concentrated near expiry that can gap to zero), liquidity availability score (estimated fill depth relative to position size), event overround (total market probability minus 1.0), tau-days (time to settlement), and regime label (adverse-selection classification). These are available at /screen and via the MCP server. A raw price feed returns prices; SF returns interpretive context on top of them.