Alternative · News & journalism
Polynews vs
SimpleFunctions.
Polynews transforms Polymarket odds into human-readable headlines — a news-consumption surface scoped to one venue, no API, no agent layer. SimpleFunctions operates at the layer above raw prices: causal-tree thesis system with auto-evaluation cycles, autonomous Portfolio Autopilot with a 7-gate risk cascade, computed indicators across 48K+ contracts on both Kalshi and Polymarket, and a 56-tool MCP server. Where Polynews is a reader, SimpleFunctions is a programmable world model for agents and researchers.
Verified 2026-04 · public sources only · live SF data from /calibration
Verdict
Pick the one that fits how
you actually work.
Choose SimpleFunctions if
You are building agents, autonomous trading systems, or research pipelines that need more than news headlines — calibrated probabilities with public Brier scores, causal-tree thesis modelling with automated evaluation cycles, regime classification across the full 48K-contract universe on both Kalshi and Polymarket, computed indicators (implied yield, cliff risk, liquidity availability score), and a 56-tool MCP server that integrates into Claude Code or Cursor in one line.
Choose Polynews if
You want to follow prediction markets as a news reader — Polynews presents Polymarket odds as live headlines in a clean dark-mode interface without requiring API keys, code, or any setup. It is purpose-built for passive consumption, not programmatic access.
Polynews is a Polymarket news reader. SimpleFunctions is an agent-first API covering both Kalshi and Polymarket, with thesis system, autopilot, and MCP. Different surfaces, different audiences.
At a glance
Three things that
actually differ.
Everything Polynews gives you — live Polymarket odds surfaced as readable news — SimpleFunctions also gives you, with normalised prices from both Kalshi and Polymarket accessible via API, CLI, or MCP.
On top of that, SF ships a causal-tree thesis system, autonomous Portfolio Autopilot (1M-context LLM, 7-gate risk cascade), computed indicators across 48K+ contracts, and 56 MCP tools that no current PM data product exposes.
SF also publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days — letting you verify model accuracy independently rather than taking accuracy claims on faith.
Side by side
10 dimensions · verified 2026-04SimpleFunctionsKalshi and Polymarket normalised together, 48K+ active contracts indexed under a unified schema.
PolynewsPolymarket only — Kalshi is not covered.
SimpleFunctionsTrade ideas with conviction and catalyst at /api/public/ideas; no dedicated news-headline UI.
PolynewsCore product — real-time news headlines synthesized from Polymarket odds with no editorial overlay.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimate.
PolynewsNot in scope — Polynews is a news product, not an orderbook viewer.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label across 48K+ contracts at /screen.
PolynewsNot in scope.
SimpleFunctionsPOST /api/thesis/create decomposes a thesis into a causal tree, propagates probabilities, scans for edges, and runs an automated evaluation heartbeat.
PolynewsNot in scope.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade before any execution.
PolynewsNot in scope.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, and any MCP client.
PolynewsNo MCP server published.
SimpleFunctionsLive Brier scores at /api/calibration by venue, category, and price bucket — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days.
PolynewsNot published.
SimpleFunctionsFull REST API, 60+ CLI commands (npm i -g @spfunctions/cli), and MCP server — all accessible without authentication for reads.
PolynewsNo public API; web UI only.
SimpleFunctionsPublic REST, MCP, and CLI reads require no authentication. Thesis and intent execution: free up to 15M tokens, then pay-per-token.
PolynewsPricing not publicly specified.
Methodology
Verified 2026-04 from public sources only — Polynews's documentation, public website, and publicly observable behaviour. We never claim non-public information about Polynews's internals. SimpleFunctions claims on this page are computed live from /api/calibration, /api/public/cross-venue/pairs, and /api/public/markets — you can re-verify them yourself with curl.
Use cases
Same data, different
best fit per scenario.
Scenario 01
Building an AI agent that needs to query, reason over, and act on prediction market data programmatically.
SimpleFunctions · best fit
SimpleFunctions exposes 56 MCP tools, a full REST API, and a CLI — all without authentication for reads. An agent can fetch normalised prices, inspect orderbook depth, run thesis decomposition, and read calibration scores in a single session via the MCP server.
Polynews
Polynews has no public API. An agent cannot query it programmatically — the product is a web interface for human readers.
Scenario 02
Following prediction markets as a casual news reader who wants to understand what the market implies about current events.
SimpleFunctions
SimpleFunctions is built for programmatic access. It has no dedicated news-headline UI; a non-technical reader would need to work through the API or CLI to extract narrative context.
Polynews · best fit
Polynews is the better fit here. Its core product is a clean, dark-mode news interface that turns Polymarket odds into live headlines — no code, no API keys, no setup required.
Scenario 03
Decomposing a complex geopolitical or macro thesis into tradeable sub-claims across Kalshi and Polymarket.
SimpleFunctions · best fit
POST /api/thesis/create accepts a plain-language claim, decomposes it into a causal tree, maps each node to live contracts on both venues, and runs an automated evaluation heartbeat — news scan, price refresh, LLM evaluation, confidence update. No competitor exposes this workflow.
Polynews
Polynews surfaces headlines from Polymarket odds but does not offer thesis decomposition, causal modelling, or cross-venue scanning.
Scenario 04
Scanning for cross-venue arbitrage opportunities between Kalshi and Polymarket on matched contract pairs.
SimpleFunctions · best fit
Cross-venue matched pairs are available at /api/public/cross-venue/pairs?preset=arb, normalised to a common schema. Orderbook depth and liquidity availability scores are co-located for each pair.
Polynews
Polynews covers Polymarket only and has no cross-venue or arbitrage tooling.
Live data
The SimpleFunctions claims on this page are not marketing copy. Brier scores, market counts, and cross-venue pair counts are computed live from /calibration, /screen, and /api/public/cross-venue/pairs. All public, all free, all CC-BY-4.0.
FAQ
What does Polynews do?+
Polynews is a news-reading interface that ingests Polymarket odds and presents them as live, human-readable headlines. There is no editorial layer — the platform surfaces what the market implies without adding analyst commentary. It is scoped to Polymarket, designed for passive consumption, and has no public API or programmatic access layer. The interface features a dark-mode UI and a planned global visualization map.
Does Polynews have a public API?+
Based on publicly observable information, Polynews does not publish a REST API. The product is a web interface for reading headlines. If you need programmatic access to Polymarket data — or Kalshi data — SimpleFunctions exposes both venues through a REST API, a 60+ command CLI, and a 56-tool MCP server, all without requiring authentication for read operations.
How does SimpleFunctions' thesis system work?+
POST /api/thesis/create accepts a plain-language claim — for example, "The ECB will cut rates before July." The system decomposes it into a causal tree of testable sub-claims, maps each to tradeable contracts on Kalshi and Polymarket, propagates implied probabilities up the tree, and runs an automated evaluation heartbeat: news scan, price refresh, milestone check, LLM evaluation, and confidence update. You can inject new signals at any time via /api/thesis/{id}/signal. Public theses are forkable.
Can I use SimpleFunctions for both Kalshi and Polymarket?+
Yes. SimpleFunctions normalises prices across Kalshi and Polymarket into a unified schema — 48K+ active contracts indexed. Cross-venue arbitrage pairs are available at /api/public/cross-venue/pairs?preset=arb. Polynews covers Polymarket only; if Kalshi coverage matters to your workflow, it is not available through Polynews.
What is Portfolio Autopilot?+
Portfolio Autopilot is SimpleFunctions' autonomous trading agent. It uses a 1M-context LLM, 13 data sources, and a 7-gate risk cascade — including a kill switch, position limits, a drawdown gate, and a regime check — before placing any execution. It is designed for researchers and systematic traders who want agent-driven position management rather than manual order entry. Polynews does not offer any trading or execution layer.
How do I add SimpleFunctions to Claude Code or Cursor?+
Run claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. That registers 56 tools covering markets, orderbook, thesis, calibration, and world snapshot. No API key is required for read access. From that point, any MCP-compatible AI client can query prediction market data, run thesis decomposition, and inspect live calibration scores within the same session context.
Does SimpleFunctions publish accuracy benchmarks?+
/api/calibration returns live Brier scores segmented by venue, category, and price bucket. Current figures: Kalshi 0.20, Polymarket 0.12, computed on T-24h prices over the past 90 days. Most prediction market products claim accuracy; SimpleFunctions publishes a verifiable endpoint so you can re-check the numbers yourself with a curl request at any time.
Start for free.
Public endpoints are free for normal usage and rate-limited for reliability. Authenticated endpoints are free up to 15M tokens, then pay per token. No credit card to start.