Alternative · Analytics aggregator
Parsec vs
SimpleFunctions.
Same Polymarket upstream. Parsec renders that data as a human-readable analytics dashboard with real-time visualizations and decision-support charts. SimpleFunctions ships the agent layer above it: a causal-tree thesis system that auto-evaluates on a news-and-price heartbeat, autonomous portfolio trading with a 7-gate risk cascade, computed indicators across 48K active contracts on both Kalshi and Polymarket, and a 56-tool MCP server that plugs into Claude Code or Cursor in one command.
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 a visualization layer — calibrated probabilities with public Brier scores, causal-tree thesis modelling with auto-evaluation cycles, regime classification across 48K contracts, computed indicators (implied yield, cliff risk, liquidity availability score, event overround), cross-venue coverage on both Kalshi and Polymarket, and a 56-tool MCP server that any AI coding assistant can consume directly.
Choose Parsec if
Parsec focuses on Polymarket analytics and decision-support visualizations for human traders who want a polished web dashboard. If your workflow is chart-driven and browser-first rather than API- or agent-first, Parsec is purpose-built for that audience.
Same Polymarket upstream. Parsec surfaces it as a human analytics dashboard; SimpleFunctions ships the agent layer: world model, theses, indicators, autopilot, MCP.
At a glance
Three things that
actually differ.
Everything Parsec gives you — real-time Polymarket prices, analytics data, and decision-support visualizations — SimpleFunctions also gives you, on the same Polymarket feed and extended to Kalshi across 48K+ active contracts.
On top of that, SF ships a causal-tree thesis system, an autonomous trading agent (Portfolio Autopilot, 1M-context LLM, 7-gate risk cascade), computed indicators across 48K contracts, and 56 MCP tools that no current PM analytics product exposes.
SF publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days — so you can audit its accuracy yourself before trusting it in a model or agent.
Side by side
9 dimensions · verified 2026-04SimpleFunctionsKalshi and Polymarket normalised, 48K+ active contracts indexed cross-venue.
ParsecPolymarket only, per public positioning and tagline.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns a bid/ask ladder with spread and slippage estimates.
ParsecOrderbook and spread data visible in the web dashboard; no public API endpoint documented.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, and regime label pre-computed across 48K contracts at /screen.
ParsecAnalytics and visualizations surface raw price and volume; pre-computed derived indicators are not described in public documentation.
SimpleFunctionsLive Brier scores at /api/calibration broken down by venue, category, and price bucket — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days.
ParsecNot published.
SimpleFunctionsPOST /api/thesis/create decomposes a natural-language sentence into a causal tree, maps sub-claims to open contracts, and runs a news-and-price evaluation heartbeat on schedule.
ParsecNot in scope; analytics surface existing market prices without thesis decomposition or automated evaluation cycles.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade — executes on Kalshi and Polymarket.
ParsecNot in scope; Parsec is a read-only analytics dashboard.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp — works with Claude Code, Cursor, any MCP client.
ParsecNo MCP server published.
SimpleFunctionsPublic REST API, 60-command CLI (npm i -g @spfunctions/cli), and MCP server — no auth required for reads.
ParsecWeb dashboard; no public REST API described in available documentation.
SimpleFunctionsPublic REST, MCP, and CLI reads require no auth. Thesis and intent execution free up to 15M tokens, then pay-per-token.
ParsecPricing not publicly documented in available sources.
Methodology
Verified 2026-04 from public sources only — Parsec's documentation, public website, and publicly observable behaviour. We never claim non-public information about Parsec'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 consume and reason over prediction market data programmatically.
SimpleFunctions · best fit
SF's 56-tool MCP server, /api/agent/world, and public REST endpoints are designed for machine consumption. Agents can query cross-venue prices, run thesis evaluations, and receive calibrated probability signals without a human in the loop.
Parsec
Parsec is a web dashboard optimized for human analysts. It does not publish an API for programmatic agent consumption based on available documentation.
Scenario 02
Monitoring Polymarket market sentiment through visual charts and analytics as a human trader.
SimpleFunctions
SF's primary surface is API-first. A human trader who wants polished visual analytics would need to build their own frontend on top of SF's data endpoints; SF does not ship a chart-driven dashboard.
Parsec · best fit
This is Parsec's core use case. Its web dashboard delivers real-time Polymarket analytics with decision-support visualizations designed for human consumption, and it is clearly purpose-built for this audience.
Scenario 03
Decomposing a complex geopolitical thesis into tradeable sub-claims across Kalshi and Polymarket.
SimpleFunctions · best fit
POST /api/thesis/create accepts a natural-language sentence, decomposes it into a causal tree, maps sub-claims to open contracts on both venues, and runs an evaluation heartbeat — news scan, price refresh, LLM evaluation, confidence update — on schedule.
Parsec
Parsec's analytics layer surfaces existing market prices but does not support thesis decomposition, causal modelling, or automated evaluation cycles.
Scenario 04
Auditing the accuracy of prediction market data before trusting it in a quantitative model.
SimpleFunctions · best fit
/api/calibration returns SF's own Brier scores by venue, category, and price bucket — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Accuracy is checkable with a single curl command.
Parsec
Parsec does not publish calibration data or Brier scores for the data it displays, so independent accuracy verification is not available.
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
How does SimpleFunctions compare to Parsec for Polymarket data?+
Both products expose Polymarket data, but at different layers. Parsec delivers a web dashboard with real-time analytics and decision-support visualizations aimed at human traders. SimpleFunctions exposes the same underlying data via a REST API, CLI, and 56-tool MCP server optimized for agents and developers — and extends coverage to Kalshi. SF also adds computed indicators (implied yield, cliff risk, liquidity availability score, event overround) and a causal thesis system that no analytics dashboard ships.
Does SimpleFunctions have a web dashboard like Parsec?+
SF's primary surfaces are API-first: public REST endpoints, a 60-command CLI, and an MCP server. The /screen page shows the full computed indicator universe across 48K contracts, but SF is not optimized for chart-driven human workflows. If your primary need is a browser-based analytics dashboard for Polymarket, Parsec is purpose-built for that use case.
What is SimpleFunctions' causal thesis system and how does it work?+
POST /api/thesis/create takes a natural-language sentence — for example, 'Fed will cut rates before June' — and decomposes it into a causal tree of testable sub-claims. Each sub-claim is matched to open contracts on Kalshi and Polymarket. An evaluation heartbeat then runs on schedule: news scan, price refresh, milestone check, LLM evaluation, and confidence update. External signals can be injected via /api/thesis/{id}/signal. Public theses are forkable by other users.
Does SimpleFunctions support autonomous trading?+
Yes. Portfolio Autopilot uses a 1M-context LLM reading 13 data sources and passes through a 7-gate risk cascade — kill switch, position limits, drawdown gate, regime check, and others — before any execution. It operates on both Kalshi and Polymarket. Parsec is a read-only analytics product and does not offer autonomous execution.
What is the MCP server and how do I connect it?+
Model Context Protocol lets AI coding assistants like Claude Code or Cursor call tools directly. SF ships 56 tools via a single command: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. From there, an AI agent can query markets, run thesis evaluations, pull calibration data, and check cross-venue arbitrage pairs without leaving the coding environment. No authentication is required for read operations.
Is Parsec limited to Polymarket, or does it also cover Kalshi?+
Based on Parsec's public positioning and tagline — 'Real-time data analytics and insights for Polymarket' — it focuses on Polymarket. SimpleFunctions normalizes data across both Kalshi and Polymarket, with 48K+ active contracts indexed cross-venue. Cross-venue arbitrage pairs are available at /api/public/cross-venue/pairs?preset=arb.
What calibration data does SimpleFunctions publish, and why does it matter?+
/api/calibration returns SF's own Brier scores by venue, category, and price bucket. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. A lower Brier score means predictions are better-calibrated. Publishing this data lets you audit SF's accuracy before relying on it in a model or agent. Most prediction market analytics products, including Parsec, do not publish equivalent calibration baselines.
Does Parsec have a public API I can call from code?+
Based on Parsec's public documentation and website, it operates as a web dashboard and does not describe a public REST API for programmatic access. SimpleFunctions' entire surface is API-first — public REST endpoints require no authentication for reads, the CLI wraps the same endpoints with 60+ commands, and the MCP server exposes 56 tools to any compatible AI assistant.
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.