Alternative · Cross-venue terminal
TradeFox vs
SimpleFunctions.
Same upstream venues. TradeFox operates as a prime-brokerage-style execution aggregator — self-custodial order routing, institutional-grade execution, backed by Alliance DAO and CMT Digital. SimpleFunctions ships the agent layer above the orderbook: causal-tree thesis system, autonomous Portfolio Autopilot with a 1M-context LLM and 7-gate risk cascade, computed indicators across 48K+ active contracts, and a 56-tool MCP server.
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 execution routing — calibrated probabilities with public Brier scores, causal-tree thesis modelling with auto-evaluation cycles, regime classification across the full 48K-contract universe, computed indicators (implied yield, cliff risk, liquidity availability score, event overround), and a 56-tool MCP server that integrates into Claude Code or Cursor in one command.
Choose TradeFox if
You need self-custodial, institutional-grade order routing across prediction-market venues — TradeFox's prime-brokerage execution model is purpose-built for that audience, backed by Alliance DAO and CMT Digital. If custodial control and execution quality for a trading desk are the primary requirements, TradeFox is the purpose-built product.
Same upstream venues (Kalshi + Polymarket). TradeFox routes institutional self-custodial execution. SimpleFunctions ships the agent layer: world model, theses, indicators, autopilot, MCP. Different products, mostly different audiences.
At a glance
Three things that
actually differ.
Everything TradeFox gives you — cross-venue access to Kalshi and Polymarket, normalised prices, and execution routing — SimpleFunctions also gives you, on the same underlying feeds.
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 execution product exposes.
SF also publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Most competitors claim accuracy; we let you check ours.
Side by side
9 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised across 48K+ active contracts, indexed and searchable.
TradeFoxKalshi + Polymarket aggregation via prime-brokerage routing; venue scope not further detailed publicly.
SimpleFunctionsREST/CLI/MCP reads for any caller; Portfolio Autopilot handles autonomous execution through a 7-gate risk cascade.
TradeFoxSelf-custodial, institutional-grade order routing designed for human traders directing execution across venues.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimates.
TradeFoxPrime-brokerage routing implies orderbook access; no public API endpoint is documented.
SimpleFunctionsImplied yield (IY), cliff risk index (CRI), liquidity availability score (LAS), event overround (EE), τ-days, and regime label pre-computed at /screen across 48K+ contracts.
TradeFoxNot documented; institutional execution focus does not include pre-computed derived signals.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, and price bucket, rolling 90-day window.
TradeFoxNot published.
SimpleFunctionsPOST /api/thesis/create decomposes any claim into a causal tree of testable sub-claims, maps nodes to live contracts, and runs an auto-evaluation heartbeat (news → price → LLM eval → confidence update).
TradeFoxNot in scope; TradeFox is an execution aggregator, not a research or thesis-modelling platform.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM ingesting 13 data sources, gated by kill switch, position limits, drawdown gate, and regime check before any execution.
TradeFoxNot documented; the platform is designed for human-directed institutional trading, not autonomous agent execution.
SimpleFunctions56 tools via `claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp`, compatible with Claude Code, Cursor, and any MCP client.
TradeFoxNo MCP server published.
SimpleFunctionsPublic REST + MCP + CLI reads require no auth. Thesis creation and intent execution are free up to 15M tokens, then pay-per-token.
TradeFoxNot publicly specified.
Methodology
Verified 2026-04 from public sources only — TradeFox's documentation, public website, and publicly observable behaviour. We never claim non-public information about TradeFox'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 autonomously research, model, and trade prediction markets.
SimpleFunctions · best fit
SF's 56-tool MCP server integrates directly into Claude Code or Cursor. The causal thesis system decomposes research into testable sub-claims mapped to live contracts, and Portfolio Autopilot handles execution with a 7-gate risk cascade. /api/agent/world delivers a compressed world snapshot in ~800 tokens for lightweight agent loops.
TradeFox
TradeFox is not designed as an agent-facing tool; its prime-brokerage model targets human traders directing institutional execution, not AI agents consuming APIs autonomously.
Scenario 02
Running a self-custodial institutional trading desk that needs prime-brokerage-style execution routing across venues.
SimpleFunctions
SF offers cross-venue pricing and autopilot execution, but it is optimised for AI-native and research workflows rather than self-custodial institutional desk operations.
TradeFox · best fit
TradeFox is built specifically for this scenario — self-custodial, institutional-grade order routing with Alliance DAO and CMT Digital backing. It is the purpose-built product for this audience.
Scenario 03
Decomposing a complex macro thesis — for example, 'US recession by Q3 2026' — into tradeable prediction-market edges.
SimpleFunctions · best fit
POST /api/thesis/create accepts the sentence, decomposes it into a causal tree, maps each node to Kalshi and Polymarket contracts, and runs an auto-evaluation heartbeat. Public theses are forkable. No competitor offers this architecture.
TradeFox
TradeFox is an execution aggregator; thesis modelling and causal decomposition are not part of its documented feature set.
Scenario 04
Evaluating whether a prediction market price is well-calibrated before committing to a position.
SimpleFunctions · best fit
/api/calibration returns SF's own Brier scores by venue, category, and price bucket on a rolling 90-day window. Pre-computed indicators at /screen (cliff risk index, event overround, regime label) add further pre-trade signal.
TradeFox
TradeFox's prime-brokerage routing is focused on execution quality rather than pre-trade calibration analysis; no equivalent calibration API is documented.
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 is SimpleFunctions' causal thesis system and how does it differ from TradeFox's model?+
SF's causal thesis system (POST /api/thesis/create) takes any claim — a macro prediction, a geopolitical scenario, a policy outcome — and decomposes it into a causal tree of testable sub-claims. Each node is mapped to tradeable contracts on Kalshi and Polymarket. An evaluation heartbeat then runs automatically: news scan → price refresh → milestone check → LLM evaluation → confidence update. You can inject new signals at any time via /api/thesis/{id}/signal. TradeFox, by contrast, focuses on institutional execution routing. No competitor currently offers a causal thesis architecture.
Does SimpleFunctions support autonomous trading, and how does that compare to TradeFox's execution?+
Yes, via Portfolio Autopilot. Where TradeFox offers self-custodial institutional routing designed for human traders, SF's Autopilot is an autonomous decision layer built on a 1M-context LLM that ingests 13 data sources. Before any execution, it runs through a 7-gate risk cascade: kill switch, position limits, drawdown gate, regime check, and additional safeguards. TradeFox's prime-brokerage model is designed for humans directing execution; SF's Autopilot is designed for agents directing themselves.
Can I use SimpleFunctions with Claude Code, Cursor, or other AI coding tools?+
Yes. SimpleFunctions ships a 56-tool MCP server at https://simplefunctions.dev/api/mcp/mcp. Add it in one command: `claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp`. This exposes thesis creation, market scanning, cross-venue pricing, orderbook depth, trade ideas, and more directly inside Claude Code or any MCP-compatible client. TradeFox does not publish an MCP server.
What computed indicators does SimpleFunctions provide that TradeFox does not?+
SF pre-computes six indicators across 48K+ active contracts at /screen: implied yield (IY), cliff risk index (CRI), liquidity availability score (LAS), event overround (EE), time to settlement (τ-days), and regime label (adverse-selection classification). These are derived signals you would otherwise need to compute yourself from raw price and volume data. TradeFox's prime-brokerage model does not document equivalent pre-computed indicators in its public materials.
How does SimpleFunctions audit its own prediction accuracy?+
SF publishes live Brier scores at /api/calibration, broken down by venue, category, and price bucket, updated on a rolling 90-day window. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price. This means you can independently verify SF's calibration claims with a single curl command. Most prediction market data and execution products do not publish their own accuracy metrics publicly.
Which platform is better for an institutional trading desk that requires self-custodial execution?+
TradeFox. Its prime-brokerage model, institutional-grade routing, and self-custodial architecture are designed for exactly that audience, with Alliance DAO and CMT Digital backing its infrastructure credibility. SimpleFunctions is optimised for AI agents, researchers, and quantitative pipelines that need the intelligence layer above execution: thesis modelling, calibrated probabilities, computed indicators, and MCP integration. The audiences are largely distinct.
Does TradeFox have a public REST API for programmatic access?+
TradeFox's public documentation does not describe a documented public REST API for third-party programmatic access. It positions itself as an institutional execution aggregator for trading desks rather than a data or developer platform. SimpleFunctions provides a fully documented public REST API with no auth required for reads, a 56-tool MCP server, and a CLI with 60+ commands — all designed for programmatic and agent-driven access from the start.
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.