Recursive Epistemic Market Microstructure MCP Server

> View on ApifyForge | Use on Apify Store

---

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf):

{
  "mcpServers": {
    "recursive-epistemic-market-mcp": {
      "url": "https://ryanclinton--recursive-epistemic-market-mcp.apify.actor/mcp"
    }
  }
}

---

Recursive epistemic market microstructure analysis is now available as an MCP server your AI agent can call directly. This server exposes 8 tools that apply advanced mathematical finance models — Soros reflexivity fixed-point iteration, Harsanyi type space belief hierarchies, minority game spin glass phase transitions, rough volatility (fBm with H<0.5), entropic optimal transport, regression discontinuity for regulatory impact, and the Kyle continuous insider trading model — each calibrated from 16 live public data sources spanning SEC filings, FDIC bank records, congressional stock trades, FRED macro indicators, and exchange rate history.

Connect once via the MCP protocol and your AI agent gains structured, quantitative market microstructure intelligence without managing data pipelines, API integrations, or financial math implementations. Every tool is pay-per-call with no subscription required.

What data can you access?

| Data Point | Source | Example |
|---|---|---|
| 📊 SEC 10-K, 10-Q, 8-K filings and analysis | SEC EDGAR Analyzer | Earnings quality scores, risk flag counts |
| 📄 SEC filing full text and metadata | SEC EDGAR Filing Search | Form type, filing date, CIK, accession number |
| 👤 Executive insider stock transactions | SEC Insider Trading (Form 4) | 50,000 shares sold by CFO at $142.30 |
| 🏦 US bank financial statements | FDIC Bank Data | Total assets, Tier 1 capital, loan loss reserves |
| 🏛️ Congressional stock trading disclosures | Congressional Stock Tracker | Representative name, ticker, trade date, amount range |
| 📈 Stock prices, quotes, and financials | Finnhub | AAPL last: $185.42, P/E: 28.6, beta: 1.24 |
| 🪙 Cryptocurrency prices and market cap | CoinGecko | BTC $67,240, 24h vol $38.4B, market cap $1.32T |
| 💱 Current foreign exchange rates | Exchange Rate Tracker | USD/EUR: 0.9214, USD/JPY: 149.82 |
| 📉 Historical exchange rate time series | Exchange Rate History | 365-day USD/EUR daily close series |
| 🏛️ US economic indicators (GDP, CPI, rates) | FRED | Fed Funds rate: 5.33%, CPI YoY: 3.1% |
| 👷 Employment and inflation statistics | BLS | Unemployment: 3.7%, wage growth: 4.1% |
| 📋 Federal rules and regulations | Federal Register | Dodd-Frank amendment, effective date, CFR citation |
| 🏢 Global corporate registrations | OpenCorporates | Jurisdiction, incorporation date, officers |
| ⚠️ Consumer financial complaints | CFPB | Product type, issue, company response, resolution |
| 🇪🇺 ECB reference exchange rates | ECB Rates | EUR/USD reference, date, change from prior day |
| 📜 Congressional bill introductions and status | Congress Bill Tracker | Bill number, sponsor, committee, latest action |

Why use this MCP server for market microstructure analysis?

Building quantitative market microstructure intelligence from scratch means integrating 16 separate APIs, implementing fixed-point iteration algorithms, calibrating Hurst exponent estimators, and coding Sinkhorn divergence solvers — weeks of work before writing a single line of domain analysis. Commercial alternatives like Bloomberg Terminal charge $24,000/year; even lighter tools like Refinitiv or FactSet run $1,000+/month, with no AI-native interface.

This MCP server plugs directly into Claude, Cursor, or any MCP-compatible AI client. Your agent issues a single tool call and receives structured JSON with regime classifications, fixed-point prices, informed trading probabilities, and volatility roughness scores — all derived from live data across 16 sources processed in parallel.

- Always-on availability — runs in Apify Standby mode, ready for requests within milliseconds
- Parallel data fetching — up to 16 actors called simultaneously per tool invocation, reducing latency
- Structured JSON output — every tool returns typed, consistently-formatted output your agent can reason over directly
- Pay-per-call pricing — $0.10 per tool call, no subscription, no minimum commitment
- Spending limits — set a per-run cap in Apify to prevent runaway agent loops from accumulating cost
- API and webhook access — trigger from any HTTP client, Zapier, Make, or LLM orchestration framework

Features

- Soros reflexivity detection — models price as p(t+1) = f(p(t), E[p(t+1)|p(t)]) and finds the fixed point p via Picard iteration, computing a reflexivity gap that measures divergence between market price and rational equilibrium
- Three reflexivity regimes — classifies markets into CONVERGENT (gap shrinking), DIVERGENT (bubble/crash dynamics), or OSCILLATING (cyclical feedback)
- Harsanyi type space construction — builds K-depth belief hierarchies via projective limit truncation, computing Bayesian Nash equilibrium strategies and a common knowledge gap score across all identified market participants
- Minority game simulation — El Farol / Minority Game with N agents (51-501, odd), S random strategies per agent, and phase transition detection at alpha = P/N where P = 2^M; spin glass order parameter measures strategy crowding
- Two minority game regimes — identifies whether the market is below the critical alpha (herding, high volatility, inefficient) or above it (efficient, low excess volatility, strategy diversity)
- Kyle (1985) continuous insider model — computes price impact lambda = sigma_v / (2sigma_u), information revelation rate via backward induction, expected insider profit, market maker loss, and Probability of Informed Trading (PIN = alphadelta / (alphadelta + 2epsilon))
- Three informedness regimes — LOW_INFO, MODERATE_INFO, HIGH_INFO based on PIN and signal-to-noise ratio
- Rough volatility estimation — Hurst exponent from log-variogram regression: V(delta) ~ Cdelta^(2H), with volatility model sigma(t) = sigma_0exp(etaW_H(t) - eta^2t^(2H)/2)
- Three roughness regimes — SMOOTH (H>0.5), ROUGH (0.15<H<0.5), ULTRA_ROUGH (H<0.15), with implied skew from rough Bergomi model
- Entropic optimal transport — Sinkhorn divergence between BULL, BEAR, VOLATILE, and STABLE regime distributions; builds Gibbs kernel K_ij = exp(-C_ij/epsilon) and iterates u <- a/(Kv), v <- b/(K^Tu) to convergence
- Regime transition probabilities — Sinkhorn divergence S_eps removes entropic bias and produces calibrated transition probability estimates between regimes
- Sharp regression discontinuity — tau = lim_{x->c+} E[Y|X=x] - lim_{x->c-} E[Y|X=x] for regulatory impact, using local linear regression with Imbens-Kalyanaraman optimal bandwidth and McCrary density test for running variable manipulation
- Full recursive epistemic forecast — forecast_fixed_point_price orchestrates all four core algorithms (reflexivity + belief hierarchy + rough volatility + Kyle model) in a single call across 16 actors for a unified multi-factor price forecast
- 16 live data sources — SEC EDGAR (analysis + filings), SEC Insider Trading, FDIC, Congressional Stock, Finnhub, CoinGecko, Exchange Rates (current + historical), FRED, BLS, Federal Register, OpenCorporates, CFPB, ECB Rates, Congress Bills

{
  "mcpServers": {
    "recursive-epistemic-market": {
      "url": "https://recursive-epistemic-market-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

{
  "mcpServers": {
    "recursive-epistemic-market": {
      "url": "https://recursive-epistemic-market-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

{

  "query": "JPMorgan Goldman Sachs banking",

  "sector": "finance"

}

{

  "query": "S&P 500 US equities",

  "num_agents": 201,

  "memory_length": 8,

  "num_rounds": 500

}

{

  "query": "NVDA AMD semiconductor AI chips"

}

{

  "query": "Dodd-Frank capital requirements",

  "sector": "banking"

}

{
  "systemReflexivity": 0.73,
  "dominantRegime": "DIVERGENT",
  "assetCount": 6,
  "states": [
    {
      "ticker": "NVDA",
      "fixedPoint": 892.40,
      "reflexivityGap": 0.18,
      "feedbackStrength": 0.81,
      "regime": "DIVERGENT",
      "convergenceIterations": 47
    },
    {
      "ticker": "AMD",
      "fixedPoint": 168.30,
      "reflexivityGap": 0.09,
      "feedbackStrength": 0.54,
      "regime": "CONVERGENT",
      "convergenceIterations": 12
    },
    {
      "ticker": "INTC",
      "fixedPoint": 34.10,
      "reflexivityGap": 0.04,
      "feedbackStrength": 0.29,
      "regime": "CONVERGENT",
      "convergenceIterations": 8
    }
  ]
}

{
  "systemInformedness": 0.62,
  "averageLambda": 0.041,
  "dominantRegime": "MODERATE_INFO",
  "assetCount": 4,
  "assets": [
    {
      "ticker": "JPM",
      "lambda": 0.058,
      "informedTradingProbability": 0.71,
      "insiderProfit": 184200,
      "priceEfficiency": 0.44,
      "signalToNoise": 2.31,
      "regime": "HIGH_INFO"
    },
    {
      "ticker": "GS",
      "lambda": 0.033,
      "informedTradingProbability": 0.48,
      "insiderProfit": 92800,
      "priceEfficiency": 0.67,
      "signalToNoise": 1.12,
      "regime": "MODERATE_INFO"
    }
  ]
}

{
  "alpha": 0.64,
  "phaseTransitionPoint": 0.34,
  "regime": "ASYMMETRIC",
  "volatilityRatio": 0.82,
  "informationContent": 0.71,
  "crowdingMeasure": 0.29,
  "topAgents": [
    { "agentId": 42, "strategy": 1, "score": 147 },
    { "agentId": 78, "strategy": 0, "score": 139 }
  ],
  "recentAttendance": [48, 53, 45, 51, 49, 55, 47, 52, 50, 48]
}

{
  "systemForecast": {
    "forecastHorizon": "30d",
    "consensusDirection": "BULLISH",
    "confidenceScore": 0.61,
    "epistemicUncertainty": 0.38
  },
  "reflexivitySummary": {
    "systemReflexivity": 0.68,
    "dominantRegime": "DIVERGENT"
  },
  "beliefSummary": {
    "commonKnowledgeGap": 0.44,
    "agentCount": 12,
    "hierarchyDepth": 5
  },
  "volatilitySummary": {
    "systemRoughness": 0.19,
    "dominantRegime": "ROUGH"
  },
  "insiderSummary": {
    "systemInformedness": 0.57,
    "averageLambda": 0.036,
    "dominantRegime": "MODERATE_INFO"
  },
  "forecasts": [
    {
      "ticker": "NVDA",
      "fixedPointPrice": 892.40,
      "beliefAdjustedPrice": 871.20,
      "volAdjustedRange": [834.10, 910.50],
      "insiderAdjustment": -0.023,
      "compositeConfidence": 0.58
    }
  ]
}

| Field | Type | Description |
|-------|------|-------------|
| systemReflexivity | number | System-wide reflexivity score 0-1; higher = stronger feedback loops |
| dominantRegime | string | Majority regime across analyzed assets |
| states[].ticker | string | Asset identifier |
| states[].fixedPoint | number | Fixed-point price p where p = f(p, E[p\|p]) |
| states[].reflexivityGap | number | Normalized distance between market price and rational equilibrium |
| states[].feedbackStrength | number | Magnitude of price-expectation feedback (0-1) |
| states[].regime | string | CONVERGENT, DIVERGENT, or OSCILLATING |
| states[].convergenceIterations | number | Picard iterations to reach fixed point (or max 100 if non-convergent) |
| commonKnowledgeGap | number | Average divergence in higher-order beliefs across agent types |
| bayesianNashEquilibrium[].strategy | number | Optimal strategy for each agent type under BNE |
| types[].privateValue | number | Agent-specific fundamental value estimate |
| types[].rationalityBound | number | Level-k rationality bound (0=naive, 1=fully rational) |
| alpha | number | Minority game complexity ratio P/N |
| phaseTransitionPoint | number | Critical alpha_c below which herding dominates |
| crowdingMeasure | number | Spin glass order parameter; higher = more crowded strategies |
| volatilityRatio | number | Excess volatility relative to efficient market benchmark |
| assets[].hurstExponent | number | Hurst exponent H; <0.5 = rough, =0.5 = standard BM, >0.5 = trending |
| assets[].roughnessIndex | number | Normalized roughness score 0-1 |
| assets[].volOfVol | number | Volatility of volatility (vol clustering measure) |
| assets[].skewImplied | number | Implied skew from rough Bergomi model |
| assets[].lambda | number | Kyle price impact coefficient ($/share per unit order flow) |
| assets[].informedTradingProbability | number | PIN — Probability of Informed Trading (0-1) |
| assets[].insiderProfit | number | Estimated expected insider profit per trading window ($) |
| assets[].priceEfficiency | number | Price efficiency score 0-1; lower = more mispricing |
| comparisons[].sinkhornDivergence | number | Sinkhorn divergence S_eps between two regime distributions |
| comparisons[].transitionProbability | number | Estimated probability of transitioning between the two regimes |
| estimates[].treatmentEffect | number | RD causal estimate tau of regulatory impact |
| estimates[].tStatistic | number | t-statistic for treatment effect significance test |
| estimates[].significant | boolean | True if |t| > 1.96 (95% confidence) |
| estimates[].mcCraryDensityTest | number | McCrary test statistic for running variable manipulation |
| forecasts[].fixedPointPrice | number | Reflexivity-adjusted fixed-point price forecast |
| forecasts[].compositeConfidence | number | Combined confidence score from all four algorithms (0-1) |

How much does it cost to use this MCP server?

This MCP server uses pay-per-event pricing — you pay $0.10 per tool call. Platform compute costs are included. All 8 tools cost the same $0.10 regardless of how many actors they invoke in the background.

| Scenario | Tool calls | Cost per call | Total cost |
|----------|-----------|---------------|------------|
| Quick test — single reflexivity check | 1 | $0.10 | $0.10 |
| Single-stock deep dive (all 8 tools) | 8 | $0.10 | $0.80 |
| Daily sector scan (10 queries/day) | 10 | $0.10 | $1.00/day |
| Weekly research workflow (50 calls) | 50 | $0.10 | $5.00 |
| Active quant research (500 calls/month) | 500 | $0.10 | $50.00/month |

You can set a maximum spending limit per run to control costs. The server stops charging when your budget is reached.

Apify's free tier includes $5 of monthly platform credits — enough for 50 tool calls per month at no cost. Compare this to Bloomberg Terminal at $2,000/month or Refinitiv Eikon at $1,200/month. Most users running daily research workflows spend $5-50/month with no subscription commitment.

Using the MCP server via API

Python

```python
from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")