# Adversarial Regulatory Arbitrage MCP Server (`ryanclinton/adversarial-regulatory-arbitrage-mcp`) Actor MCP intelligence server for adversarial regulatory arbitrage detection and analysis. - **URL**: https://apify.com/ryanclinton/adversarial-regulatory-arbitrage-mcp.md - **Developed by:** [ryan clinton](https://apify.com/ryanclinton) (community) - **Categories:** AI, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing Pay per event + usage This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Adversarial Regulatory Arbitrage MCP Server Multi-jurisdiction regulatory evasion detection with game-theoretic enforcement modeling. This MCP server cross-references corporate registries across 7 jurisdictions, sanctions databases, SEC filings, and regulatory publications to detect regulatory arbitrage patterns, trace ultimate beneficial ownership through layered shell structures, and simulate the strategic dynamics between regulators and regulated entities. ### Available Tools | Tool | Description | |------|-------------| | `detect_regulatory_arbitrage` | Cross-reference 17 data sources to detect multi-jurisdiction shell layering, regulatory timing arbitrage, and insider trading around regulatory events | | `trace_beneficial_ownership` | Trace UBO through layered corporate structures across UK, Canada, Australia, NZ, and OpenCorporates with stochastic reachability and cycle detection | | `analyze_jurisdiction_topology` | Classify and compare regulatory regimes across jurisdictions with multi-dimensional scoring and cluster analysis | | `simulate_enforcement_game` | Compute multi-leader Stackelberg GNEP equilibrium between regulators and regulated entities with damped iterated best response | | `classify_regulatory_regime` | Detailed regulatory profile for a single jurisdiction with rankings across 7 dimensions | | `assess_shell_company_risk` | Bayesian shell company risk assessment using 10 FATF-derived indicators with posterior probability scoring | | `compute_arbitrage_equilibrium` | GAN-inspired adversarial co-evolution of arbitrage strategies and detection methods with evolutionary arms race simulation | | `forecast_regulatory_convergence` | Predict regulatory convergence/divergence between jurisdiction pairs with mean-reversion modeling | ### Data Sources (17 Actors) | Source | Actor | Coverage | Purpose | |--------|-------|----------|---------| | OFAC Sanctions | `ofac-sanctions-search` | US Treasury SDN list | Primary sanctions screening | | OpenSanctions | `opensanctions-search` | 80+ international lists | Cross-jurisdiction sanctions | | OpenCorporates | `opencorporates-search` | 140M+ companies globally | Cross-jurisdiction company data | | UK Companies House | `uk-companies-house` | All UK registered companies | UK corporate registry + PSCs | | Canada Corporations | `canada-corporation-search` | Federal corporations | Canadian corporate registry | | Australia ABN | `australia-abn-lookup` | Australian Business Register | Australian entity lookup | | NZ Companies Office | `nz-companies-search` | NZ registered companies | New Zealand corporate registry | | GLEIF LEI | `gleif-lei-lookup` | Global LEI database | Legal Entity Identifiers | | SEC EDGAR Analyzer | `sec-edgar-filing-analyzer` | All SEC filings | Company analysis with XBRL | | EDGAR Filing Search | `edgar-filing-search` | All SEC filings | Filing search and retrieval | | SEC Insider Trading | `sec-insider-trading` | Form 4 filings | Insider transaction monitoring | | FDIC Bank Search | `fdic-bank-search` | All FDIC-insured banks | US banking institution data | | Federal Register | `federal-register-search` | All federal regulations | Regulatory action monitoring | | Congress Bill Search | `congress-bill-search` | Congressional legislation | Legislative tracking | | EU VAT Validator | `eu-vat-validator` | EU VIES system | VAT number verification | | EUIPO Trademark | `euipo-trademark-search` | EU trademarks | IP/trademark intelligence | | Interpol Red Notices | `interpol-red-notices` | Interpol wanted persons | International criminal alerts | ### Mathematical Foundations This MCP server implements several computationally significant algorithms: #### Ownership Graph Analysis - **Tarjan's Strongly Connected Components** (O(V+E)): Detects circular ownership structures that indicate shell company layering - **Jaro-Winkler Similarity**: Fuzzy entity matching across jurisdictions with different naming conventions - **Spectral Graph Bisection**: Fiedler vector computation via power iteration on the normalized graph Laplacian for ownership community detection - **Stochastic UBO Reachability**: Monte Carlo simulation for tracing effective ownership through chains with uncertain ownership percentages #### Game-Theoretic Modeling - **Multi-Leader Stackelberg GNEP**: Iterated best response with damped updates for computing approximate Nash equilibria in the regulator-entity game (the exact problem is PPAD-hard) - **Softmax Best Response**: Bounded rationality model where entities' jurisdiction choices follow a logit distribution over costs - **GAN-Inspired Co-Evolution**: Evolutionary algorithm where a population of arbitrage strategies (generator) co-evolves with a detection model (discriminator) #### Risk Scoring - **Bayesian Posterior Scoring**: 10 FATF-derived shell company indicators update a prior probability via log-likelihood ratios calibrated from empirical studies (Findley et al. 2014) - **Multi-Source Evidence Accumulation**: Weighted evidence aggregation across corporate registries, sanctions lists, SEC filings, and regulatory publications ### How to Connect #### Claude Desktop Add to your `claude_desktop_config.json`: ```json { "mcpServers": { "regulatory-arbitrage": { "url": "https://actors-mcp-server.apify.actor/mcp?actorId=ryanclinton/adversarial-regulatory-arbitrage-mcp&token=YOUR_APIFY_TOKEN" } } } ```` #### Cursor Add the same URL in Cursor's MCP server settings. #### Direct HTTP ```bash curl -X POST https://actors-mcp-server.apify.actor/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "detect_regulatory_arbitrage", "arguments": { "entity_name": "Example Holdings Ltd", "jurisdictions": ["GB", "KY", "IE"] } }, "id": 1 }' ``` ### Example Conversations **Investigating a company for regulatory arbitrage:** > "Investigate Acme International Holdings for signs of regulatory arbitrage across UK, Ireland, Luxembourg, and Cayman Islands" The AI will call `detect_regulatory_arbitrage` with those jurisdictions, building an ownership graph and checking for multi-jurisdiction layering, timing patterns around regulatory changes, and insider trading correlations. **Tracing beneficial ownership:** > "Who ultimately controls Global Finance Ltd through its corporate chain?" The AI will call `trace_beneficial_ownership` to trace UBO through layered structures, detecting circular ownership and identifying ultimate controllers. **Understanding regulatory dynamics:** > "Simulate the enforcement game between US, UK, Ireland, Singapore, and Cayman Islands regulators" The AI will call `simulate_enforcement_game` to compute the Stackelberg equilibrium, showing which jurisdictions end up in a race to the bottom and which arbitrage routes dominate. **Shell company due diligence:** > "Assess shell company risk for Pacific Trading Corp registered in the British Virgin Islands" The AI will call `assess_shell_company_risk` to evaluate 10 risk indicators using Bayesian scoring, returning a risk level and detailed explanation. ### How It Works 1. **Data Collection**: Tools query 17 underlying Apify actors in parallel, fetching corporate registry data, sanctions records, SEC filings, and regulatory publications. 2. **Graph Construction**: Corporate relationships are normalized into a unified directed multigraph with entities as nodes and ownership/directorship relationships as edges. Cross-jurisdiction entity matching uses Jaro-Winkler fuzzy similarity. 3. **Analysis**: The graph is analyzed for structural indicators of arbitrage: cycles (Tarjan's SCC), depth (BFS), spectral communities (Fiedler vector), and stochastic UBO chains (Monte Carlo reachability). 4. **Risk Scoring**: Each entity receives a Bayesian risk score based on 10 FATF-derived indicators, with likelihood ratios calibrated from empirical shell company studies. 5. **Game-Theoretic Simulation**: The strategic interaction between regulators and entities is modeled as a multi-leader Stackelberg game, with equilibrium computed via damped iterated best response. ### Limitations - **Ownership data completeness**: Corporate registries vary in disclosure requirements. Some jurisdictions (e.g., BVI, Panama) provide minimal public ownership data. - **Real-time data**: Data freshness depends on underlying actor update frequencies. Corporate registry data may lag by days to weeks. - **Equilibrium convergence**: The GNEP may not converge for all jurisdiction combinations (the problem is PPAD-hard). Non-convergence is reported when detected. - **Fuzzy matching**: Cross-jurisdiction entity matching may produce false positives for common company names. Use specific names for best results. - **Sanctions coverage**: OFAC and OpenSanctions provide extensive but not exhaustive coverage. Additional list-specific actors may be needed for comprehensive screening. ### Combine with Other Apify Actors - **Company Deep Research** (`company-deep-research`): Deep dive into a specific company identified as high-risk - **WHOIS Domain Lookup** (`whois-domain-lookup`): Investigate digital presence of suspected shell companies - **Brand Protection Monitor** (`brand-protection-monitor`): Detect trademark abuse by shell entities - **Website Tech Stack Detector** (`website-tech-stack-detector`): Verify whether shell companies have real web presence ### Tips for Best Results 1. **Be specific with entity names**: Use the exact registered name, not abbreviations 2. **Start broad, then narrow**: Use `analyze_jurisdiction_topology` first to understand the landscape, then investigate specific entities 3. **Combine tools**: Use `detect_regulatory_arbitrage` for initial screening, then `trace_beneficial_ownership` for deep UBO analysis on flagged entities 4. **Interpret game simulations carefully**: Stackelberg equilibria are approximations — non-convergence is informative (it means the regulatory landscape is inherently unstable) ### Pricing Each tool call is billed as a separate pay-per-event charge. See the actor's pricing page for current rates. ### FAQ **Q: Does this detect all forms of regulatory arbitrage?** A: No — it detects patterns detectable from public data (corporate registries, SEC filings, sanctions lists). Private arrangements, informal structures, and undisclosed beneficial ownership are not visible. **Q: How accurate is the shell company risk score?** A: The Bayesian scoring model is calibrated against FATF red flag indicators and empirical studies. It produces a probability estimate, not a binary classification. Scores above 70 warrant further investigation. **Q: What does "GNEP did not converge" mean?** A: The multi-leader Stackelberg game may have no pure-strategy Nash equilibrium, or the solution set may be disconnected. This itself is informative — it indicates an inherently unstable regulatory environment where small changes can produce large strategic shifts. **Q: Can this be used for compliance purposes?** A: This tool is designed for research, due diligence, and regulatory analysis. For formal compliance decisions, results should be verified by qualified compliance professionals. # Actor input Schema ## Actor input object example ```json {} ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("ryanclinton/adversarial-regulatory-arbitrage-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("ryanclinton/adversarial-regulatory-arbitrage-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call ryanclinton/adversarial-regulatory-arbitrage-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=ryanclinton/adversarial-regulatory-arbitrage-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Adversarial Regulatory Arbitrage MCP Server", "description": "MCP intelligence server for adversarial regulatory arbitrage detection and analysis.", "version": "1.0", "x-build-id": "GGYF1TrE2wkwAGQYX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ryanclinton~adversarial-regulatory-arbitrage-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ryanclinton-adversarial-regulatory-arbitrage-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ryanclinton~adversarial-regulatory-arbitrage-mcp/runs": { "post": { "operationId": "runs-sync-ryanclinton-adversarial-regulatory-arbitrage-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ryanclinton~adversarial-regulatory-arbitrage-mcp/run-sync": { "post": { "operationId": "run-sync-ryanclinton-adversarial-regulatory-arbitrage-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": {} }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```