Regulatory Change Intelligence MCP Server

Regulatory change intelligence across 13 US federal data sources, delivered as an MCP server your AI agent can query directly. Built for compliance officers, GRC teams, and trade compliance operations who need forward-looking signals — not just a list of current rules. The server produces a composite Compliance Impact Score (0-100) backed by four scoring sub-models: Legislative Probability, Enforcement Trend, Tariff Impact, and Regulatory Domino Effect.

Rather than manually parsing the Federal Register, checking OSHA inspection databases, and cross-referencing CBP customs rulings every week, you send a single tool call and receive a scored, structured assessment. The server runs up to 13 Apify actors in parallel across congressional bill databases, agency enforcement records, trade tariff schedules, lobbying disclosure filings, and FEC campaign finance data — then applies weighted scoring models to surface what actually matters to your compliance program.

⬇️ What data can you access?

Why use the Regulatory Change Intelligence MCP Server?

Compliance teams at mid-market and enterprise companies spend 8-15 hours per week across analyst roles just scanning the Federal Register, checking agency enforcement feeds, and tracking bills through committee. That process misses cross-agency signals — an EPA enforcement surge often precedes OSHA inspections at the same facility type, and a cluster of lobbying filings around a regulatory topic frequently predicts rulemaking within 6-12 months. Manual scanning cannot detect those correlations.

This MCP server automates the entire intelligence gathering and correlation layer. Your AI agent calls a single tool — compliance_impact_report — and receives a scored assessment with sub-model breakdowns and a plain-language recommendation, drawn from simultaneous queries across all 13 data sources.

Beyond the intelligence itself, running this server on the Apify platform means:

• Scheduling — run weekly scans on your priority regulatory topics and receive fresh scores automatically
• API access — trigger assessments from Python, JavaScript, n8n, or any HTTP client that supports MCP
• Proxy rotation — Apify's built-in proxy infrastructure ensures reliable access to all 13 source APIs
• Monitoring — configure Slack or email alerts when a Compliance Impact Score crosses a threshold
• Integrations — connect to Zapier, Make, webhooks, or push results directly to your GRC platform

Features

• 4-model scoring engine producing a composite Compliance Impact Score (0-100) with per-model breakdowns and a letter-grade equivalent (LOW / MODERATE / HIGH / CRITICAL COMPLIANCE RISK)
• Legislative Probability Engine (0-100) classifies bills across 4 pipeline stages — introduced, committee, passed, enacted — and weights passage probability against Federal Register rulemaking volume and lobbying intensity
• Enforcement Trend Detector (0-100) aggregates active enforcement records from OSHA, EPA ECHO, DOL WHD, FDA, and SEC, identifying DORMANT / MODERATE / ACTIVE / INTENSIFYING enforcement directions
• Tariff Impact Analyzer (0-100) scores trade policy disruption from CBP customs rulings, USITC HTS duty rate data, and trade-related Federal Register entries, with labeling from MINIMAL IMPACT through HIGH DISRUPTION
• Regulatory Domino Effect model (-100 to +100) measures cross-agency cascade potential by detecting when 3+ agencies show correlated enforcement activity in the same sector — the strongest signal of a coordinated regulatory campaign
• Weighted composite formula: Legislative Probability (30%) + Enforcement Trend (30%) + Domino Effect normalized (25%) + Tariff Impact (15%)
• Parallel actor execution — up to 13 data source actors run simultaneously, reducing total wall-clock time versus serial queries
• 8 MCP tools covering the full regulatory intelligence stack from pipeline search through full compliance impact reporting
• Sub-regulatory guidance monitoring via website change detection on agency domains — catches guidance documents and advisory opinions that change compliance requirements without formal rulemaking
• Lobbying pressure mapping correlates Senate lobbying filings and FEC contribution patterns with specific regulatory topics to surface industry influence on pending rules

Use cases for regulatory change intelligence

Compliance officer early-warning monitoring

Compliance officers at publicly traded companies need 3-12 months of advance notice on rules that affect their regulated activities. The regulatory_pipeline_search tool scans the Federal Register for proposed rules during their comment period and correlates them with bill activity in Congress. You get actionable signals before rules take effect — not after.

GRC team resource prioritization

Governance, Risk, and Compliance teams cannot respond equally to every Federal Register entry. The compliance_impact_report produces a scored rank across regulatory topics so teams allocate attention proportionally. A topic scoring 78 (CRITICAL) gets immediate attention; one scoring 22 (LOW) gets a quarterly review.

Trade compliance and tariff risk management

Import/export operations monitor CBP customs ruling changes because a reclassification of an HTS code can double landed costs overnight. The tariff_trade_impact tool tracks CBP rulings, USITC HTS duty rate changes, and trade-related legislation simultaneously. Procurement and trade compliance teams use this to anticipate duty exposure before purchase orders are placed.

Cross-agency enforcement pattern analysis

The cross_agency_domino_forecast is designed for industries that operate under multiple simultaneous regulatory regimes — chemicals, food manufacturing, healthcare, financial services. When EPA enforcement in a sector accelerates, OSHA often follows within months. The domino model quantifies that cascade risk before the second agency acts.

Lobbying intelligence for public affairs teams

Government affairs and public affairs teams use the lobbying_pressure_map to understand who is spending on which regulatory topics, and whether that spending correlates with FEC contribution patterns targeting key committee members. This surfaces the political economy around a regulation — not just its text.

Sub-regulatory guidance tracking

Federal agencies change compliance requirements without formal notice-and-comment rulemaking through guidance documents, FAQs, and policy interpretations posted to their websites. The agency_guidance_monitor tool detects changes to federal agency web pages and correlates them with Federal Register activity — catching informal compliance shifts before they become enforcement actions.

How to use the Regulatory Change Intelligence MCP Server

1. Connect the MCP server — Add the server URL https://regulatory-change-intelligence-mcp.apify.actor/mcp to your MCP client (Claude Desktop, Cursor, Windsurf, or any MCP-compatible tool). Authenticate with your Apify API token.
2. Choose your tool — For a quick scan of a regulatory topic, start with regulatory_pipeline_search. For a full scored assessment across all 13 sources, use compliance_impact_report.
3. Provide a query — Pass a regulatory topic, industry, company name, HTS code, or agency name. Example: "PFAS water contamination", "pharmaceutical drug pricing", "Section 301 tariffs solar panels".
4. Review the scored output — The server returns a Compliance Impact Score, sub-model breakdowns, active agencies, legislative pipeline stage counts, and a plain-language recommendation. Most tools complete in 30-90 seconds.

MCP tools

Connection examples

Claude Desktop — claude_desktop_config.json:

{
  "mcpServers": {
    "regulatory-change-intelligence": {
      "url": "https://regulatory-change-intelligence-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

Cursor / Windsurf / Cline — MCP config:

{
  "mcpServers": {
    "regulatory-change-intelligence": {
      "url": "https://regulatory-change-intelligence-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

cURL — direct tool call:

curl -X POST "https://regulatory-change-intelligence-mcp.apify.actor/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "compliance_impact_report",
      "arguments": {
        "query": "PFAS water contamination regulation"
      }
    },
    "id": 1
  }'

⬆️ Output example

{
  "query": "pharmaceutical drug pricing regulation",
  "complianceImpactScore": {
    "total": 74,
    "grade": "HIGH COMPLIANCE RISK",
    "recommendation": "Active regulatory environment. Monitor legislative pipeline and enforcement trends. Update compliance programs proactively."
  },
  "legislativeProbability": {
    "score": 68,
    "label": "LIKELY",
    "billStages": {
      "introduced": 9,
      "committee": 5,
      "passed": 2,
      "enacted": 0
    },
    "findings": [
      "2 bill(s) passed at least one chamber — high probability of enactment",
      "5 bills in committee — significant legislative attention",
      "9 introduced bills — building legislative momentum",
      "18 proposed/final rules in Federal Register — active rulemaking",
      "24 lobbying filings — high industry engagement"
    ]
  },
  "enforcementTrend": {
    "score": 58,
    "direction": "INTENSIFYING",
    "agencyActivity": {
      "FDA": 22,
      "DOL-WHD": 4,
      "SEC": 7
    },
    "findings": [
      "22 FDA recall/enforcement actions — heavy product safety enforcement",
      "4 DOL WHD enforcement action(s)",
      "7 SEC filing(s) — financial regulatory activity",
      "12 enforcement-related Federal Register notice(s)",
      "3 agencies actively enforcing — multi-front regulatory pressure"
    ]
  },
  "tariffImpact": {
    "score": 18,
    "label": "LOW DISRUPTION",
    "findings": [
      "2 CBP customs ruling(s)",
      "6 trade-related Federal Register notice(s)",
      "3 trade-related bill(s) in Congress"
    ]
  },
  "dominoEffect": {
    "score": 42,
    "direction": "EXPANDING",
    "activeAgencies": ["FDA", "SEC", "DOL-WHD"],
    "findings": [
      "3 agencies with active enforcement — moderate cascade potential",
      "Active agencies: FDA, SEC, DOL-WHD",
      "18 Federal Register entries — regulatory momentum building",
      "16 congressional bills — legislative pressure amplifies regulatory cascade"
    ]
  },
  "sourceCounts": {
    "federalRegisterEntries": 18,
    "congressBills": 16,
    "cbpRulings": 2,
    "usitcTariffEntries": 0,
    "secFilings": 7,
    "oshaInspections": 0,
    "epaEnforcement": 0,
    "dolWhdActions": 4,
    "fdaRecalls": 14,
    "fdaDevices": 8,
    "websiteChanges": 3,
    "lobbyingFilings": 24,
    "fecContributions": 11
  }
}

Output fields

How much does it cost to run regulatory change intelligence?

This MCP uses pay-per-event pricing — you pay $0.045 per tool call. Platform compute costs are included.

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

Apify's free tier includes $5 of monthly platform credits — enough for over 100 tool calls per month at no cost. Compare this to dedicated RegTech platforms (Lexis+ Regulatory Tracker, Compliance.ai, RegData) at $500-2,500/month — with this MCP, most compliance teams spend under $10/month with no subscription commitment.

How to use the Regulatory Change Intelligence MCP Server via the API

Python

from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")

run = client.actor("ryanclinton/regulatory-change-intelligence-mcp").call(run_input={})

# Or call via HTTP to the MCP endpoint after the actor starts
import requests

response = requests.post(
    "https://regulatory-change-intelligence-mcp.apify.actor/mcp",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer YOUR_APIFY_TOKEN",
    },
    json={
        "jsonrpc": "2.0",
        "method": "tools/call",
        "params": {
            "name": "compliance_impact_report",
            "arguments": {"query": "PFAS water contamination regulation"},
        },
        "id": 1,
    },
)

result = response.json()
impact = result["result"]["content"][0]["text"]
print(f"Compliance Impact Score: {impact}")

JavaScript

import fetch from "node-fetch";

const response = await fetch(
  "https://regulatory-change-intelligence-mcp.apify.actor/mcp",
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: "Bearer YOUR_APIFY_TOKEN",
    },
    body: JSON.stringify({
      jsonrpc: "2.0",
      method: "tools/call",
      params: {
        name: "compliance_impact_report",
        arguments: { query: "pharmaceutical drug pricing regulation" },
      },
      id: 1,
    }),
  }
);

const result = await response.json();
const report = JSON.parse(result.result.content[0].text);
console.log(`Score: ${report.complianceImpactScore.total} — ${report.complianceImpactScore.grade}`);
console.log(`Recommendation: ${report.complianceImpactScore.recommendation}`);

cURL

# Call a tool directly via the MCP endpoint
curl -X POST "https://regulatory-change-intelligence-mcp.apify.actor/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "enforcement_trend_analysis",
      "arguments": {
        "query": "chemical manufacturing OSHA EPA compliance"
      }
    },
    "id": 1
  }'

# List all available tools
curl -X POST "https://regulatory-change-intelligence-mcp.apify.actor/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -d '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":1}'

How the Regulatory Change Intelligence MCP Server works

Phase 1: Parallel data collection across 13 federal sources

When a tool is called, the server identifies which of the 13 underlying Apify actors are relevant to that tool and fires them in parallel using Promise.all. A compliance_impact_report call queries all 13 sources simultaneously: Federal Register (ryanclinton/federal-register-search), Congress bills (ryanclinton/congress-bill-search), CBP customs rulings (ryanclinton/cbp-customs-rulings), USITC HTS tariff data (ryanclinton/usitc-hts-tariff-search), SEC EDGAR (ryanclinton/edgar-filing-search), OSHA inspections (ryanclinton/osha-inspection-search), EPA ECHO (ryanclinton/epa-echo-search), DOL WHD enforcement (ryanclinton/dol-whd-enforcement), FDA food recalls (ryanclinton/fda-food-recall-monitor), FDA device recalls (ryanclinton/fda-device-recalls), website change monitoring (ryanclinton/website-change-monitor), Senate lobbying (ryanclinton/senate-lobbying-search), and FEC campaign finance (ryanclinton/fec-campaign-finance). Each actor runs with a 120-second timeout and 256 MB memory allocation.

Phase 2: Four-model scoring

Legislative Probability Engine classifies each bill by stage using status field text matching (enacted/signed/became law, passed/agreed to, committee/referred/reported, introduced). Stage weights are additive: enacted bills (+35), passed one chamber (+25), 3+ in committee (+15), Federal Register proposed rules (+5-12), and lobbying intensity (+5). Score is capped at 100 and labeled UNLIKELY / POSSIBLE / LIKELY / NEAR CERTAIN.

Enforcement Trend Detector aggregates per-agency record counts (OSHA, EPA, DOL-WHD, FDA, SEC) and applies tiered scoring: >20 OSHA inspections adds 20 points, >5 adds 12. Federal Register notices containing the terms enforcement, penalty, violation, or compliance add 10 points. The direction label (DORMANT / MODERATE / ACTIVE / INTENSIFYING) is determined at score thresholds 10, 30, 60.

Tariff Impact Analyzer scores from CBP customs ruling counts, USITC HTS entry counts, and Federal Register text filtering for tariff, trade, import, export, customs, duty. Congressional bills with trade-related titles and lobbying filings with trade issue areas contribute secondary signals. Score labels at 15, 40, 70.

Regulatory Domino Effect counts agencies exceeding activity thresholds (>3 records) and adds per-agency base scores (OSHA: +15, EPA: +15, DOL-WHD: +15, FDA: +15, SEC: +10, CBP: +10). When 4+ agencies are simultaneously active, a cascade bonus of +20 is applied. The raw score ranges -100 to +100 and is normalized to 0-100 for composite weighting.

Phase 3: Weighted composite and output assembly

The Compliance Impact Score applies weights: Legislative Probability (30%) + Enforcement Trend (30%) + normalized Domino Effect (25%) + Tariff Impact (15%). The composite is capped 0-100 and mapped to four grade labels. The recommendation field selects from four pre-defined action templates based on score bands (0-20, 20-45, 45-70, 70-100). Full source-count metadata is included alongside the scored output so callers can assess the evidence base.

Tips for best results

1. Use specific industry or regulatory terms in your query. Broad queries like "environmental" return noise from every EPA activity. Specific queries like "PFAS in drinking water EPA maximum contaminant levels" focus all 13 sources on the relevant regulatory program.

2. Run regulatory_pipeline_search first, then compliance_impact_report. The pipeline search is cheaper and faster for a first scan. Escalate to the full report only for topics that show active Federal Register or Congressional activity.

3. Interpret the Domino Effect score in context. A score of 40 (EXPANDING) with 2 active agencies in a sector you operate in is more actionable than a score of 70 with 4 agencies in an unrelated industry. Always check activeAgencies alongside the raw score.

4. Schedule weekly monitoring with Apify Scheduler. Regulatory environments shift over months. A topic that scores 22 this week may score 65 in 90 days after a proposed rule advances to final rule. Set up a scheduled run for your top 5 priority topics.

5. Combine the Legislative Probability label with billStages for nuance. A score of 50 (LIKELY) built on 8 introduced bills with no committee activity is weaker than 50 built on 3 committee bills and 1 passed chamber. The billStages breakdown tells you the pipeline distribution.

6. Use lobbying_pressure_map as a leading indicator. Lobbying spending on a regulatory topic typically precedes rulemaking by 6-24 months. High lobbying activity with low Federal Register activity often means a rule is in early development — use this to build compliance capacity ahead of the curve.

7. Cross-reference agency_guidance_monitor output with enforcement trend findings. When both the guidance monitor and the enforcement trend tool return activity from the same agency in the same week, the probability of an imminent compliance focus is high.

Combine with other Apify actors and MCP servers

Limitations

• US federal regulatory sources only. State, local, and international regulation is not covered. California CPRA, EU GDPR, UK FCA rules, and similar non-US regulatory regimes require separate data sources.
• Data freshness depends on source update frequency. Federal Register data updates daily. Congressional bill status can lag by 24-48 hours. OSHA and EPA enforcement databases typically update weekly. FEC data has filing deadlines that create gaps between activity and availability.
• Scoring is evidence-based, not predictive AI. The four scoring models are deterministic rule-based engines, not machine learning models. They measure the volume and pattern of observable regulatory signals; they do not predict political outcomes or agency leadership decisions.
• Lobbying filings have reporting delays. Senate lobbying disclosure requires quarterly filings. The lobbying pressure scores reflect disclosed filings, not real-time spending. Activity from the current quarter may not yet be visible.
• Sub-regulatory guidance monitoring requires matching query specificity. The website change monitor queries federal agency pages but does not cover every sub-agency microsite. Highly specialized regulatory guidance (e.g., specific CDER division guidance for a particular drug class) may require targeted monitoring configuration.
• The Domino Effect model is symmetric. It measures multi-agency correlation but cannot distinguish coordinated enforcement campaigns from coincidental simultaneous activity in the same sector.
• Tool call timeouts at 120 seconds per underlying actor. In rare cases where source APIs are slow, individual data sources may time out and return empty arrays. The scoring engine handles this gracefully but affected sub-scores will be lower than if all sources returned data.
• FEC campaign finance data is lagged by election cycle reporting. Contribution patterns are most complete for completed reporting periods; real-time political spending during active campaigns may be underrepresented.

Integrations

• Apify API — trigger the MCP server programmatically from your compliance workflow automation
• Webhooks — configure webhook alerts when Compliance Impact Scores exceed a defined threshold for any monitored topic
• Zapier — push high-score regulatory alerts into Slack, Jira, or your GRC ticketing system automatically
• Make — build multi-step compliance monitoring workflows triggered on a schedule or by score conditions
• Google Sheets — export weekly regulatory scan results to a tracking spreadsheet for compliance program documentation
• LangChain / LlamaIndex — use regulatory change intelligence output as a retrieval source in compliance-focused RAG applications
• Claude Desktop / Cursor / Windsurf / Cline — connect directly via MCP protocol for conversational regulatory intelligence inside your AI development environment

❓ FAQ

How far ahead can the regulatory change intelligence MCP predict compliance changes? The system tracks proposed rules during their comment periods (typically 60-180 days) and congressional bills from introduction through enactment. For legislation with strong lobbying signals, the bill_impact_assessment tool can flag pipeline activity 12-24 months before likely enactment. Federal Register proposed rules typically provide 3-6 months of advance notice before a final rule takes effect.

What does the Compliance Impact Score measure, exactly? The score (0-100) measures the intensity of observable regulatory signals around a topic at the time of the query. It is not a probability that your specific company will be investigated. It answers the question: "How much regulatory pressure is building in this area right now?" Higher scores mean more evidence from more sources pointing toward active or imminent regulatory change.

How is this different from Lexis+ Regulatory Tracker or Compliance.ai? Dedicated RegTech platforms provide attorney-curated regulatory libraries and change management workflows, typically at $500-2,500/month per seat. This MCP is a data intelligence layer — it surfaces raw signals from 13 US government databases, scores them, and returns structured JSON. It is designed for teams building compliance automation into AI agents or workflows, not as a replacement for a full compliance management platform. Most users spend under $10/month.

Can I track a specific proposed rule through the rulemaking process? Yes. Call regulatory_pipeline_search with the rule's title or RIN number (Regulation Identifier Number) on a recurring schedule. The Federal Register source tracks documents from Notice of Proposed Rulemaking through Final Rule publication. Pair with agency_guidance_monitor to catch any interim guidance published between the NPRM and final rule.

Does the regulatory change intelligence MCP cover state regulations? No. All 13 data sources are US federal. State-level regulatory activity (California OSHA, state environmental agencies, state securities regulators, PUCs) is not covered. For state regulation, you would need to combine this with state-specific data sources or a third-party state regulatory database.

How does the Regulatory Domino Effect model work? The model checks whether multiple agencies simultaneously exceed their enforcement activity thresholds. When OSHA, EPA, and DOL-WHD all show elevated activity in the same query, the model returns EXPANDING or CASCADING EXPANSION direction. Historically, multi-agency enforcement campaigns follow a pattern where one agency opens an investigation that triggers referrals or parallel investigations at related agencies. The domino score quantifies how many agencies are simultaneously active in the topic area queried.

Is it legal to use this data for compliance monitoring? All 13 data sources are US government public databases (Federal Register, Congress.gov, CBP CROSS, USITC, SEC EDGAR, OSHA enforcement database, EPA ECHO, DOL WHISARD, FDA recall databases, Senate Lobbying Disclosure, FEC). Public government data is freely accessible under US law. See Apify's guide on web scraping legality.

How accurate is the Legislative Probability score? The Legislative Probability Engine is evidence-based: it counts bills at each pipeline stage and correlates them with Federal Register rulemaking volume and lobbying intensity. It is not a political science prediction model and does not account for political leadership changes, budget negotiations, or legislative calendar constraints. Use it to rank regulatory topics by signal strength, not as an absolute probability estimate.

Can I use this MCP with Claude, Cursor, or other AI tools? Yes. The server implements the Model Context Protocol and runs in standby mode on Apify, making it available 24/7 at a fixed URL. It works with any MCP-compatible client: Claude Desktop, Cursor, Windsurf, Cline, and custom MCP clients built with the @modelcontextprotocol/sdk.

What happens if one of the 13 data sources times out during a run? The server handles source failures gracefully. If an underlying actor times out or returns an error, it returns an empty array for that source. The scoring engine processes whatever data is available. The sourceCounts object in the output shows exactly how many records each source returned, so you can see if any sources were missing data for a given run.

Can I schedule this MCP to run weekly compliance scans automatically? Yes. Use Apify Scheduler to run the actor on a weekly or daily schedule, or use webhooks to trigger a scan when specific conditions are met. You can also call the MCP endpoint from any scheduler (cron, n8n, Zapier, Make) that supports HTTP POST requests.

How does regulatory change intelligence relate to ESG compliance monitoring? EPA enforcement trends, OSHA inspection patterns, and DOL WHD wage-hour enforcement are all core ESG regulatory signals. The enforcement_trend_analysis and compliance_impact_report tools surface agency-level enforcement intensity that directly maps to E (environmental), S (labor/safety), and G (SEC disclosure) dimensions. Use the scores to build an evidence base for ESG regulatory exposure assessments.

Help us improve

If you encounter issues, you can help us debug faster by enabling run sharing in your Apify account:

1. Go to Account Settings > Privacy
2. Enable Share runs with public Actor creators

This lets us see your run details when something goes wrong, so we can fix issues faster. Your data is only visible to the actor developer, not publicly.

Responsible use

• This server only accesses publicly available US government regulatory databases.
• All 13 underlying data sources are free public records under US federal law.
• Comply with applicable data protection laws when incorporating regulatory intelligence into AI-assisted decision-making workflows.
• Do not use regulatory change intelligence data to facilitate market manipulation, insider trading, or other securities law violations.
• For guidance on web scraping legality, see Apify's guide.

Support

Found a bug or have a feature request? Open an issue in the Issues tab on this actor's page. For custom solutions or enterprise integrations, reach out through the Apify platform.