Litigation Intelligence MCP Server

Litigation intelligence MCP server that detects lawsuit risk before cases are filed. This server gives any MCP-compatible AI client — Claude, Cursor, Windsurf, Cline — direct access to pre-litigation signals drawn from 7 US government data sources, scored by 4 independent risk models into a composite Litigation Probability Score (0-100).

General counsel, compliance officers, and litigation funders can ask their AI assistant to assess a company's litigation risk in natural language. The server handles all data gathering and scoring behind the scenes, returning structured risk assessments with specific action items in seconds.

What data can you access?

Why use Litigation Intelligence MCP?

Building a pre-litigation risk picture manually means pulling CFPB complaint exports, searching EDGAR, checking EPA ECHO facility records, reading Federal Register PDFs, scanning OFAC lists, and cross-referencing patent databases — all for a single company. A thorough review takes an analyst 4-6 hours and produces a snapshot that is stale within days.

This MCP server automates the entire process. Ask your AI assistant one question. Get back quantified scores, flagged signals, and specific action items across all seven data sources within 30-60 seconds.

• Scheduling — connect the underlying Apify actors on a recurring schedule to track risk trajectories over time
• API access — call any tool programmatically from Python, JavaScript, or any HTTP client
• Parallel execution — all 7 data sources are queried simultaneously, not sequentially
• Monitoring — get Slack or email alerts when litigation scores cross defined thresholds via Apify webhooks
• Integrations — connect outputs to Zapier, Make, Google Sheets, or directly to your GRC platform

MCP Tools

Use cases for litigation intelligence MCP

General counsel early warning

General counsel teams at mid-to-large companies run quarterly litigation risk sweeps across their top counterparties and regulated business lines. Complaint velocity on a specific product, combined with Federal Register enforcement activity, surfaces risk that would otherwise sit in siloed data. This MCP gives legal teams a structured, repeatable process with quantified metrics for board-level risk reporting.

Litigation funding assessment

Litigation funders evaluate case viability before committing capital. Complaint clustering patterns and EPA enforcement trajectories serve as upstream signals of viable litigation — high complaint concentration around a single issue is statistically correlated with subsequent class action filings. This MCP turns that signal extraction from a week-long research exercise into a 60-second query.

Insurance defense and reserve setting

Claims adjusters and actuarial teams model litigation reserves based on complaint trends and enforcement histories. A company showing a SURGING complaint trend with 5+ EPA violations and disputed complaint responses warrants higher reserves than one with STABLE trends and CLEAR enforcement records. Each scoring dimension maps directly to actuarial risk factors.

Corporate compliance risk reporting

Compliance officers preparing board-ready risk reports need quantified scores, not qualitative summaries. This MCP produces numerical scores (0-100) for each risk dimension — litigation probability, class action warning, enforcement trajectory, legislative exposure — alongside the specific signals that drove the score. That structured output feeds directly into compliance dashboards.

Patent landscape and IP litigation monitoring

Technology companies and patent counsel need to track competing patent portfolios before launching products. The monitor_patent_disputes tool queries the USPTO database, groups results by assignee, and surfaces concentration — a single entity holding 20+ patents in your technology space is a material IP litigation risk factor.

Sanctions compliance screening

Financial institutions, legal teams, and compliance departments conducting counterparty due diligence need fast OFAC SDN list verification. The screen_sanctions_liability tool returns a CLEAR / HIGH / CRITICAL classification with match counts and specific match records, directly inside any AI assistant workflow.

How to connect this litigation intelligence MCP server

Step 1 — Get your Apify API token. Go to Apify Console and copy your token from Settings > Integrations. New accounts receive $5 in free monthly credits.

Step 2 — Add the server to your MCP client. The server URL is always https://litigation-intelligence-mcp.apify.actor/mcp. Add your token as a Bearer header or as a URL parameter depending on your client.

Step 3 — Ask your AI assistant. Type a natural-language question: "What is the litigation risk for Acme Financial Services?". The AI calls the right tool automatically.

Step 4 — Review scored results. The response includes numeric scores for each dimension, specific signals that drove the score, and action items prioritized by severity.

Claude Desktop

Add to your claude_desktop_config.json:

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

Cursor / Windsurf / Cline

Point your MCP client to:

https://litigation-intelligence-mcp.apify.actor/mcp

All MCP-compatible clients that support StreamableHTTP transport work with this server.

Token as URL parameter (some clients)

https://litigation-intelligence-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN

Input parameters

Each tool accepts its own parameter set. All parameters are passed at call time — there is no actor-level input configuration for an MCP server.

Example tool calls

Single-dimension litigation probability assessment:

{
  "tool": "assess_litigation_risk",
  "arguments": {
    "company": "Pinnacle Financial Services",
    "product": "personal loans"
  }
}

Full legal landscape report with industry context:

{
  "tool": "generate_legal_landscape_report",
  "arguments": {
    "company": "Acme Chemicals Inc",
    "industry": "chemical manufacturing",
    "product": "industrial solvents"
  }
}

Class action early warning for a specific company:

{
  "tool": "detect_class_action_signals",
  "arguments": {
    "company": "Westbridge Insurance Group"
  }
}

Input tips

• Include industry context in generate_legal_landscape_report — the industry parameter sharpens Federal Register and Congress bill searches, which use keyword matching against broad regulatory databases.
• Use product to narrow financial services assessments — CFPB complaints are categorized by product; adding "credit card" or "mortgage" reduces noise significantly.
• Combine targeted tools before running the full report — use detect_class_action_signals first to gauge whether a deep report is warranted; each tool call is independently priced.
• For sanctions screening, use the legal entity name — OFAC SDN matches against registered entity names. Use the full legal name, not trade names or abbreviations.
• For patent monitoring, use technology keywords rather than company names — patent searches return more relevant results when querying the technology domain (e.g., "neural network inference chip") rather than just the company name.

Output example

The generate_legal_landscape_report tool returns a full structured JSON report:

{
  "company": "Pinnacle Financial Services",
  "compositeScore": 72,
  "riskLevel": "HIGH",
  "litigationProbability": {
    "score": 78,
    "complaintCount": 34,
    "complaintTrend": "SURGING",
    "enforcementActions": 2,
    "edgarFilings": 5,
    "riskLevel": "HIGH",
    "signals": [
      "34 CFPB complaints — elevated litigation risk",
      "Complaint volume surging — 2x+ increase over prior quarter",
      "7 disputed/untimely complaint responses"
    ]
  },
  "classActionWarning": {
    "score": 64,
    "clusterCount": 3,
    "largestCluster": {
      "issue": "Incorrect information on your credit report",
      "count": 12
    },
    "productClusters": [
      { "product": "Credit reporting, credit repair services", "count": 18 },
      { "product": "Debt collection", "count": 9 }
    ],
    "issueClusters": [
      { "issue": "Incorrect information on your credit report", "count": 12 },
      { "issue": "Attempts to collect debt not owed", "count": 8 },
      { "issue": "Communication tactics", "count": 5 }
    ],
    "warningLevel": "WARNING",
    "signals": [
      "\"Incorrect information on your credit report\" — 12 complaints (35% concentration)",
      "3 distinct issue clusters with 5+ complaints each"
    ]
  },
  "enforcementTrajectory": {
    "score": 45,
    "epaViolations": 0,
    "federalRegisterActions": 4,
    "sanctionsExposure": 0,
    "trajectoryDirection": "STABLE",
    "agencies": ["Federal Register"],
    "signals": [
      "4 relevant Federal Register enforcement/rule documents"
    ]
  },
  "legislativeExposure": {
    "score": 55,
    "relevantBills": 9,
    "billsByStage": {
      "introduced": 4,
      "committee": 3,
      "passed_one": 1,
      "passed_both": 0,
      "enacted": 1
    },
    "highImpactBills": 2,
    "exposureLevel": "SIGNIFICANT",
    "signals": [
      "1 enacted bill(s) creating new compliance obligations",
      "1 bill(s) passed one chamber — advancing through Congress",
      "9 relevant bills in Congress — significant legislative attention"
    ]
  },
  "allSignals": [
    "34 CFPB complaints — elevated litigation risk",
    "Complaint volume surging — 2x+ increase over prior quarter",
    "7 disputed/untimely complaint responses",
    "\"Incorrect information on your credit report\" — 12 complaints (35% concentration)",
    "3 distinct issue clusters with 5+ complaints each",
    "4 relevant Federal Register enforcement/rule documents",
    "1 enacted bill(s) creating new compliance obligations",
    "1 bill(s) passed one chamber — advancing through Congress",
    "9 relevant bills in Congress — significant legislative attention"
  ],
  "actionItems": [
    "Complaint volume surging — consider proactive consumer outreach/settlement",
    "New legislation enacted — review compliance program for gaps"
  ]
}

Output fields

Scoring models

The composite Litigation Probability Score combines four independent models:

Litigation Probability (30% weight): Derived from CFPB complaint volume (max 35 points), complaint trend acceleration (max 15 points), EPA enforcement actions (max 20 points), SEC filing presence (max 15 points), and disputed complaint responses (max 15 points). Trend acceleration is computed by comparing the mean complaint rate across the three most recent months to the three prior months. A ratio of 2.0 or above triggers the SURGING designation.

Class Action Warning (25% weight): Issue concentration score — the ratio of complaints about the single top issue to total complaints — is weighted up to 40 points. Cluster size adds up to 30 points, multiple large clusters up to 15 points, and total volume amplification up to 15 points. A top-issue concentration ratio of 30% or higher with at least 10 absolute complaints triggers a named cluster signal.

Enforcement Trajectory (25% weight): EPA VIOLATION and NON-COMPLIANCE facility records (max 30 points), Federal Register enforcement/rule/penalty documents (max 25 points), OFAC SDN matches (max 30 points, weighted heavily at 15 points each), and cross-agency amplification when multiple agencies contribute (max 15 points). A single OFAC match triggers a CRITICAL alert independently.

Legislative Exposure (20% weight): Enacted bills score 15 points each (max 35 total), bills that have passed both or one chamber score 10 and 5 points respectively, committee-stage bills add up to 20 points, total bill volume up to 20 points, and Federal Register proposed/final rules up to 25 points.

How much does it cost to run litigation intelligence queries?

Each tool call costs $0.045 regardless of how many data sources it queries internally. The generate_legal_landscape_report tool queries all 7 sources in parallel for the same $0.045 price.

You can set a maximum spending limit per run on the Apify platform to control costs. The server stops processing when your budget is reached.

Apify's free tier includes $5 of monthly platform credits — approximately 111 tool calls per month at no cost. Compare this to legal data platforms like Dun & Bradstreet Risk Analytics or LexisNexis Risk Solutions that charge $500-2,000/month for institutional subscriptions. Most users spend under $5/month.

How to use litigation intelligence with the API

Python

from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")

# Run the full legal landscape report
run = client.actor("ryanclinton/litigation-intelligence-mcp").call(run_input={})

for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(f"Company: {item.get('company')} | Score: {item.get('compositeScore')} | Risk: {item.get('riskLevel')}")
    for signal in item.get("allSignals", []):
        print(f"  Signal: {signal}")

JavaScript

import { ApifyClient } from "apify-client";

const client = new ApifyClient({ token: "YOUR_API_TOKEN" });

const run = await client.actor("ryanclinton/litigation-intelligence-mcp").call({});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
for (const item of items) {
  console.log(`${item.company} — Score: ${item.compositeScore} (${item.riskLevel})`);
  console.log(`Class action warning: ${item.classActionWarning?.warningLevel}`);
  console.log(`Enforcement trajectory: ${item.enforcementTrajectory?.trajectoryDirection}`);
}

cURL — direct MCP tool call

# Call the generate_legal_landscape_report tool directly via the MCP endpoint
curl -X POST "https://litigation-intelligence-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "generate_legal_landscape_report",
      "arguments": {
        "company": "Acme Financial Group",
        "industry": "consumer finance",
        "product": "auto loans"
      }
    },
    "id": 1
  }'

# Call the sanctions screening tool
curl -X POST "https://litigation-intelligence-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "screen_sanctions_liability",
      "arguments": { "query": "Acme Financial Group" }
    },
    "id": 2
  }'

How Litigation Intelligence MCP works

Phase 1: Parallel data collection

When a tool is called, the server dispatches parallel actor runs across up to 7 Apify wrapper actors using Promise.allSettled. Each sub-actor queries its respective government API: cfpb-consumer-complaints queries the CFPB complaint database, epa-echo-search queries the EPA ECHO facility compliance system, edgar-filing-search queries the SEC EDGAR full-text search, federal-register-search queries the Federal Register API, congress-bill-search queries Congress.gov, ofac-sanctions-search queries the Treasury SDN list, and patent-search queries the USPTO Patent Full-Text Database. Sub-actors run with 256MB memory and a 120-second timeout each. Failed sub-actors return empty arrays rather than failing the whole request — the scoring models degrade gracefully when individual sources are unavailable.

Phase 2: Temporal clustering and trend analysis

The complaint trend engine extracts the date_received field from each CFPB complaint and groups them by YYYY-MM using a regex match pattern /^\d{4}-\d{2}$/. It calculates mean complaint rates across the three most recent months versus the three prior months. The trend ratio drives the DECLINING / STABLE / RISING / SURGING classification (ratios: below 0.7, 0.7-1.3, 1.3-2.0, 2.0+). This temporal pattern is one of the strongest pre-litigation signals — a complaint SURGE in financial services has historically preceded class action filings by 6-18 months.

Phase 3: Issue concentration and class action scoring

The class action model groups complaints by their issue field and product field, sorts by frequency, and extracts the top 10 clusters for each dimension. The concentration score is based on the ratio of the top single issue to total complaints multiplied by 60 — a company where 35% of all complaints concern a single issue ("Incorrect information on your credit report") receives a high concentration score regardless of absolute volume. This mirrors the typicality requirement in class action certification: a single dominant issue affecting many people is exactly the pattern courts look for.

Phase 4: Composite scoring and action item generation

The composite score is a weighted average: Litigation Probability 30%, Enforcement Trajectory 25%, Class Action Warning 25%, Legislative Exposure 20%. Each sub-model contributes signals (human-readable text strings) that are merged into allSignals. Action items are generated conditionally from critical-level triggers: IMMINENT class action warning triggers an immediate counsel engagement recommendation, any OFAC sanctions match triggers an enhanced due diligence alert, a SURGING complaint trend triggers a settlement outreach recommendation, enacted legislation triggers a compliance gap review, and 3+ EPA violations trigger an environmental audit recommendation.

Tips for best results

1. Run detect_class_action_signals before investing in a full report. At $0.045 per call, using the targeted tool first to gauge whether a company has significant complaint clustering helps you prioritize which companies warrant the full 7-source report.

2. Add product context for financial services companies. CFPB complaint searches without a product term return all complaints for a company across all products. Specifying "mortgage", "credit card", or "auto loan" scopes the complaint analysis to the specific business line under review.

3. Use industry terms in analyze_legislative_exposure. Congress bill searches use keyword matching. "Consumer financial protection" returns more relevant bills than the company name alone when assessing a bank's legislative exposure.

4. Cross-check enforcement trajectory with the full report. The track_enforcement_trends tool returns raw EPA details and OFAC matches in addition to the scored output. The raw data often contains facility names, violation dates, and enforcement action types useful for legal memo drafting.

5. Schedule monthly monitoring for portfolio companies. Use Apify's built-in scheduler to run assess_litigation_risk for each portfolio company monthly and store scores in a dataset. Tracking score changes over time is more predictive than any single snapshot.

6. For patent monitoring, search by technology domain first, then by assignee. Running monitor_patent_disputes with a technology keyword returns the full landscape. Then re-run with the top assignee to get their complete portfolio — this two-step approach surfaces both competitive landscape and specific entity risk.

7. Pipe outputs into your GRC platform via webhooks. When a company's composite score crosses 75 (CRITICAL threshold), an Apify webhook can POST the full JSON report to your GRC system or Slack channel automatically without any manual review step.

Combine with other Apify actors

Limitations

• No access to court filing databases. PACER, state court systems, and LexisNexis CourtLink are not queried. This server detects pre-litigation signals — the upstream data that precedes filings — not the filings themselves.
• CFPB complaints are limited to financial products and services. Companies outside the financial sector (manufacturing, healthcare, technology) will show zero CFPB complaints, which reduces the Litigation Probability score's relevance for those sectors.
• EPA ECHO is facility-based. A company must have registered facilities in the EPA ECHO system. Holding companies, shell entities, and non-industrial companies may return no EPA records even if their subsidiaries have violations.
• Congressional bill search is keyword-based. Bills that affect your sector but do not contain the company or industry keyword in their title or description will not be retrieved. Legislative exposure scores may undercount for broad regulatory changes.
• OFAC SDN matching is lexical, not fuzzy. The search uses the company name as a query string. Name variations, transliterations, or aliases not present in the query string may miss legitimate matches. Always supplement with a dedicated sanctions screening service for high-stakes decisions.
• Patent search returns recently filed and published patents. Pending applications under confidentiality (pre-publication) are not included. Patent landscape analysis reflects the published record, not the complete pipeline.
• Scores are directional signals, not legal opinions. A score of 85 does not mean litigation will occur — it means multiple upstream indicators are elevated. A score of 10 does not mean a company is litigation-safe. Always engage qualified legal counsel for final assessment.
• Complaint volume is affected by CFPB database search limits. High-volume companies may have more complaints than are returned in a single query. Scores may understate risk for very large financial institutions.

Integrations

• Apify API — trigger litigation risk assessments programmatically as part of M&A due diligence or vendor onboarding workflows
• Zapier — route HIGH or CRITICAL litigation scores automatically to a legal review queue in your case management system
• Make — build multi-step compliance workflows that trigger additional research when enforcement trajectory reaches ESCALATING
• Webhooks — push score-crossing alerts to Slack, Teams, or PagerDuty when composite scores exceed a defined threshold
• Google Sheets — maintain a running litigation risk register for portfolio companies with historical score tracking
• LangChain / LlamaIndex — feed legal landscape reports as structured context to RAG pipelines for AI-powered legal memo drafting

Troubleshooting

Scores are unexpectedly low for a company you know has litigation history — The server detects pre-litigation signals from upstream data, not active court cases. A company may have extensive past litigation that is not reflected in current CFPB complaint volumes or EPA enforcement records. The scores reflect present-tense risk signals, not historical litigation records. Combine with Company Deep Research for historical context.

EPA and CFPB scores are zero for a non-financial or non-industrial company — CFPB only covers financial services products. EPA ECHO only covers registered facilities. For technology companies, retail businesses, or service-sector companies, these dimensions will naturally score near zero. The enforcement trajectory and legislative exposure dimensions will still provide value. Use analyze_legislative_exposure and monitor_patent_disputes as the primary tools for these sectors.

generate_legal_landscape_report takes longer than expected — The full report queries 7 sub-actors in parallel with a 120-second timeout per sub-actor. Peak Apify platform load or slow underlying government APIs (particularly EPA ECHO and Federal Register) can extend response time to 60-90 seconds. This is normal. Do not retry — the first call is in progress.

OFAC screening returns unexpected matches — The OFAC SDN list uses fuzzy matching at the government database level. Common corporate name components (words like "National", "International", "Capital") can match SDN entries for unrelated entities. Always review the returned match records against the full SDN entry — look at country, address, and entity type before concluding a match is a genuine sanctions exposure.

Class action warning shows WATCH or WARNING but complaints look low in number — The class action model is sensitive to concentration rather than absolute volume. Ten complaints where 8 share the same issue string will score higher than 50 complaints spread evenly across 20 different issues. This is by design — issue concentration is the primary class action predictor, not volume alone.

Responsible use

• This server queries only publicly available US government databases. All data sources are open access.
• OFAC sanctions data should be used as a first-pass screen only. Formal sanctions compliance programs require certified screening tools and legal review.
• Litigation risk scores are analytical signals, not legal advice. Do not act on scores without qualified legal counsel review.
• Comply with GDPR, CCPA, and applicable data protection regulations when using company and individual data in due diligence workflows.
• For guidance on public data usage and web scraping legality, see Apify's guide.

FAQ

How does litigation intelligence MCP detect class action risk? The class action model analyzes CFPB complaint records for issue concentration — the percentage of all complaints that share a single issue type. When one issue dominates (30%+ concentration with 10+ absolute complaints), this mirrors the "typicality" requirement in class certification: one dominant problem affecting many people. The model also detects temporal complaint spikes, which historically precede filings by 6-18 months.

Does litigation intelligence MCP access court filings or PACER? No. This server detects the upstream signals that precede litigation — consumer complaints, regulatory enforcement actions, legislative pressure — not the court filings themselves. If you need active docket monitoring, pair this server with a dedicated court filing service. The pre-litigation signals here are most valuable precisely because they appear before cases are filed.

How accurate is the litigation probability scoring? The scores are calibrated directional signals based on publicly observable data. A company with a CFPB complaint SURGE, multiple EPA violations, and IMMINENT class action concentration has empirically observable risk factors. The models do not claim statistical validation against a historical case outcome dataset. Treat scores as a structured research starting point, not a probability estimate with confidence intervals.

Is it legal to use public government data for litigation risk assessment? Yes. All seven data sources — CFPB, SEC EDGAR, EPA ECHO, Federal Register, Congress.gov, OFAC, and USPTO — are US government public databases maintained for public access. There are no legal restrictions on querying or analyzing them. See Apify's guide on web scraping legality for broader context.

How long does a typical litigation intelligence query take? Single-dimension tools (assess_litigation_risk, detect_class_action_signals, screen_sanctions_liability) typically return in 10-30 seconds. The generate_legal_landscape_report tool queries 7 sources in parallel and typically takes 30-90 seconds depending on government API response times. Sub-actor execution uses a 120-second timeout per source.

Can I use litigation intelligence MCP to monitor a portfolio of companies continuously? Yes. The recommended approach is to call assess_litigation_risk or generate_legal_landscape_report for each portfolio company on a monthly schedule via the Apify platform scheduler. Store results in a dataset and use webhooks to trigger alerts when scores cross defined thresholds. At $0.045 per call, monitoring 20 companies monthly costs $0.90.

How is this different from LexisNexis Risk Solutions or Dun & Bradstreet? LexisNexis and D&B aggregate data into proprietary databases with institutional subscription pricing ($500-2,000/month or more). This MCP queries the original government sources directly at query time, returning current data without licensing lag. It also runs inside any MCP-compatible AI assistant, meaning your existing legal AI workflow gets litigation intelligence without a separate platform login. The tradeoff: no court docket access, no proprietary enrichment.

What happens if one of the 7 data sources is unavailable? The server uses Promise.allSettled — if any sub-actor fails or times out, that source returns an empty array and the scoring models continue with the available data. The response will reflect lower scores on dimensions where data was unavailable, but the call will complete and not return an error.

Can litigation intelligence MCP be used for M&A due diligence? Yes, and this is one of the strongest use cases. Run generate_legal_landscape_report on acquisition targets during initial screening to surface material litigation risk signals before committing to full legal due diligence. A CRITICAL composite score or IMMINENT class action warning warrants deeper investigation. This does not replace formal legal due diligence — it prioritizes where to focus it.

What types of EPA violations does the enforcement model detect? The EPA ECHO filter matches facility compliance status records containing "VIOLATION", "ENFORCEMENT", or "NON-COMPLIANCE" in the complianceStatus or status field. These correspond to formal Notice of Violation (NOV), penalty assessment, and compliance schedule records in the ECHO database. General permit conditions and self-disclosed minor deviations that have been resolved may not appear.

Can I run the MCP tools without an AI assistant? Yes. The MCP endpoint is a standard HTTP POST endpoint at https://litigation-intelligence-mcp.apify.actor/mcp. You can call any tool directly via cURL, Python's requests library, or any HTTP client using the JSON-RPC 2.0 format shown in the API examples above. No AI client is required.

How is the composite score weighted across the four models? Litigation Probability contributes 30%, Enforcement Trajectory 25%, Class Action Warning 25%, and Legislative Exposure 20%. The weights reflect the relative predictive value of each signal type for near-term litigation: complaint velocity and enforcement are the strongest direct predictors; class action clustering is a leading indicator; legislative exposure is a lagging but impactful structural factor.

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.

Support

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