M&A Target Intelligence MCP Server

M&A target intelligence at your AI agent's fingertips — this MCP server runs pre-acquisition due diligence screening by orchestrating 16 Apify actors in parallel across financial filings, IP databases, workforce signals, technology assessment, and reputation data. It produces an Acquisition Readiness Score (0-100) with dimensional scoring across five factors and automatic deal breaker detection. Built for corporate development teams, PE firms, venture investors, and financial analysts who want fast, programmatic target screening without expensive data subscriptions.

Connect once via the Model Context Protocol and your AI assistant — Claude, Cursor, Windsurf, or any MCP client — can assess acquisition targets, compare candidates, and surface red flags across the entire due diligence spectrum in a single tool call. The server runs in Apify Standby mode, meaning it stays warm and responds to queries immediately with no cold-start delay.

What data can you extract?

Why use M&A Target Intelligence MCP Server?

Manual pre-acquisition screening is slow and expensive. A typical analyst spends 2-3 days gathering SEC filings, checking patent databases, reading reviews, and mapping the tech stack — for a single target. At $300+/hour for financial advisors, even a preliminary screen costs thousands. Enterprise data platforms like Capital IQ or PitchBook charge $20,000-40,000 per year for similar coverage.

This MCP server automates the entire initial screening process. Your AI agent calls one tool and receives structured, scored intelligence across 16 data sources in under three minutes, at a fraction of the cost.

• Scheduling — monitor deal pipeline targets weekly to catch changes in insider sentiment, hiring velocity, or complaint volumes
• API access — integrate target screening directly into Python, JavaScript, or any HTTP workflow
• Proxy rotation — all underlying actors use Apify's built-in proxy infrastructure for reliable data collection
• Monitoring — receive Slack or email alerts when a target's acquisition readiness score shifts materially
• Integrations — pipe scored targets into Airtable, HubSpot, Notion, Zapier, or any webhook-compatible deal tracking system

Features

• 8 specialized MCP tools covering every phase of pre-acquisition screening from financial health to market position
• 16 parallel data sources executed simultaneously — full acquisition readiness assessment completes in under 3 minutes
• Acquisition Readiness Score (0-100) computed across 5 weighted dimensions: Financial Health (25 pts), IP Portfolio (20 pts), Workforce Stability (20 pts), Technology Maturity (20 pts), Market Position (15 pts)
• 5-tier grade system — PRIME TARGET, STRONG TARGET, MODERATE TARGET, WEAK TARGET, NOT RECOMMENDED — with a plain-language recommendation
• Automatic deal breaker detection — flags massive insider selling with zero buys, CFPB complaint counts above 200, and zero IP protection on technology-heavy targets
• Insider trading sentiment analysis — compares Form 4 buy/sell ratios and applies a negative flag when sells exceed buys by 2x with more than 5 total transactions
• IP geographic coverage mapping — tracks US (USPTO), European (EPO), and EU trademark (EUIPO) coverage separately and awards bonus points for multi-jurisdiction protection
• Tech debt scoring — detects legacy frameworks (jQuery, AngularJS, Backbone, CoffeeScript, Flash, Silverlight) and subtracts value relative to modern stack presence
• Modern stack bonus — awards additional points when 3+ modern technologies (React, Vue, Next.js, TypeScript, Kubernetes, Docker, GraphQL, Terraform) are detected
• R&D intensity scoring — calculates the percentage of engineering/research job postings as a proxy for innovation investment
• Hiring velocity classification — AGGRESSIVE (30+ postings), HEALTHY (10-30), MODERATE (1-9), STAGNANT (0)
• Department diversity scoring — maps postings across engineering, sales, marketing, product, and operations to flag single-function organizations
• Standby mode deployment — server stays warm with no cold-start latency; connects instantly from any MCP client
• Pay-per-tool pricing — each tool call is charged individually at $0.045, so focused assessments cost less than full scans

Use cases for M&A target intelligence

Pre-LOI acquisition screening

Corporate development teams screening 10-20 targets before issuing a letter of intent. Run acquisition_readiness_score for each candidate and rank by composite score, grade, and deal breaker count. A two-hour screening process replaces two weeks of manual research and surfaces the highest-potential targets for deeper financial due diligence.

Private equity deal sourcing

PE analysts building proprietary deal flow pipelines who need rapid, repeatable screening across sectors. The scoring model works for both public companies (full SEC data available) and private targets (job postings, tech stack, reviews, and competitive intelligence still produce meaningful scores). Integrate with your deal CRM via webhooks for automated pipeline scoring.

Intellectual property valuation

IP and licensing teams assessing patent portfolio depth before an acquisition. The target_ip_portfolio tool queries USPTO, EPO, and EUIPO simultaneously and maps geographic coverage. Patent counts across US and European jurisdictions serve as a proxy for IP moat strength and potential licensing revenue.

Technology due diligence

Engineering leaders and CTOs assessing a target's technology maturity before a tech acquisition. The target_technology_assessment tool fingerprints the target's website stack, scans GitHub for open source activity, and flags tech debt signals in legacy frameworks — all before the first technical interview.

Competitor acquisition monitoring

Strategy teams tracking whether a competitor is becoming an acquisition target. Schedule weekly target_regulatory_exposure runs to detect sudden changes in insider trading patterns, spikes in CFPB complaints, or reductions in hiring velocity that signal distress.

Reputation risk assessment

Brand and communications teams checking whether a target carries hidden reputation liabilities. The target_reputation_scan tool aggregates Trustpilot and multi-platform reviews, computes a weighted average rating, and classifies sentiment. Average ratings below 3.0 trigger a POOR classification that feeds into the composite score.

How to use M&A target intelligence tools

1. Connect the MCP server — Add the server URL https://m-and-a-target-intelligence-mcp.apify.actor/mcp to your MCP client configuration (Claude Desktop, Cursor, Windsurf, or any compatible client). Provide your Apify API token as the bearer token.
2. Configure your query — Tell your AI assistant the company name to assess. Optionally provide the domain (e.g., acmecorp.com) for tech stack detection and the GitHub organization handle for repository scanning. The server infers reasonable defaults when these are omitted.
3. Choose a tool or run a full scan — Use individual tools like target_ip_portfolio for focused queries, or call acquisition_readiness_score to run all 16 data sources at once. The full scan takes 2-3 minutes.
4. Review scored results — The response includes dimension scores, deal breaker flags, a grade (PRIME TARGET through NOT RECOMMENDED), and a plain-language recommendation you can paste directly into a deal memo.

MCP tools

Tool parameters

Input tips

• Provide the domain explicitly when the company name does not match the domain — auto-inference works for simple names but fails for branded domains like "stripe.com" vs "Stripe Inc".
• Use the full legal name for SEC and patent lookups — abbreviated or brand names may miss filings. "Meta Platforms Inc" returns more filings than "Meta".
• Run individual tools for cost control — if you only need IP data, call target_ip_portfolio at $0.045 rather than the full acquisition_readiness_score.
• Batch multiple targets sequentially — run acquisition_readiness_score for each candidate and compare the composite scores side-by-side in your AI chat session.
• Set a spending limit in Apify to cap costs per run automatically. The server checks the limit before each tool call and returns a clean error message if reached.

Output example

{
  "company": "Pinnacle Analytics Inc",
  "acquisitionReadinessScore": 74,
  "grade": "STRONG TARGET",
  "dimensions": {
    "financialHealth": {
      "score": 19,
      "max": 25,
      "findings": [
        "18 SEC filing(s) — financial transparency available",
        "4 annual reports (10-K) — multi-year financial history",
        "Insider sentiment POSITIVE: 8 buys vs 3 sells — management believes in growth",
        "No CFPB complaints — clean consumer track record"
      ]
    },
    "ipPortfolio": {
      "score": 16,
      "max": 20,
      "findings": [
        "34 USPTO patents — strong US IP portfolio",
        "11 EPO patents — international IP coverage",
        "7 EUIPO trademark(s)",
        "IP coverage spans US and EU — geographic diversity"
      ]
    },
    "workforceStability": {
      "score": 17,
      "max": 20,
      "findings": [
        "47 active job postings — aggressive growth hiring",
        "Hiring across 5 departments — well-rounded organization",
        "68% R&D roles — innovation-focused"
      ]
    },
    "technologyMaturity": {
      "score": 15,
      "max": 20,
      "findings": [
        "23 technologies detected — mature tech stack",
        "14 public GitHub repos",
        "No major tech debt signals in detected stack",
        "Modern tech stack: React, TypeScript, Next.js, Docker, Kubernetes"
      ]
    },
    "marketPosition": {
      "score": 7,
      "max": 15,
      "findings": [
        "Average review rating 4.3/5 across 312 reviews — strong reputation",
        "Competitive intelligence data available for market positioning analysis",
        "Company research data available",
        "4 top-10 SERP ranking(s) — strong search visibility"
      ]
    }
  },
  "dealBreakers": [],
  "recommendation": "Strong acquisition target. Proceed to detailed due diligence and valuation.",
  "dataSources": {
    "secFilings": 18,
    "insiderTrades": 11,
    "cfpbComplaints": 0,
    "usptoPatents": 34,
    "epoPatents": 11,
    "trademarks": 7,
    "jobPostings": 47,
    "techStackItems": 23,
    "githubRepos": 14,
    "reviews": 312,
    "competitiveIntel": 6,
    "serpRankings": 20
  }
}

Output fields

How much does it cost to screen acquisition targets?

Each MCP tool call costs $0.045. That is the full price — no platform fees, no subscription. The acquisition_readiness_score tool, which queries all 16 data sources, still costs $0.045 per company assessed.

You can set a maximum spending limit per run in Apify to control costs. The server checks the limit before each tool call and returns a graceful error if the budget is reached rather than continuing to charge.

Compare this to Capital IQ or PitchBook at $20,000-40,000 per year, or to manual analyst time at $300+/hour per target. Most corporate development teams screen 20-50 targets per quarter and spend under $3 total with this server.

How to connect and use the API

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "m-and-a-target-intelligence": {
      "url": "https://m-and-a-target-intelligence-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

Python (with MCP client)

import httpx
import json

APIFY_TOKEN = "YOUR_APIFY_TOKEN"
MCP_URL = "https://m-and-a-target-intelligence-mcp.apify.actor/mcp"

payload = {
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
        "name": "acquisition_readiness_score",
        "arguments": {
            "companyName": "Pinnacle Analytics Inc",
            "domain": "pinnacleanalytics.com",
            "githubOrg": "pinnacle-analytics"
        }
    },
    "id": 1
}

response = httpx.post(
    MCP_URL,
    json=payload,
    headers={"Authorization": f"Bearer {APIFY_TOKEN}"}
)

result = response.json()
data = json.loads(result["result"]["content"][0]["text"])
print(f"Company: {data['company']}")
print(f"Score: {data['acquisitionReadinessScore']}/100 — {data['grade']}")
print(f"Deal breakers: {data['dealBreakers'] or 'None'}")
print(f"Recommendation: {data['recommendation']}")

JavaScript

const APIFY_TOKEN = "YOUR_APIFY_TOKEN";
const MCP_URL = "https://m-and-a-target-intelligence-mcp.apify.actor/mcp";

const response = await fetch(MCP_URL, {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${APIFY_TOKEN}`,
  },
  body: JSON.stringify({
    jsonrpc: "2.0",
    method: "tools/call",
    params: {
      name: "acquisition_readiness_score",
      arguments: {
        companyName: "Pinnacle Analytics Inc",
        domain: "pinnacleanalytics.com",
      },
    },
    id: 1,
  }),
});

const result = await response.json();
const data = JSON.parse(result.result.content[0].text);
console.log(`${data.company}: ${data.acquisitionReadinessScore}/100 — ${data.grade}`);
for (const [dim, detail] of Object.entries(data.dimensions)) {
  console.log(`  ${dim}: ${detail.score}/${detail.max}`);
}
if (data.dealBreakers.length > 0) {
  console.warn("DEAL BREAKERS:", data.dealBreakers);
}

cURL

# Run a full acquisition readiness assessment
curl -X POST "https://m-and-a-target-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": "acquisition_readiness_score",
      "arguments": {
        "companyName": "Pinnacle Analytics Inc",
        "domain": "pinnacleanalytics.com"
      }
    },
    "id": 1
  }'

# Run an IP-only assessment (lower cost)
curl -X POST "https://m-and-a-target-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": "target_ip_portfolio",
      "arguments": { "companyName": "Pinnacle Analytics Inc" }
    },
    "id": 2
  }'

How M&A Target Intelligence MCP Server works

Phase 1: Parallel data collection

When a tool call arrives, the server immediately fans out to the relevant Apify actors using runActorsParallel(). The full acquisition_readiness_score tool launches all 16 actors simultaneously — SEC EDGAR, SEC EDGAR Analyzer, SEC Insider Trading, CFPB, USPTO, EPO, EUIPO, Job Market Intelligence, Website Tech Stack Detector, GitHub, Trustpilot, Multi-Review Analyzer, SaaS Competitive Intel, Company Deep Research, Shopify Intelligence, and SERP Rank Tracker. Each actor is called via the Apify client with a 120-second timeout and 256 MB memory allocation. Actors that fail return empty arrays rather than throwing, so a partial data availability never breaks the scoring.

Phase 2: Dimensional scoring

The computeAcquisitionScore() function in scoring.ts evaluates five independent dimensions. Financial Health (0-25) weights SEC filing existence (8 pts for any filings, +4 pts for 3+ annual 10-K reports), insider sentiment (+6 for net buying, -0 for net selling), and CFPB complaint volume (+5 for zero complaints, scaling down to 0 for 10+ complaints). IP Portfolio (0-20) scores USPTO patent count in three tiers (2/5/8 pts), EPO patents in two tiers (2/5 pts), EUIPO trademarks in three tiers (1/3/5 pts), and awards a 2-point geographic diversity bonus for multi-jurisdiction coverage. Workforce (0-20) scores hiring velocity (4/7/10 pts), department diversity (3/6 pts for 2/4+ departments), and R&D intensity (+4 pts when engineering/research roles exceed 40% of postings). Technology (0-20) scores stack depth in three tiers (2/4/6 pts), GitHub repo count in three tiers (1/3/5 pts), tech debt penalty when legacy frameworks are detected, and a 5-point bonus for 3+ modern frameworks. Market Position (0-15) scores review average (3/5 pts for 3.0+/4.0+ ratings), adds 3 pts for competitive intelligence, 2 pts for company research, 2 pts for Shopify presence, and 3 pts for at least one top-10 SERP ranking.

Phase 3: Deal breaker detection

Before computing the composite score, identifyDealBreakers() checks three hard conditions. Massive insider selling: if sell transactions exceed 10 and buy transactions are zero, this is flagged as a critical signal that insiders are exiting ahead of bad news. Extreme CFPB complaints: counts above 200 indicate severe consumer satisfaction failure that would likely impair post-acquisition brand value. IP vacuum: if a technology-heavy target (technology maturity score above 10) has zero patents and zero trademarks, the absence of IP protection is flagged as a structural weakness.

Phase 4: Grade and recommendation

The composite score maps to one of five grades — PRIME TARGET (80-100), STRONG TARGET (60-79), MODERATE TARGET (40-59), WEAK TARGET (20-39), NOT RECOMMENDED (0-19). The recommendation field outputs a plain-language string. If deal breakers are present, the recommendation always includes the specific breaker text and a caution notice regardless of the numeric score.

Tips for best results

1. Always provide the domain parameter for technology targets. The tech stack detector and Trustpilot scraper use the domain directly. Without it, the server guesses {companyname}.com, which fails for companies with non-obvious domains like stripe.com vs "Stripe Inc".
2. Use the full legal entity name for public companies. SEC and insider trading lookups search by exact company name. "Meta Platforms Inc" returns far more filings than "Meta" or "Facebook". Check EDGAR first if unsure.
3. Run focused tools for rapid pre-screening. If you are filtering a long list, start with target_regulatory_exposure (insider selling + CFPB) and target_ip_portfolio to eliminate clear negatives before running the full assessment. This costs $0.09 per candidate instead of $0.045.
4. Cross-reference the workforce tool output with the tech tool. A company with 70%+ R&D job postings but an outdated tech stack may be in the middle of a replatform — a potential value-add opportunity or a risk depending on execution.
5. Compare candidates by dimension, not just total score. Two companies with a score of 65 can have very different profiles: one might be STRONG on IP (18/20) but WEAK on financial health (8/25), while another is the inverse. Dimension-level comparison informs acquisition thesis.
6. Schedule weekly regulatory exposure scans on your top pipeline targets. Sudden changes in insider sentiment or complaint volume spikes are early warning signals. Use Apify's scheduler and webhooks to push alerts to Slack or your deal tracking system.
7. Supplement with WHOIS data for private targets. For companies with no SEC filings, the WHOIS Domain Lookup actor adds domain age and registration data — older domains correlate with more established businesses.

Combine with other Apify actors

Limitations

• Private company financial data is limited. SEC filings are only available for public US companies. The Financial Health dimension scores at most 2/25 for private targets with no regulatory filings.
• CFPB complaints are only relevant for financial services companies. Retail, SaaS, and manufacturing targets will have zero CFPB records — this is expected, not a positive signal. The scoring model partially accounts for this but does not apply industry adjustment factors.
• Patent coverage is US (USPTO) and EU (EPO + EUIPO) only. Japanese (JPO), Chinese (CNIPA), and international PCT applications are not included. Targets with Asia-Pacific IP exposure will be underscored on the IP dimension.
• Tech stack detection requires a live website. If the target's domain is down, behind heavy authentication, or a pure mobile app, the technology assessment will return zero items and score 0/20 on that dimension.
• Hiring data reflects public job boards. Companies that hire primarily through internal referrals, executive search, or confidential listings will appear to have lower hiring velocity than their actual growth rate.
• Review data depends on public review platform coverage. B2B software companies with few consumer-facing interactions may have no Trustpilot presence. The reputation scan returns NO_DATA for these targets rather than inferring a score.
• The scoring model is a screening signal, not a valuation. The Acquisition Readiness Score assesses strategic attractiveness, not enterprise value or financial metrics. It is designed to prioritize targets for deeper analysis, not to replace financial modeling, legal due diligence, or advisors.
• SERP data reflects brand search visibility only. The model queries the company name as a keyword. Strong rankings for brand terms signal market awareness but do not indicate product-market fit, revenue, or competitive defensibility.

Integrations

• Apify API — call the MCP server directly via HTTP POST from any language or automation platform without an MCP client
• Zapier — trigger acquisition screenings from new rows in a deal tracking spreadsheet and push scored results to Airtable or Notion
• Make — build automated M&A pipeline workflows that screen batches of targets and route by score into different deal stages
• Webhooks — receive Slack notifications when a scheduled target scan completes or when deal breakers are detected
• Google Sheets — export acquisition readiness scores and dimensional breakdowns to a deal comparison spreadsheet automatically
• LangChain / LlamaIndex — wrap this MCP server as a tool in a multi-step AI workflow that synthesizes M&A intelligence with internal financial models

Troubleshooting

• Score is unexpectedly low for a known strong company. The most common cause is a company name mismatch. SEC filings, patents, and job board searches are sensitive to exact naming. Try the full legal entity name (e.g., "Alphabet Inc" instead of "Google"). Also provide the domain explicitly — without it, the tech stack and review lookups may target the wrong website.

• Financial Health score is 2/25 for a clearly public company. This usually means the company name passed to SEC EDGAR did not match the registrant name exactly. Check the company's SEC filing page directly and use the exact registered entity name. Some subsidiaries file under parent company names.

• IP Portfolio shows 0 despite the company holding patents. Patent searches on USPTO and EPO use keyword matching. Short or common company names (e.g., "Apex" or "Global Systems") may return too many false positives or miss the specific entity. Append the industry or location to disambiguate: "Apex Semiconductor Inc".

• Technology assessment returns zero items. The tech stack detector visits the company's primary domain. If the domain redirects to a marketing page hosted on a third-party platform or is under construction, fingerprinting returns nothing. Try specifying the exact domain including subdomain if the main product runs on app.company.com.

• Tool calls time out after 120 seconds. The server allocates 120 seconds per underlying actor call. If one data source is slow, the parallel calls still complete. If the entire tool times out, your MCP client's connection timeout may be shorter than the server's processing time. Increase the client timeout to 180+ seconds for acquisition_readiness_score.

Responsible use

• This server only queries publicly available data sources: SEC EDGAR filings, USPTO and EPO patent databases, EUIPO trademark records, public job boards, public GitHub repositories, and published customer reviews.
• Do not use M&A intelligence outputs to trade securities ahead of announcements. Insider trading laws apply regardless of the data source.
• Comply with applicable data protection and financial regulation in your jurisdiction when using this data for investment decisions.
• The Acquisition Readiness Score is an automated screening signal derived from alternative data. It is not investment advice and does not constitute a fairness opinion, valuation, or financial analysis.
• For guidance on web scraping legality, see Apify's guide.

FAQ

How many acquisition targets can I screen in one session? There is no per-session limit. Call acquisition_readiness_score for each target sequentially within your MCP client session. Each call costs $0.045, so screening 20 targets costs $0.90. Set a spending limit in Apify to cap total session costs.

Does M&A target intelligence work for private companies? Partially. SEC filing data is only available for public US companies. For private targets, the scoring model still evaluates job postings, tech stack, GitHub activity, customer reviews, competitive positioning, and SERP visibility — typically yielding meaningful scores on 4 of the 5 dimensions. Expect Financial Health scores of 2-5/25 for private companies.

How is this different from Capital IQ, PitchBook, or Bloomberg? Those platforms provide structured financial data from proprietary databases and require $20,000-40,000 annual contracts. This server aggregates live alternative data — insider sentiment, job posting velocity, tech stack, patent filings, and review scores — in real time and via MCP so an AI agent can use the data directly. The two approaches are complementary: use this server for pre-screening and pattern detection, then move to a financial data platform for detailed valuation work on shortlisted targets.

How accurate is the Acquisition Readiness Score? The score reflects signal density, not absolute quality. A company with abundant public data (many SEC filings, patents, job postings, and reviews) will score higher than an identical company with sparse public data. Treat scores as a relative ranking tool within a comparable peer group rather than as an absolute measure of acquisition attractiveness.

What triggers a deal breaker flag? Three conditions trigger deal breakers: (1) more than 10 insider sell transactions with zero buys — indicating insiders are exiting; (2) more than 200 CFPB consumer complaints — indicating severe consumer satisfaction failure in a financial services company; (3) zero IP protection (no patents, no trademarks) combined with a Technology Maturity score above 10 — indicating unprotected technology assets.

Can I screen acquisition targets with this on a schedule? Yes. Use Apify's built-in scheduler to run the server on a recurring basis and track score changes over time. Combine with webhooks to push delta alerts to Slack or email when a target's score changes by more than 10 points.

How current is the data? All data is fetched live at query time. SEC filings reflect EDGAR's latest index, which updates within hours of filing. USPTO and EPO patent data updates weekly. Job postings reflect live board listings. Review data pulls the most recent reviews available on each platform at query time.

Is it legal to use this data for M&A screening? All sources are publicly available. SEC filings are public record by regulation. Patent and trademark registrations are public by statute. Job postings are published for recruitment. Review data is publicly visible. Using public data for investment screening is legal in all major jurisdictions. See Apify's guide on web scraping legality.

Can I use M&A target intelligence with Cursor or Windsurf? Yes. The server implements the MCP Streamable HTTP transport protocol and is compatible with any MCP client. Add the server URL and your Apify token to your Cursor or Windsurf MCP configuration, and the tools will appear in your assistant's tool list immediately.

What happens if one of the 16 data sources is unavailable? The server handles failures gracefully. Each underlying actor call is wrapped in a try/catch that returns an empty array on error. A single source failure lowers the data density and may reduce the composite score slightly, but it never causes the tool call to fail. The dataSources object in the response shows exactly how many records each source returned.

How do I compare two acquisition targets side by side? Run acquisition_readiness_score for each target in the same chat session and ask your AI assistant to compare them. The dimensional scores (financialHealth, ipPortfolio, workforceStability, technologyMaturity, marketPosition) are directly comparable across companies.

Does this MCP server store my queries or results? The server is stateless. Queries are not logged beyond Apify's standard run logging. Results are stored temporarily in the Apify dataset associated with each underlying actor run and expire per Apify's standard data retention policy.

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 deal screening workflows or enterprise integrations with proprietary data sources, reach out through the Apify platform.