Influencer Brand Safety Intelligence MCP Server

Creator vetting and brand risk intelligence via the Model Context Protocol. This MCP server orchestrates 9 data sources for brand safety screening, audience authenticity verification, controversy risk analysis, platform diversification scoring, historical content auditing, sanctions/watchlist checking, creator comparison, and comprehensive brand fit assessment. Produces a Composite Brand Fit Score (0-100) with verdicts. Built for brand marketers, influencer agencies, legal/compliance teams, and PR crisis teams.

What data can you access?

Data Point	Source
Social media presence and engagement quality	Bluesky Social Search
Brand and creator consumer review reputation	Trustpilot Reviews
Cross-platform review aggregation	Multi-Review Analyzer
US Treasury SDN list screening	OFAC Sanctions Search
Multi-jurisdiction watchlist and PEP screening	OpenSanctions Search
Tech community discussion and reputation	Hacker News Search
Historical web content archives	Wayback Machine
Creator web presence and contact data	Website Contact Scraper
Website content analysis for brand alignment	Website Content to Markdown

MCP Tools

Tool	Price	Description
creator_brand_safety_screen	$1.50	Screen a creator for brand safety risks including controversial content, unsafe associations, and review sentiment across Bluesky, Trustpilot, multi-platform reviews, and Hacker News
audience_authenticity_check	$1.50	Verify audience authenticity through engagement quality analysis on Bluesky, cross-platform presence on Hacker News, and website verification with content analysis
controversy_risk_analysis	$1.50	Analyze controversy risk from social media, tech community discussions, archived web content, and sanctions/watchlist screening via OFAC and OpenSanctions
platform_diversification_score	$1.50	Assess creator platform diversification across Bluesky, Hacker News, review platforms, and personal website. Score = active platforms x 25. Higher diversification = lower deplatforming risk
historical_content_audit	$1.50	Audit historical content through Wayback Machine archives and current website content to detect deleted or modified controversial material
sanctions_watchlist_check	$1.50	Screen creator against OFAC SDN list and OpenSanctions for sanctions, watchlist, and PEP matches. Returns BLOCKED, REVIEW_REQUIRED, or CLEAR verdict
compare_creators	$1.50	Compare 2-5 creators on brand safety, authenticity, controversy risk, and historical content with ranked scoring and recommendation
brand_fit_assessment	$8.00	Comprehensive brand fit assessment combining all 9 data sources for safety, authenticity, controversy, historical content, and sanctions screening

Data Sources

• Bluesky Social Search -- Decentralized social media platform search for creator posts, engagement patterns, and content analysis
• Trustpilot Reviews -- Consumer review platform data for brand and creator reputation assessment
• Multi-Review Analyzer -- Cross-platform review aggregation from Google, Yelp, and other review sites for comprehensive reputation signals
• OFAC Sanctions Search -- US Treasury SDN list screening to ensure creators are not sanctioned individuals or entities
• OpenSanctions Search -- Multi-jurisdiction watchlist and PEP screening across 100+ international sanctions databases
• Hacker News Search -- Y Combinator's Hacker News community discussions for tech creator reputation and controversy signals
• Wayback Machine -- Internet Archive historical snapshots for detecting content that has been deleted or modified from creator websites
• Website Contact Scraper -- Creator web presence verification with contact information extraction
• Website Content to Markdown -- Full website content extraction for brand alignment analysis and content review

How the scoring works

The MCP produces six scoring dimensions that combine into a Composite Brand Fit Score (0-100) where lower scores indicate safer partnerships.

Brand Safety Score evaluates review sentiment across Trustpilot and multi-platform reviews, Bluesky social media content for unsafe keywords, and Hacker News discussion tone. Negative sentiment and controversial content associations raise the safety risk.

Audience Authenticity Index measures cross-platform engagement consistency. Genuine creators maintain presence across multiple platforms (Bluesky, Hacker News, personal website) with consistent engagement patterns. Single-platform presence or inconsistent profiles lower authenticity scores.

Controversy Risk Rating analyzes Bluesky social media controversy density, Hacker News discussion negativity, Wayback Machine archived content for deleted controversy, and sanctions/watchlist proximity. Multiple controversy signals across platforms indicate systemic risk.

Platform Diversification Score is calculated as active platforms x 25 (max 100). Four active platforms (Bluesky, Hacker News, review sites, personal website) = 100 = HIGHLY_DIVERSIFIED. Single platform = 25 = high platform dependency risk.

Historical Content Risk examines Wayback Machine snapshots for content that has been deleted or significantly modified, which may indicate controversial material the creator attempted to remove.

Sanctions/Watchlist Flag screens OFAC matches with confidence scoring and OpenSanctions dataset breadth. Any match triggers BLOCKED (2+ matches) or REVIEW_REQUIRED (1 match).

Verdict	Meaning
SAFE	Low risk across all dimensions -- proceed with partnership
CAUTION	Some risk signals -- review specific areas before proceeding
RISK	Multiple adverse signals -- enhanced due diligence required
BLOCKED	Sanctions or watchlist match -- do not proceed without legal review

How to connect this MCP server

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "influencer-brand-safety-intelligence": {
      "url": "https://influencer-brand-safety-intelligence-mcp.apify.actor/mcp"
    }
  }
}

Programmatic (HTTP)

curl -X POST https://influencer-brand-safety-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":"creator_brand_safety_screen","arguments":{"creator":"techinfluencer123"}},"id":1}'

This MCP also works with Cursor, Windsurf, Cline, and any other MCP-compatible client.

Use cases for influencer brand safety

Pre-Partnership Creator Vetting

Screen creators across brand safety, controversy risk, audience authenticity, and sanctions before signing partnership agreements. Get quantified risk scores instead of subjective assessments.

Influencer Portfolio Risk Assessment

Compare multiple creators simultaneously to identify the safest partnership candidates. Rank creators by composite brand fit score for data-driven selection.

Sanctions and Legal Compliance

Ensure influencer partnerships comply with sanctions laws by screening creators against OFAC and international watchlists before executing contracts.

Historical Content Discovery

Audit creator websites through Wayback Machine archives to discover controversial content that has been deleted or modified. Detect reputation risks that current content reviews would miss.

Platform Risk Assessment

Evaluate creator platform diversification to assess deplatforming risk. Creators dependent on a single platform pose higher business continuity risk to brand partnerships.

Ongoing Brand Safety Monitoring

Set up recurring brand safety screens on existing creator partnerships to detect emerging controversy, declining authenticity, or new sanctions matches.

How much does it cost?

This MCP uses pay-per-event pricing. You are only charged when a tool is called -- there is no subscription or monthly fee.

The Apify Free plan includes $5 of monthly platform credits, covering multiple creator screenings at no cost.

Cost examples:

• Quick brand safety screen: $1.50
• Sanctions/watchlist check: $1.50
• Full brand fit assessment (9 actors): $8.00
• Compare 3 creators: $1.50

How it works

1. You call a tool (e.g., brand_fit_assessment) with a creator name or handle
2. The MCP dispatches parallel requests to up to 9 Apify actors simultaneously
3. Social media posts, review data, sanctions lists, Hacker News discussions, Wayback Machine archives, and website content are collected
4. Scoring functions compute brand safety, audience authenticity, controversy risk, platform diversification, historical content risk, and sanctions flags
5. A structured JSON response is returned with the composite brand fit score, verdict, dimensional analysis, and all supporting signals

FAQ

Q: Does this analyze Instagram or TikTok directly? A: It currently analyzes Bluesky social media, Hacker News discussions, review platforms, and web presence. Instagram and TikTok analysis requires platform-specific integrations not included in this version.

Q: How does audience authenticity work? A: It cross-references presence across multiple platforms. Multi-platform consistency with genuine engagement patterns (Bluesky + Hacker News + reviews + website) indicates higher authenticity than single-platform presence.

Q: Can it detect deleted tweets or posts? A: The historical_content_audit tool uses Wayback Machine archives to detect content deleted or modified from websites. Social media post deletion detection depends on whether archived snapshots captured the content.

Q: How does the sanctions screening work for influencers? A: Creator names are screened against OFAC SDN list and OpenSanctions with confidence scoring. High-confidence matches (score >= 60%) trigger flags. This catches situations where creators share names with sanctioned individuals.

Q: Is it legal to use this data? A: All data sources are publicly available. See Apify's guide on web scraping legality.

Q: Can I combine this with other MCPs? A: Yes. Use the Brand Narrative Intelligence MCP for broader brand protection analysis, or the Competitive Digital Intelligence MCP for competitive creator landscape mapping.

Related MCP servers

MCP Server	Description
ryanclinton/brand-narrative-intelligence-mcp	Brand protection and narrative tracking
ryanclinton/competitive-digital-intelligence-mcp	Digital competitive analysis and market intelligence
ryanclinton/financial-crime-screening-mcp	AML/CFT screening for deeper sanctions analysis

Integrations

This MCP server runs on the Apify platform and supports:

• Apify API -- Call any tool programmatically via the Apify Actor API
• Scheduling -- Set up recurring creator monitoring for active partnerships
• Webhooks -- Get notified when screenings complete for integration with influencer management platforms
• Apify integrations -- Connect to Slack, Google Sheets, Zapier, Make, and other platforms