scamverifyai/scamverify-mcp

🔒 Security
0 Views
0 Installs

📇 ☁️ - AI-powered scam and threat verification MCP server. Check phone numbers, URLs, text messages, emails, documents, and QR codes against 8M+ threat intelligence records (FTC/FCC complaints, carrier analysis, URLhaus, ThreatFox). Returns risk scores, verdicts, and detailed signals. 10 tools, OAuth 2.1 + API key auth, Streamable HTTP transport.

Quick Install

One-Click IDE Configuration
claude_desktop_config.json
{
  "mcpServers": {
    "scamverifyai-scamverify-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "scamverifyai-scamverify-mcp"
      ]
    }
  }
}
Or

Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.

Documentation Overview

ScamVerify MCP Server

AI-powered scam and threat verification MCP server. Verify phone numbers, URLs, text messages, emails, documents, and QR codes against 10M+ threat intelligence records from FTC, FCC, URLhaus, ThreatFox, and community reports.

Server URL: https://scamverify.ai/api/mcp

Transport: Streamable HTTP (stateless) or stdio (local proxy)

Authentication: API key or OAuth 2.1 (PKCE)

Tools (10)

ToolDescription
check_phoneLook up a US phone number for scam reports, carrier info, robocall flags, and community reports. Returns risk score (0-100), verdict, and detailed signals from FTC, FCC, carrier, and community data.
check_urlCheck a website URL for safety. Analyzes domain age, SSL certificate, redirect chains, brand impersonation, Google Web Risk, URLhaus, ThreatFox, and community reports.
check_textAnalyze a text/SMS message for scam indicators. Extracts and cross-references embedded phone numbers and URLs. AI identifies scam type, red flags, and risk level.
check_emailAnalyze an email for phishing indicators. Checks sender domain, email headers (SPF/DKIM/DMARC), brand impersonation, embedded URLs and phone numbers.
check_documentAnalyze a document image for scam indicators. Uses vision AI to extract entities (addresses, officials, citations, phone numbers) and verifies them against government databases.
check_qrScan a QR code image and verify its contents. Decodes the QR code server-side and, if it contains a URL, runs full URL verification.
batch_phoneLook up multiple phone numbers in a single request (max 100).
batch_urlCheck multiple URLs in a single request (max 100).
get_usageCheck your current API usage quota and rate limits for the billing period.
get_statusCheck the operational status of ScamVerify API services. No authentication required.

Prompts (4)

PromptDescription
investigate_phoneInvestigate a suspicious phone number for scam indicators and provide a safety recommendation.
verify_urlCheck if a website URL is safe to visit and provide a detailed safety assessment.
analyze_textAnalyze a suspicious text message for scam indicators and explain the findings.
check_emailAnalyze a suspicious email for phishing indicators and provide a safety assessment.

Data Sources

  • FTC Do Not Call Complaints - 9.7M+ records with scam type classification
  • FCC Consumer Complaints - 443K+ telecom violation reports
  • URLhaus - 74K+ active malicious URL indicators
  • ThreatFox - 60K+ IOCs (indicators of compromise)
  • Carrier Intelligence - Line type, CNAM, VoIP detection, high-risk carrier flagging
  • Community Reports - User-submitted scam reports with verification

Setup

Option 1: Remote Server (Recommended)

Connect directly to the hosted ScamVerify MCP server. No installation required.

Claude Desktop:

{
  "mcpServers": {
    "scamverify": {
      "type": "streamable-http",
      "url": "https://scamverify.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Claude Desktop (OAuth - no API key needed):

{
  "mcpServers": {
    "scamverify": {
      "type": "streamable-http",
      "url": "https://scamverify.ai/api/mcp"
    }
  }
}

When using without an API key, Claude Desktop will initiate the OAuth 2.1 flow. You'll be redirected to sign in at scamverify.ai and authorize access.

Cursor / Windsurf / Other MCP Clients:

{
  "type": "streamable-http",
  "url": "https://scamverify.ai/api/mcp",
  "headers": {
    "Authorization": "Bearer YOUR_API_KEY"
  }
}

ChatGPT:

ScamVerify is available as a ChatGPT connector. Add it through the ChatGPT plugin/connector settings using:

  • MCP URL: https://scamverify.ai/api/mcp
  • Auth: OAuth

Option 2: Local Proxy (stdio)

Run a local MCP server that proxies all tool calls to the ScamVerify API. Useful for MCP clients that only support stdio transport.

Install and run:

npm install -g @scamverifyai/scamverify-mcp
SCAMVERIFY_API_KEY=sv_live_... scamverify-mcp

Or run directly with npx:

SCAMVERIFY_API_KEY=sv_live_... npx @scamverifyai/scamverify-mcp

Claude Desktop (stdio):

{
  "mcpServers": {
    "scamverify": {
      "command": "npx",
      "args": ["@scamverifyai/scamverify-mcp"],
      "env": {
        "SCAMVERIFY_API_KEY": "sv_live_..."
      }
    }
  }
}

Docker:

docker build -t scamverify-mcp .
docker run -e SCAMVERIFY_API_KEY=sv_live_... scamverify-mcp

Environment Variables

VariableRequiredDescription
SCAMVERIFY_API_KEYYesYour API key (prefix: sv_live_ for production, sv_test_ for testing)
SCAMVERIFY_API_URLNoOverride the API base URL (default: https://scamverify.ai)

Getting an API Key

  1. Sign up at scamverify.ai
  2. Go to Settings > API Keys
  3. Generate a key (prefix: sv_live_ for production, sv_test_ for testing)

OAuth 2.1 Authentication

The remote server supports OAuth 2.1 with PKCE (S256). Discovery endpoints:

  • Authorization Server: https://scamverify.ai/.well-known/oauth-authorization-server
  • Protected Resource: https://scamverify.ai/.well-known/oauth-protected-resource

OAuth scopes: phone:lookup, url:lookup, text:analyze, email:analyze, usage:read

Development

git clone https://github.com/scamverifyai/scamverify-mcp.git
cd scamverify-mcp
npm install
npm run build
SCAMVERIFY_API_KEY=sv_test_... npm start

Pricing

A free tier (50 lookups/month) is automatically provisioned on first OAuth login or API key creation.

PlanMonthly PriceLookups/moRate Limit
Free$05010 RPM
Starter$19/mo1,00030 RPM
Growth$49/mo5,00060 RPM
Pro$149/mo25,000120 RPM
Scale$499/mo100,000300 RPM
EnterpriseCustomCustomCustom

Full API documentation: docs.scamverify.ai

Links

License

MIT

Related MCP Servers

13bm/GhidraMCP

🐍 ☕ 🏠 - MCP server for integrating Ghidra with AI assistants. This plugin enables binary analysis, providing tools for function inspection, decompilation, memory exploration, and import/export analysis via the Model Context Protocol.

🔒 Security1 views
123Ergo/unphurl-mcp

📇 ☁️ - URL intelligence for AI agents. 13 tools for security signals and data quality: redirect behaviour, brand impersonation detection, domain age, SSL validation, parked detection, URL structural analysis, DNS enrichment.

🔒 Security0 views
82ch/MCP-Dandan

🐍 📇 🏠 🍎 🪟 🐧 - Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines.

🔒 Security0 views
9hannahnine-jpg/arc-gate-mcp

🐍 - Runtime governance for MCP tool calls. Blocks prompt injection and capability abuse before tool results reach your agent.

🔒 Security0 views

Engagement

Views
0
Installs
0
Upvotes
0

Views and upvotes are unique per visitor network (hashed IP). Installs count copy actions.

Status

Health: Not checked yet

We have not completed a health check for this listing yet.

No check timestamp yet.

Unclaimed listing (imported or pending owner verification). Claim it →
★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to get the verified badge and attach your website.

Claim this listing

Promote this listing

Optional paid placement. Free listings stay free forever.

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.