Scam Detector MCP
Scam Detector MCP
От MEOK AI Labs | Единственный MCP-сервер для обнаружения мошенничества.
Установка · Документация · Сообщить об ошибке
Установка
pip install scam-detector-mcp
# or
npm install -g @meok-ai/scam-detector-mcpRelated MCP server: Deepfake Detector MCP
Быстрый старт
Полную документацию и примеры смотрите в репозитории проекта.
Корпоративная поддержка
Лицензия
MIT © CSOAI
Available Tools
5 toolsanalyze_urlA
Check a URL for phishing indicators and suspicious patterns.
Args: url: The URL to analyze for phishing indicators. api_key: Optional MEOK API key for pro tier.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: url (required), api_key.
detect_social_engineeringA
Detect manipulation tactics (Cialdini's principles) in conversations.
Args: conversation: The conversation text to analyze for social engineering tactics. api_key: Optional MEOK API key for pro tier.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: conversation (required), api_key.
quick_checkA
Paste any message (email, text, DM) -> instant scam probability score. No API key required.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: message (required).
report_scamA
Log and analyze a scam report. Contributes to collective threat intelligence.
Args: description: Description of the scam including the message, sender, and what happened. api_key: Optional MEOK API key for pro tier.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: description (required), api_key.
verify_senderA
Check sender patterns against known scam vectors.
Args: email_or_phone: The email address or phone number to check. api_key: Optional MEOK API key for pro tier.
Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.
When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.
Inputs: email_or_phone (required), api_key.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools target different inputs: URLs, conversations, messages, reports, and sender patterns. Some overlap between quick_check and detect_social_engineering, but descriptions differentiate them adequately.
Most tools follow verb_noun convention (analyze_url, detect_social_engineering, report_scam, verify_sender). quick_check deviates as adjective_noun, but still uses underscores and is readable.
5 tools is well-scoped for a scam detection server, covering key analysis and reporting functions without bloat or deficiency.
Covers major scam detection areas: URL analysis, social engineering, message scoring, sender verification, and reporting. Missing maybe bulk or historical queries, but covers essential workflows.
Maintenance
Related MCP Connectors
Official IPinfo MCP Server - IP intelligence tools for AI assistants
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Crypto market intelligence, token rug-checks, and wallet verification in one MCP server.
MCP server for Flux AI image generation
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceFaker AI - MCP server providing AI-powered tools and automation by MEOK AI Labs4 npm45 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceDeepfake Detector - MCP server providing AI-powered tools and automation by MEOK AI Labs8 npm41 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceAI Self Audit - MCP server providing AI-powered tools and automation by MEOK AI Labs5 npm81 PyPIMIT

License Checker AI MCPofficial
AlicenseNot gradedqualityCmaintenanceLicense Checker AI - MCP server providing AI-powered tools and automation by MEOK AI Labs2 npm37 PyPIMIT