Skip to main content
Glama
CSOAI-ORG

Scam Detector MCP

by CSOAI-ORG
OverviewSchemaRelated ServersScoreDiscussions
Python

analyze_url

Checks a URL for phishing indicators and suspicious patterns, providing analysis to identify potential scams.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
api_keyNo

Implementation Reference

  • server.py:397-397 (registration)
    Registration of the analyze_url tool via the @mcp.tool() decorator on FastMCP instance.
    @mcp.tool()
  • server.py:398-548 (handler)
    The analyze_url handler function. Takes a URL and optional API key. Checks HTTPS, phishing indicators (TLD, typosquatting, suspicious structure, IP in URL, excessive subdomains), URL length, @ symbol, redirects, and suspicious file extensions. Returns a risk score, verdict, and recommended action.
    def analyze_url(
    url: str,
    api_key: str = "",
) -> dict:
    """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.
    """
    allowed, msg, tier = check_access(api_key)
    if not allowed:
        return {"error": msg, "upgrade_url": "https://meok.ai/pricing"}
    limit_err = _check_rate_limit("analyze_url", tier)
    if limit_err:
        return {"error": "rate_limited", "message": limit_err}

    url_lower = url.lower().strip()
    findings = []  # type: List[Dict[str, str]]
    total_risk = 0.0

    # Check for HTTPS
    if url_lower.startswith("http://"):
        findings.append({
            "finding": "No HTTPS",
            "severity": "medium",
            "detail": "URL uses HTTP instead of HTTPS -- data transmitted in plain text",
        })
        total_risk += 0.15
    elif not url_lower.startswith("https://"):
        findings.append({
            "finding": "Missing protocol",
            "severity": "low",
            "detail": "URL does not specify a protocol",
        })

    # Check phishing indicators
    for indicator_name, indicator_info in PHISHING_URL_INDICATORS.items():
        for pattern in indicator_info["patterns"]:
            if indicator_name == "ip_in_url" or indicator_name == "excessive_subdomains":
                if re.search(pattern, url_lower):
                    findings.append({
                        "finding": indicator_info["description"],
                        "severity": "high" if indicator_info["weight"] > 0.3 else "medium",
                        "detail": "Matched pattern: {}".format(pattern),
                    })
                    total_risk += indicator_info["weight"]
                    break
            else:
                if pattern.lower() in url_lower:
                    findings.append({
                        "finding": indicator_info["description"],
                        "severity": "high" if indicator_info["weight"] > 0.3 else "medium",
                        "detail": "Matched indicator: {}".format(pattern),
                    })
                    total_risk += indicator_info["weight"]
                    break

    # Check URL length (phishing URLs tend to be long)
    if len(url) > 100:
        findings.append({
            "finding": "Unusually long URL",
            "severity": "low",
            "detail": "URL is {} characters (phishing URLs are often longer than legitimate ones)".format(len(url)),
        })
        total_risk += 0.1

    # Check for @ symbol (used to obscure real domain)
    if "@" in url_lower:
        findings.append({
            "finding": "@ symbol in URL",
            "severity": "high",
            "detail": "@ symbol can be used to obscure the actual destination domain",
        })
        total_risk += 0.4

    # Check for multiple redirects (double slashes after domain)
    if url_lower.count("//") > 1:
        double_slash_count = url_lower.count("//")
        if double_slash_count > 2:
            findings.append({
                "finding": "Multiple double-slashes",
                "severity": "medium",
                "detail": "May indicate redirect chains or URL obfuscation",
            })
            total_risk += 0.15

    # Check for suspicious file extensions
    suspicious_extensions = [".exe", ".scr", ".bat", ".cmd", ".vbs", ".js", ".hta", ".pif"]
    for ext in suspicious_extensions:
        if url_lower.endswith(ext):
            findings.append({
                "finding": "Suspicious file extension",
                "severity": "critical",
                "detail": "URL points to executable file ({}) -- likely malware".format(ext),
            })
            total_risk += 0.5

    # Normalize score
    risk_score = min(1.0, total_risk)

    if risk_score >= 0.6:
        verdict = "HIGH RISK -- likely phishing"
        action = "Do NOT click this link. Do not enter any credentials on this site."
    elif risk_score >= 0.3:
        verdict = "MODERATE RISK -- potentially suspicious"
        action = "Verify the URL through official channels before proceeding."
    else:
        verdict = "LOW RISK -- no major indicators"
        action = "URL appears relatively safe but always verify sender context."

    return {
        "url_analyzed": url,
        "risk_score": round(risk_score, 2),
        "verdict": verdict,
        "recommended_action": action,
        "findings": findings,
        "url_length": len(url),
        "uses_https": url_lower.startswith("https://"),
        "next_step": "Use quick_check on the full message containing this URL for comprehensive scam analysis",
        "meok_labs": "https://meok.ai",
    }
  • server.py:398-548 (schema)
    Input parameters (url: str, api_key: str = "") and return dict schema for analyze_url tool.
    def analyze_url(
    url: str,
    api_key: str = "",
) -> dict:
    """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.
    """
    allowed, msg, tier = check_access(api_key)
    if not allowed:
        return {"error": msg, "upgrade_url": "https://meok.ai/pricing"}
    limit_err = _check_rate_limit("analyze_url", tier)
    if limit_err:
        return {"error": "rate_limited", "message": limit_err}

    url_lower = url.lower().strip()
    findings = []  # type: List[Dict[str, str]]
    total_risk = 0.0

    # Check for HTTPS
    if url_lower.startswith("http://"):
        findings.append({
            "finding": "No HTTPS",
            "severity": "medium",
            "detail": "URL uses HTTP instead of HTTPS -- data transmitted in plain text",
        })
        total_risk += 0.15
    elif not url_lower.startswith("https://"):
        findings.append({
            "finding": "Missing protocol",
            "severity": "low",
            "detail": "URL does not specify a protocol",
        })

    # Check phishing indicators
    for indicator_name, indicator_info in PHISHING_URL_INDICATORS.items():
        for pattern in indicator_info["patterns"]:
            if indicator_name == "ip_in_url" or indicator_name == "excessive_subdomains":
                if re.search(pattern, url_lower):
                    findings.append({
                        "finding": indicator_info["description"],
                        "severity": "high" if indicator_info["weight"] > 0.3 else "medium",
                        "detail": "Matched pattern: {}".format(pattern),
                    })
                    total_risk += indicator_info["weight"]
                    break
            else:
                if pattern.lower() in url_lower:
                    findings.append({
                        "finding": indicator_info["description"],
                        "severity": "high" if indicator_info["weight"] > 0.3 else "medium",
                        "detail": "Matched indicator: {}".format(pattern),
                    })
                    total_risk += indicator_info["weight"]
                    break

    # Check URL length (phishing URLs tend to be long)
    if len(url) > 100:
        findings.append({
            "finding": "Unusually long URL",
            "severity": "low",
            "detail": "URL is {} characters (phishing URLs are often longer than legitimate ones)".format(len(url)),
        })
        total_risk += 0.1

    # Check for @ symbol (used to obscure real domain)
    if "@" in url_lower:
        findings.append({
            "finding": "@ symbol in URL",
            "severity": "high",
            "detail": "@ symbol can be used to obscure the actual destination domain",
        })
        total_risk += 0.4

    # Check for multiple redirects (double slashes after domain)
    if url_lower.count("//") > 1:
        double_slash_count = url_lower.count("//")
        if double_slash_count > 2:
            findings.append({
                "finding": "Multiple double-slashes",
                "severity": "medium",
                "detail": "May indicate redirect chains or URL obfuscation",
            })
            total_risk += 0.15

    # Check for suspicious file extensions
    suspicious_extensions = [".exe", ".scr", ".bat", ".cmd", ".vbs", ".js", ".hta", ".pif"]
    for ext in suspicious_extensions:
        if url_lower.endswith(ext):
            findings.append({
                "finding": "Suspicious file extension",
                "severity": "critical",
                "detail": "URL points to executable file ({}) -- likely malware".format(ext),
            })
            total_risk += 0.5

    # Normalize score
    risk_score = min(1.0, total_risk)

    if risk_score >= 0.6:
        verdict = "HIGH RISK -- likely phishing"
        action = "Do NOT click this link. Do not enter any credentials on this site."
    elif risk_score >= 0.3:
        verdict = "MODERATE RISK -- potentially suspicious"
        action = "Verify the URL through official channels before proceeding."
    else:
        verdict = "LOW RISK -- no major indicators"
        action = "URL appears relatively safe but always verify sender context."

    return {
        "url_analyzed": url,
        "risk_score": round(risk_score, 2),
        "verdict": verdict,
        "recommended_action": action,
        "findings": findings,
        "url_length": len(url),
        "uses_https": url_lower.startswith("https://"),
        "next_step": "Use quick_check on the full message containing this URL for comprehensive scam analysis",
        "meok_labs": "https://meok.ai",
    }
  • server.py:171-203 (helper)
    PHISHING_URL_INDICATORS data dictionary used by analyze_url to detect phishing patterns in URLs.
    PHISHING_URL_INDICATORS = {
    "suspicious_tld": {
        "patterns": [".xyz", ".top", ".club", ".work", ".click", ".loan", ".win", ".gq", ".tk", ".ml", ".cf", ".ga"],
        "weight": 0.3,
        "description": "Suspicious top-level domains commonly used in phishing",
    },
    "typosquatting": {
        "patterns": [
            "paypa1", "g00gle", "micros0ft", "amaz0n", "faceb00k",
            "app1e", "netfl1x", "1inkedin", "twitt3r", "inst4gram",
        ],
        "weight": 0.5,
        "description": "Intentional misspellings of legitimate brands",
    },
    "suspicious_structure": {
        "patterns": [
            "login-", "secure-", "verify-", "update-", "account-",
            "signin.", "security.", "-alert.", "-confirm.",
        ],
        "weight": 0.25,
        "description": "URL structures designed to look like security pages",
    },
    "ip_in_url": {
        "patterns": [r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}"],
        "weight": 0.4,
        "description": "Direct IP address in URL instead of domain name",
    },
    "excessive_subdomains": {
        "patterns": [r"\w+\.\w+\.\w+\.\w+\.\w+"],
        "weight": 0.3,
        "description": "Excessive subdomain depth to obscure actual domain",
    },
}
  • server.py:57-72 (helper)
    Rate limiting helper used by analyze_url (line 440: _check_rate_limit("analyze_url", tier)).
    def _check_rate_limit(caller="anonymous", tier="free"):
    # type: (str, str) -> Optional[str]
    """Returns error string if rate-limited, else None."""
    if tier == "pro":
        return None
    now = datetime.now()
    cutoff = now - timedelta(days=1)
    _usage[caller] = [t for t in _usage[caller] if t > cutoff]
    if len(_usage[caller]) >= FREE_DAILY_LIMIT:
        return (
            "Free tier limit reached ({}/day). "
            "Upgrade to MEOK AI Labs Pro for unlimited access at $29/mo: "
            "https://meok.ai/mcp/scam-detector/pro".format(FREE_DAILY_LIMIT)
        )
    _usage[caller].append(now)
    return None

Tool Definition Quality

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description comprehensively covers side effects, authentication, rate limits, error handling, idempotency, and data privacy in a dedicated section. This fully compensates for the lack of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear headings and sections, but it is somewhat verbose and repeats behavioral transparency information in both a list and a block. It is front-loaded with the main purpose and remains readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, no annotations, and no schema descriptions, the description is highly complete. It covers behavior, error handling, rate limits, authentication, and privacy, leaving no critical gaps for an AI agent to understand the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (no descriptions in schema). The description provides brief explanations for each parameter (url, api_key) in the Args section, adding some meaning beyond the schema, but does not elaborate on formats, constraints, or defaults. This partially compensates but could be more detailed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Check a URL for phishing indicators and suspicious patterns,' which is a specific verb and resource. It clearly distinguishes from sibling tools like detect_social_engineering or verify_sender by focusing on URL phishing analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides 'When to use' (structured analysis against frameworks) and 'When NOT to use' (not for real-time production without human review), offering clear context and exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CSOAI-ORG/scam-detector-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server