Skip to main content
Glama
enesjakozh
ricauts

CyberMCP

by ricauts
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

sensitive_data_check

Detect sensitive data exposure in APIs by testing endpoints for vulnerabilities like authentication bypass, injection attacks, and data leakage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endpointYesAPI endpoint to test
http_methodNoHTTP method to useGET
request_bodyNoRequest body (for POST/PUT requests)
use_authNoWhether to use current authentication if available

Implementation Reference

  • src/tools/dataLeakage.ts:19-109 (handler)
    The core handler function that performs HTTP requests to the specified endpoint (with optional auth), scans the response body, headers, and error details for sensitive data exposure using predefined regex patterns for PII, API keys, JWTs, passwords, stack traces, etc., collects findings by severity, and returns a formatted markdown report.
    async ({ endpoint, http_method, request_body, use_auth }) => {
  try {
    // Get auth headers if available and requested
    let headers = {};
    if (use_auth) {
      const authManager = AuthManager.getInstance();
      const authState = authManager.getAuthState();
      
      if (authState.type !== 'none' && authState.headers) {
        headers = { ...headers, ...authState.headers };
      }
    }
    
    // Make the request
    const response = await axios({
      method: http_method.toLowerCase(),
      url: endpoint,
      data: request_body ? JSON.parse(request_body) : undefined,
      headers,
      validateStatus: () => true, // Accept any status code
    });

    // Check for data leakage in the response
    const responseBody = typeof response.data === 'string' ? response.data : JSON.stringify(response.data);
    const responseHeaders = response.headers;
    
    // Patterns to check for in the response
    const sensitivePatterns = [
      // PII
      { type: "Email Address", regex: /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}/g },
      { type: "Phone Number", regex: /(\+\d{1,3}[- ]?)?\d{3}[- ]?\d{3,4}[- ]?\d{4}/g },
      { type: "Social Security Number", regex: /\b\d{3}[-]?\d{2}[-]?\d{4}\b/g },
      
      // Credentials and Tokens
      { type: "API Key", regex: /(api[_-]?key|apikey|access[_-]?key|auth[_-]?key)[\"']?\s*[=:]\s*[\"']?([a-zA-Z0-9]{16,})/gi },
      { type: "JWT", regex: /eyJ[a-zA-Z0-9_-]{5,}\.eyJ[a-zA-Z0-9_-]{5,}\.[a-zA-Z0-9_-]{5,}/g },
      { type: "Password", regex: /(password|passwd|pwd)[\"']?\s*[=:]\s*[\"']?([^\"']{3,})/gi },
      
      // Internal Info
      { type: "Internal Path", regex: /(\/var\/www\/|\/home\/\w+\/|C:\\Program Files\\|C:\\inetpub\\)/gi },
      { type: "SQL Query", regex: /(SELECT|INSERT|UPDATE|DELETE|CREATE|ALTER|DROP)\s+.+?(?=FROM|WHERE|VALUES|SET|TABLE)/gi },
      { type: "Stack Trace", regex: /(Exception|Error):\s*.*?at\s+[\w.<>$_]+\s+\(.*?:\d+:\d+\)/s },
      { type: "IP Address", regex: /\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b/g },
    ];
    
    // Check for sensitive data in response
    const findings = [];
    for (const pattern of sensitivePatterns) {
      const matches = responseBody.match(pattern.regex);
      if (matches && matches.length > 0) {
        findings.push({
          type: pattern.type,
          occurrence: matches.length,
          examples: matches.slice(0, 3), // Show max 3 examples
          severity: getSeverity(pattern.type),
        });
      }
    }
    
    // Check response headers
    const sensitiveHeaders = checkSensitiveHeaders(responseHeaders);
    
    // Check for error details
    const errorDetails = checkErrorDetails(response);
    
    // Add authentication info to the report
    const authManager = AuthManager.getInstance();
    const authState = authManager.getAuthState();
    const authInfo = use_auth && authState.type !== 'none'
      ? `\nTest performed with authentication: ${authState.type}`
      : '\nTest performed without authentication';
    
    return {
      content: [
        {
          type: "text",
          text: formatFindings(findings, sensitiveHeaders, errorDetails, endpoint, authInfo),
        },
      ],
    };
  } catch (error) {
    return {
      content: [
        {
          type: "text",
          text: `Error checking for sensitive data exposure: ${(error as Error).message}`,
        },
      ],
    };
  }
}
  • src/tools/dataLeakage.ts:13-18 (schema)
    Zod schema defining input parameters for the sensitive_data_check tool: endpoint (required URL), http_method (default GET), optional request_body, use_auth (default true).
    {
  endpoint: z.string().url().describe("API endpoint to test"),
  http_method: z.enum(["GET", "POST", "PUT", "DELETE"]).default("GET").describe("HTTP method to use"),
  request_body: z.string().optional().describe("Request body (for POST/PUT requests)"),
  use_auth: z.boolean().default(true).describe("Whether to use current authentication if available"),
},
  • src/tools/dataLeakage.ts:11-110 (registration)
    Direct registration of the 'sensitive_data_check' tool on the MCP server within registerDataLeakageTools function.
    server.tool(
  "sensitive_data_check",
  {
    endpoint: z.string().url().describe("API endpoint to test"),
    http_method: z.enum(["GET", "POST", "PUT", "DELETE"]).default("GET").describe("HTTP method to use"),
    request_body: z.string().optional().describe("Request body (for POST/PUT requests)"),
    use_auth: z.boolean().default(true).describe("Whether to use current authentication if available"),
  },
  async ({ endpoint, http_method, request_body, use_auth }) => {
    try {
      // Get auth headers if available and requested
      let headers = {};
      if (use_auth) {
        const authManager = AuthManager.getInstance();
        const authState = authManager.getAuthState();
        
        if (authState.type !== 'none' && authState.headers) {
          headers = { ...headers, ...authState.headers };
        }
      }
      
      // Make the request
      const response = await axios({
        method: http_method.toLowerCase(),
        url: endpoint,
        data: request_body ? JSON.parse(request_body) : undefined,
        headers,
        validateStatus: () => true, // Accept any status code
      });

      // Check for data leakage in the response
      const responseBody = typeof response.data === 'string' ? response.data : JSON.stringify(response.data);
      const responseHeaders = response.headers;
      
      // Patterns to check for in the response
      const sensitivePatterns = [
        // PII
        { type: "Email Address", regex: /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}/g },
        { type: "Phone Number", regex: /(\+\d{1,3}[- ]?)?\d{3}[- ]?\d{3,4}[- ]?\d{4}/g },
        { type: "Social Security Number", regex: /\b\d{3}[-]?\d{2}[-]?\d{4}\b/g },
        
        // Credentials and Tokens
        { type: "API Key", regex: /(api[_-]?key|apikey|access[_-]?key|auth[_-]?key)[\"']?\s*[=:]\s*[\"']?([a-zA-Z0-9]{16,})/gi },
        { type: "JWT", regex: /eyJ[a-zA-Z0-9_-]{5,}\.eyJ[a-zA-Z0-9_-]{5,}\.[a-zA-Z0-9_-]{5,}/g },
        { type: "Password", regex: /(password|passwd|pwd)[\"']?\s*[=:]\s*[\"']?([^\"']{3,})/gi },
        
        // Internal Info
        { type: "Internal Path", regex: /(\/var\/www\/|\/home\/\w+\/|C:\\Program Files\\|C:\\inetpub\\)/gi },
        { type: "SQL Query", regex: /(SELECT|INSERT|UPDATE|DELETE|CREATE|ALTER|DROP)\s+.+?(?=FROM|WHERE|VALUES|SET|TABLE)/gi },
        { type: "Stack Trace", regex: /(Exception|Error):\s*.*?at\s+[\w.<>$_]+\s+\(.*?:\d+:\d+\)/s },
        { type: "IP Address", regex: /\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b/g },
      ];
      
      // Check for sensitive data in response
      const findings = [];
      for (const pattern of sensitivePatterns) {
        const matches = responseBody.match(pattern.regex);
        if (matches && matches.length > 0) {
          findings.push({
            type: pattern.type,
            occurrence: matches.length,
            examples: matches.slice(0, 3), // Show max 3 examples
            severity: getSeverity(pattern.type),
          });
        }
      }
      
      // Check response headers
      const sensitiveHeaders = checkSensitiveHeaders(responseHeaders);
      
      // Check for error details
      const errorDetails = checkErrorDetails(response);
      
      // Add authentication info to the report
      const authManager = AuthManager.getInstance();
      const authState = authManager.getAuthState();
      const authInfo = use_auth && authState.type !== 'none'
        ? `\nTest performed with authentication: ${authState.type}`
        : '\nTest performed without authentication';
      
      return {
        content: [
          {
            type: "text",
            text: formatFindings(findings, sensitiveHeaders, errorDetails, endpoint, authInfo),
          },
        ],
      };
    } catch (error) {
      return {
        content: [
          {
            type: "text",
            text: `Error checking for sensitive data exposure: ${(error as Error).message}`,
          },
        ],
      };
    }
  }
);
  • src/tools/index.ts:5-15 (registration)
    Imports and calls registerDataLeakageTools(server) as part of registerSecurityTools, which registers the sensitive_data_check among other tools.
    import { registerDataLeakageTools } from "./dataLeakage.js";
import { registerRateLimitingTools } from "./rateLimiting.js";
import { registerSecurityHeadersTools } from "./securityHeaders.js";

/**
 * Register all security testing tools with the MCP server
 */
export function registerSecurityTools(server: McpServer) {
  registerAuthenticationTools(server);
  registerInjectionTools(server);
  registerDataLeakageTools(server);
  • src/index.ts:9-20 (registration)
    Main server entry point imports and calls registerSecurityTools(server), initiating the registration chain for all tools including sensitive_data_check.
    import { registerSecurityTools } from "./tools/index.js";
import { registerResources } from "./resources/index.js";

// Create an MCP server
const server = new McpServer({
  name: "CyberMCP",
  version: "0.2.0",
  description: "MCP server for cybersecurity API testing and vulnerability assessment"
});

// Register all our security testing tools
registerSecurityTools(server);
  • src/tools/dataLeakage.ts:46-62 (helper)
    Array of sensitive data detection patterns (regex) used by the handler to scan responses for leaked information, categorized by type.
    const sensitivePatterns = [
  // PII
  { type: "Email Address", regex: /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}/g },
  { type: "Phone Number", regex: /(\+\d{1,3}[- ]?)?\d{3}[- ]?\d{3,4}[- ]?\d{4}/g },
  { type: "Social Security Number", regex: /\b\d{3}[-]?\d{2}[-]?\d{4}\b/g },
  
  // Credentials and Tokens
  { type: "API Key", regex: /(api[_-]?key|apikey|access[_-]?key|auth[_-]?key)[\"']?\s*[=:]\s*[\"']?([a-zA-Z0-9]{16,})/gi },
  { type: "JWT", regex: /eyJ[a-zA-Z0-9_-]{5,}\.eyJ[a-zA-Z0-9_-]{5,}\.[a-zA-Z0-9_-]{5,}/g },
  { type: "Password", regex: /(password|passwd|pwd)[\"']?\s*[=:]\s*[\"']?([^\"']{3,})/gi },
  
  // Internal Info
  { type: "Internal Path", regex: /(\/var\/www\/|\/home\/\w+\/|C:\\Program Files\\|C:\\inetpub\\)/gi },
  { type: "SQL Query", regex: /(SELECT|INSERT|UPDATE|DELETE|CREATE|ALTER|DROP)\s+.+?(?=FROM|WHERE|VALUES|SET|TABLE)/gi },
  { type: "Stack Trace", regex: /(Exception|Error):\s*.*?at\s+[\w.<>$_]+\s+\(.*?:\d+:\d+\)/s },
  { type: "IP Address", regex: /\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b/g },
];

Tool Definition Quality

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Related 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/ricauts/CyberMCP'

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