Skip to main content
Glama

scan_project

Performs comprehensive security scans on project directories to identify vulnerabilities and ensure compliance with industry standards like OWASP, CIS, and NIST frameworks.

Instructions

Performs comprehensive security scan on project directory

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
incrementalNoUse incremental scanning if available
pathYesProject path to scan
profileNoScan profile
toolsNoSpecific tools to use

Implementation Reference

  • Primary MCP tool handler for 'scan_project'. Validates input, enforces boundaries, supports incremental scanning, applies false positive filtering, and delegates core scanning to ProjectScanner.scan()
    private async handleProjectScan(args: any): Promise<ScanResult> {
      const { path, profile = 'standard', tools, incremental = false } = args;
    
      // Validate project boundaries
      const validation = await this.boundaryEnforcer.validatePath(path);
      if (!validation.allowed) {
        throw new McpError(ErrorCode.InvalidRequest, validation.reason || 'Path validation failed');
      }
    
      // Perform scan
      const request: ScanRequest = {
        type: 'project',
        target: path,
        profile,
        tools,
        options: {
          maxTokens: this.tokenManager.getRemainingTokens(),
          incremental,
        },
      };
    
      // Use incremental scanner if requested
      if (incremental && this.incrementalScanner) {
        const result = await this.incrementalScanner.scan(request);
        
        // Apply false positive filtering
        if (this.falsePositiveFilter) {
          const filterResults = await this.falsePositiveFilter.filterFindings(result.findings);
          result.findings = filterResults.filter(r => !r.filtered).map(r => r.finding);
          
          // Add filter stats to result
          const filterStats = this.falsePositiveFilter.getStatistics(filterResults);
          console.error(`Filtered ${filterStats.filtered} false positives (${filterStats.filterRate.toFixed(1)}%)`);
        }
        
        return result;
      }
    
      // Regular scan
      const result = await this.projectScanner.scan(request);
      
      // Apply false positive filtering
      if (this.falsePositiveFilter) {
        const filterResults = await this.falsePositiveFilter.filterFindings(result.findings);
        result.findings = filterResults.filter(r => !r.filtered).map(r => r.finding);
      }
      
      return result;
    }
  • Core implementation of project scanning logic. Orchestrates multiple security tools (Semgrep, Trivy, Gitleaks, Checkov, etc.), supports caching, parallel execution, and aggregates findings from all scanners.
    async scan(request: ScanRequest): Promise<ScanResult> {
      const scanId = this.generateScanId();
      const startTime = Date.now();
    
      // Validate boundaries
      const validation = await this.boundaryEnforcer.validatePath(request.target);
      if (!validation.allowed) {
        throw new Error(`Boundary violation: ${validation.reason}`);
      }
    
      // Determine which tools to run
      const tools = request.tools || this.getDefaultTools(request.profile);
      
      // Check cache first
      const cachedResult = await this.cache.get('project', request.target, tools, request.profile);
      if (cachedResult) {
        console.error(`Cache hit for project scan: ${scanId}`);
        // Update scan ID and timing for the cached result
        cachedResult.scanId = scanId;
        cachedResult.scanTimeMs = Date.now() - startTime;
        return cachedResult;
      }
    
      console.error(`Starting project scan: ${scanId} with tools: ${tools.join(', ')}`);
    
      const allFindings: Finding[] = [];
      const errors: string[] = [];
      let tokenUsage = 0;
    
      // Determine execution strategy
      const useParallel = request.options?.parallel !== false && tools.length > 1;
      
      if (useParallel) {
        // Run scanners in parallel
        const scanResults = await this.runScannersInParallel(request.target, tools);
        
        // Aggregate results
        for (const result of scanResults.results) {
          if (result.status === 'success' && result.result) {
            allFindings.push(...result.result.findings);
            tokenUsage += result.result.tokenUsage;
          } else if (result.status === 'error') {
            const errorMsg = `${result.id} failed: ${result.error?.message}`;
            console.error(errorMsg);
            errors.push(errorMsg);
          }
        }
      } else {
        // Run scanners sequentially
        for (const tool of tools) {
          try {
            console.error(`Running ${tool} scanner...`);
            
            const scanResult = await this.runSingleScanner(tool, request.target);
            allFindings.push(...scanResult.findings);
            tokenUsage += scanResult.tokenUsage;
            
          } catch (error) {
            const errorMsg = `${tool} failed: ${error instanceof Error ? error.message : 'Unknown error'}`;
            console.error(errorMsg);
            errors.push(errorMsg);
          }
        }
      }
    
      // Calculate summary
      const summary = this.calculateSummary(allFindings);
    
      const result: ScanResult = {
        scanId,
        status: errors.length === 0 ? 'success' : (allFindings.length > 0 ? 'partial' : 'failed'),
        summary,
        findings: allFindings,
        tokenUsage,
        scanTimeMs: Date.now() - startTime,
        errors: errors.length > 0 ? errors : undefined,
      };
    
      // Cache successful results
      if (result.status === 'success') {
        await this.cache.set('project', request.target, tools, result, request.profile);
      }
    
      console.error(`Project scan completed: ${result.status}, ${allFindings.length} findings`);
      return result;
    }
  • Tool registration and input schema definition for 'scan_project' in the MCP tools list returned by ListToolsRequestHandler.
    {
      name: 'scan_project',
      description: 'Performs comprehensive security scan on project directory',
      inputSchema: {
        type: 'object',
        properties: {
          path: { type: 'string', description: 'Project path to scan' },
          profile: { 
            type: 'string', 
            enum: ['quick', 'standard', 'thorough'],
            description: 'Scan profile'
          },
          tools: {
            type: 'array',
            items: { type: 'string' },
            description: 'Specific tools to use'
          },
          incremental: {
            type: 'boolean',
            description: 'Use incremental scanning if available'
          },
        },
        required: ['path'],
      },
  • Tool dispatch registration in the central CallToolRequestHandler switch statement.
    switch (name) {
      case 'scan_project':
        result = await this.handleProjectScan(args);
        break;
  • Helper function that dispatches to individual scanner implementations (Semgrep, Trivy, Gitleaks, etc.) based on tool name.
    private async runSingleScanner(tool: string, targetPath: string): Promise<{ findings: Finding[]; tokenUsage: number }> {
      switch (tool) {
        case 'semgrep':
          return await this.runSemgrep(targetPath);
        case 'trivy':
          return await this.runTrivy(targetPath);
        case 'gitleaks':
          return await this.runGitleaks(targetPath);
        case 'checkov':
          return await this.runCheckov(targetPath);
        case 'nuclei':
          return await this.runNuclei(targetPath);
        case 'bandit':
          return await this.runBandit(targetPath);
        case 'grype':
          return await this.runGrype(targetPath);
        case 'custom_rules':
          return await this.runCustomRules(targetPath);
        case 'owasp_dependency_check':
          return await this.runOwaspDependencyCheck(targetPath);
        default:
          throw new Error(`Unknown scanner tool: ${tool}`);
      }
    }

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/NeoTecDigital/mcp_shamash'

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