Skip to main content
Glama
sieteunoseis

mcp-cisco-support

Search Bugs by Keyword

search_bugs_by_keyword

Search Cisco bug database using keywords for symptoms, error messages, or general terms to identify relevant technical issues and solutions.

Instructions

Search for bugs using keywords in descriptions and headlines. Use this when searching by general terms, symptoms, or when product-specific tools are not applicable. IMPORTANT: severity parameter returns ONLY that specific level. For "severity 3 or higher" searches, use multi_severity_search tool instead. NOTE: Do NOT use product IDs (like ISR4431/K9) as keywords - use search_bugs_by_product_id instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYesKeywords to search for (general terms, symptoms, error messages - NOT product IDs)
page_indexNoPage number (10 results per page)
statusNoBug status filter. IMPORTANT: Only ONE status allowed per search. Values: O=Open, F=Fixed, T=Terminated. Do NOT use comma-separated values like "O,F".
severityNoBug severity filter. Returns bugs with ONLY the specified severity level. Values: 1=Severity 1 (highest), 2=Severity 2, 3=Severity 3, 4=Severity 4, 5=Severity 5, 6=Severity 6 (lowest). For "severity 3 or higher" bugs, use multi_severity_search tool which handles multiple separate API calls.
modified_dateNoLast modified date filter. Values: 1=Last Week, 2=Last 30 Days, 3=Last 6 Months, 4=Last Year, 5=All. Default: 5 (All)5
sort_byNoSort order for results. Default: modified_date (recent first)

Implementation Reference

  • Defines the input schema, title, description, and parameters for the search_bugs_by_keyword tool.
    name: 'search_bugs_by_keyword',
    title: 'Search Bugs by Keyword',
    description: 'Search for bugs using keywords in descriptions and headlines. Use this when searching by general terms, symptoms, or when product-specific tools are not applicable. IMPORTANT: severity parameter returns ONLY that specific level. For "severity 3 or higher" searches, use multi_severity_search tool instead. NOTE: Do NOT use product IDs (like ISR4431/K9) as keywords - use search_bugs_by_product_id instead.',
    inputSchema: {
      type: 'object',
      properties: {
        keyword: {
          type: 'string',
          description: 'Keywords to search for (general terms, symptoms, error messages - NOT product IDs)'
        },
        page_index: {
          type: 'integer',
          default: 1,
          description: 'Page number (10 results per page)'
        },
        status: {
          type: 'string',
          description: 'Bug status filter. IMPORTANT: Only ONE status allowed per search. Values: O=Open, F=Fixed, T=Terminated. Do NOT use comma-separated values like "O,F".',
          enum: ['O', 'F', 'T']
        },
        severity: {
          type: 'string',
          description: 'Bug severity filter. Returns bugs with ONLY the specified severity level. Values: 1=Severity 1 (highest), 2=Severity 2, 3=Severity 3, 4=Severity 4, 5=Severity 5, 6=Severity 6 (lowest). For "severity 3 or higher" bugs, use multi_severity_search tool which handles multiple separate API calls.',
          enum: ['1', '2', '3', '4', '5', '6']
        },
        modified_date: {
          type: 'string',
          description: 'Last modified date filter. Values: 1=Last Week, 2=Last 30 Days, 3=Last 6 Months, 4=Last Year, 5=All. Default: 5 (All)',
          enum: ['1', '2', '3', '4', '5'],
          default: '5'
        },
        sort_by: {
          type: 'string',
          description: 'Sort order for results. Default: modified_date (recent first)',
          enum: ['status', 'modified_date', 'severity', 'support_case_count', 'modified_date_earliest']
        },
      },
      required: ['keyword']
    }
  • Handles execution of search_bugs_by_keyword by constructing the Cisco Bug API endpoint `/bugs/keyword/{keyword}` with standard parameters and making the authenticated HTTP request.
        case 'search_bugs_by_keyword':
          endpoint = `/bugs/keyword/${encodeURIComponent(processedArgs.keyword)}`;
          break;
          
        case 'search_bugs_by_product_id':
          // Ensure forward slashes are properly encoded for product IDs like ISR4431-V/K9
          const encodedBasePid = encodeURIComponent(processedArgs.base_pid).replace(/\//g, '%2F');
          endpoint = `/bugs/products/product_id/${encodedBasePid}`;
          break;
          
        case 'search_bugs_by_product_and_release':
          // Ensure forward slashes are properly encoded for product IDs like ISR4431-V/K9
          const encodedBasePidForRelease = encodeURIComponent(processedArgs.base_pid).replace(/\//g, '%2F');
          endpoint = `/bugs/products/product_id/${encodedBasePidForRelease}/software_releases/${encodeURIComponent(processedArgs.software_releases)}`;
          break;
          
        case 'search_bugs_by_product_series_affected':
          endpoint = `/bugs/product_series/${encodeURIComponent(processedArgs.product_series)}/affected_releases/${encodeURIComponent(processedArgs.affected_releases)}`;
          break;
          
        case 'search_bugs_by_product_series_fixed':
          endpoint = `/bugs/product_series/${encodeURIComponent(processedArgs.product_series)}/fixed_in_releases/${encodeURIComponent(processedArgs.fixed_releases)}`;
          logger.info('Product series fixed endpoint', { 
            product_series: processedArgs.product_series,
            fixed_releases: processedArgs.fixed_releases,
            endpoint,
            fullUrl: `${this.baseUrl}${endpoint}`
          });
          break;
          
        case 'search_bugs_by_product_name_affected':
          endpoint = `/bugs/products/product_name/${encodeURIComponent(processedArgs.product_name)}/affected_releases/${encodeURIComponent(processedArgs.affected_releases)}`;
          break;
          
        case 'search_bugs_by_product_name_fixed':
          endpoint = `/bugs/products/product_name/${encodeURIComponent(processedArgs.product_name)}/fixed_in_releases/${encodeURIComponent(processedArgs.fixed_releases)}`;
          break;
          
        // Enhanced search tools
        case 'smart_search_strategy':
          return this.generateSearchStrategy(processedArgs);
    
        case 'progressive_bug_search':
          return this.executeProgressiveSearch(processedArgs, meta);
    
        case 'multi_severity_search':
          return this.executeMultiSeveritySearch(processedArgs, meta);
    
        case 'comprehensive_analysis':
          return this.executeComprehensiveAnalysis(processedArgs, meta);
    
        case 'compare_software_versions':
          return this.executeCompareSoftwareVersions(processedArgs, meta);
    
        case 'product_name_resolver':
          return this.executeProductNameResolver(processedArgs);
          
        default:
          throw new Error(`Tool implementation not found: ${name}`);
      }
      
      return await this.makeApiCall(endpoint, apiParams) as BugApiResponse;
    }
  • ApiRegistry.getAvailableTools() collects tools from BugApi.getTools() (including search_bugs_by_keyword) and returns them for MCP tools/list.
      // In OAuth 2.1 mode, filter tools based on current request scopes
      let apisToUse = this.enabledApis;
    
      if (process.env.AUTH_TYPE === 'oauth2.1' && currentRequestScopes) {
        apisToUse = getEnabledAPIs(currentRequestScopes);
      }
    
      const availableTools: Tool[] = [];
    
      for (const apiName of apisToUse) {
        // Handle sampling tools specially (they're not in the apis map)
        if (apiName === 'sampling') {
          availableTools.push(...samplingTools);
          continue;
        }
    
        const api = this.apis.get(apiName);
        if (api) {
          const apiTools = api.getTools();
          availableTools.push(...apiTools);
        }
      }
    
      return availableTools;
    }
  • Instantiates BugApi instance in ApiRegistry, making its tools (including search_bugs_by_keyword) available.
      // Initialize implemented APIs
      this.apis.set('bug', new BugApi());
      this.apis.set('case', new CaseApi());
      this.apis.set('eox', new EoxApi());
      this.apis.set('psirt', new PsirtApi());
      this.apis.set('product', new ProductApi());
      this.apis.set('software', new SoftwareApi());
      this.apis.set('serial', new SerialApi());
      this.apis.set('rma', new RmaApi());
      this.apis.set('enhanced_analysis', new EnhancedAnalysisApi());
      this.apis.set('smart_bonding', new SmartBondingApi() as any); // Cast needed due to different base class
    }
  • formatSearchContext helper adds search context display for search_bugs_by_keyword results.
    if (searchContext.toolName === 'search_bugs_by_keyword' && searchContext.args.keyword) {
      formatted += `**Search Keywords:** "${searchContext.args.keyword}"\n\n`;
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the tool's search scope (descriptions and headlines), the exclusive nature of severity filtering ('returns ONLY that specific level'), and important constraints about what NOT to search for (product IDs). It also hints at pagination behavior through the page_index parameter context. The description doesn't fully cover all potential behavioral aspects like rate limits or authentication requirements, but provides substantial operational context.

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

Conciseness5/5

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

The description is perfectly structured with three sentences that each earn their place: the first states the core purpose, the second provides usage guidelines, and the third gives critical exclusions. It's front-loaded with essential information and contains zero wasted words or redundant information. The IMPORTANT and NOTE markers effectively highlight critical constraints without adding unnecessary length.

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

Completeness4/5

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

For a search tool with 6 parameters (1 required), 100% schema coverage, and no output schema, the description provides excellent contextual completeness. It covers purpose, usage guidelines, behavioral constraints, and exclusions. The main gap is the lack of information about return format or result structure, which would be helpful since there's no output schema. However, given the comprehensive parameter documentation and clear operational context, it's mostly complete.

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?

With 100% schema description coverage, the schema already documents all 6 parameters thoroughly. The description adds some semantic context by reinforcing the keyword parameter's purpose ('general terms, symptoms, error messages') and warning against product IDs, and by explaining the severity parameter's exclusive behavior. However, most parameter semantics are already covered in the schema, so the description adds only marginal value beyond what's already structured.

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 clearly states the specific action ('Search for bugs using keywords in descriptions and headlines') and distinguishes it from multiple sibling tools by explicitly mentioning when NOT to use it (e.g., for product IDs). It provides a precise verb+resource+scope combination that differentiates it from alternatives like search_bugs_by_product_id and multi_severity_search.

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?

The description provides explicit guidance on when to use this tool ('when searching by general terms, symptoms, or when product-specific tools are not applicable') and when NOT to use it (for product IDs or severity 3+ searches). It names specific alternative tools (multi_severity_search, search_bugs_by_product_id) and provides clear exclusion criteria, making it easy for an agent to choose correctly among siblings.

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/sieteunoseis/mcp-cisco-support'

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