Skip to main content
Glama
noodlemctwoodle

Sentinel Solutions MCP Server

search_solutions

Find Microsoft Sentinel solutions by name, publisher, or keyword. Retrieve details about data connectors, detections, and playbooks from GitHub repositories.

Instructions

Search solutions by name, publisher, or keyword

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The execute function that implements the search_solutions tool logic. It searches solutions by name (case-insensitive match), filters by publisher and/or support_tier, groups connector-table mappings by solution, and returns matching solutions with connector/table counts.
    export const searchSolutionsTool = {
      name: 'search_solutions',
      description: 'Search solutions by name, publisher, or keyword',
      inputSchema: z.object({
        query: z.string().describe('Search query'),
        publisher: z.string().optional().describe('Filter by publisher'),
        support_tier: z.string().optional().describe('Filter by support tier'),
      }),
      execute: async (args: {
        query: string;
        publisher?: string;
        support_tier?: string;
      }): Promise<SearchResult> => {
        await ensureAnalysis();
    
        if (!cachedAnalysisResult) {
          throw new Error('Analysis results not available');
        }
    
        const queryLower = args.query.toLowerCase();
    
        // Group by solution
        const solutionMap = new Map<string, any>();
    
        cachedAnalysisResult.mappings.forEach((mapping) => {
          if (!solutionMap.has(mapping.solution)) {
            solutionMap.set(mapping.solution, {
              name: mapping.solution,
              publisher: mapping.publisher,
              version: mapping.version,
              supportTier: mapping.supportTier,
              connectorIds: new Set<string>(),
              tables: new Set<string>(),
            });
          }
    
          const sol = solutionMap.get(mapping.solution)!;
          sol.connectorIds.add(mapping.connectorId);
          sol.tables.add(mapping.tableName);
        });
    
        // Filter solutions
        const matchingSolutions = Array.from(solutionMap.values()).filter((sol) => {
          const matchesQuery = sol.name.toLowerCase().includes(queryLower);
          const matchesPublisher = !args.publisher || sol.publisher === args.publisher;
          const matchesTier = !args.support_tier || sol.supportTier === args.support_tier;
    
          return matchesQuery && matchesPublisher && matchesTier;
        });
    
        return {
          solutions: matchingSolutions.map((sol) => ({
            name: sol.name,
            publisher: sol.publisher,
            version: sol.version,
            supportTier: sol.supportTier,
            connectorCount: sol.connectorIds.size,
            tableCount: sol.tables.size,
          })),
        };
      },
    };
  • Zod input schema for the search_solutions tool, defining query (required string), publisher (optional string), and support_tier (optional string) parameters.
    inputSchema: z.object({
      query: z.string().describe('Search query'),
      publisher: z.string().optional().describe('Filter by publisher'),
      support_tier: z.string().optional().describe('Filter by support tier'),
    }),
  • SearchResult interface defining the output shape: an array of solutions with name, publisher, version, optional supportTier, connectorCount, and tableCount.
    export interface SearchResult {
      solutions: Array<{
        name: string;
        publisher: string;
        version: string;
        supportTier?: string;
        connectorCount: number;
        tableCount: number;
      }>;
    }
  • solutionTools array registration that includes searchSolutionsTool for export and aggregation.
    export const solutionTools = [
      analyzeSolutionsTool,
      getConnectorTablesTool,
      searchSolutionsTool,
      getSolutionDetailsTool,
      listTablesTool,
      validateConnectorTool,
    ];
  • src/index.ts:27-36 (registration)
    MCP server registration: list_tools handler exposes the tool name/description/schema, and call_tool handler dispatches by name to the tool's execute function.
    // Handle list_tools request
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: allTools.map((tool) => ({
          name: tool.name,
          description: tool.description,
          inputSchema: tool.inputSchema,
        })),
      };
    });
Behavior1/5

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

With no annotations provided, the description carries the full burden. It only states the basic function and fails to disclose behavioral traits such as pagination, output format, or authentication requirements.

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 a single concise sentence that is front-loaded with the action. Every word earns its place with no redundancy.

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

Completeness2/5

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

Given three optional parameters, no output schema, and many sibling tools, the description is too sparse. It omits information about return values, pagination, and error handling, which is insufficient for complete understanding.

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 description coverage is 100% (baseline 3). The description adds meaning for 'query' and 'publisher' but ignores 'support_tier', so it partially compensates but does not fully enhance understanding.

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 verb 'search' and resource 'solutions', and specifies searchable fields (name, publisher, keyword), distinguishing it from sibling tools like analyze_solutions or get_solution_details.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives, nor any context on prerequisites or when not to use it.

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/noodlemctwoodle/sentinel-solutions-mcp'

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