Skip to main content
Glama
90barricade93

MSFS SDK MCP Server

natural_language_query

Process natural language queries to search Microsoft Flight Simulator SDK documentation, enabling users to find information using conversational language.

Instructions

Process natural language queries like "Search livery op msfs sdk"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesNatural language query (e.g., "Search livery op msfs sdk")

Implementation Reference

  • Main handler logic for the 'natural_language_query' tool. Parses the natural language query using NaturalLanguageService and dispatches to the corresponding tool handler.
    case 'natural_language_query':
      if (!args?.query) {
        throw new Error('Query parameter is required');
      }
    
      // Parse the natural language query
      const parsedCommand = NaturalLanguageService.parse(String(args.query));
    
      if (!parsedCommand) {
        throw new Error(`Could not parse natural language query: ${args.query}`);
      }
    
      // Execute the parsed command
      switch (parsedCommand.tool) {
        case 'search_msfs_docs':
          return await this.documentationService.searchDocumentation(
            String(parsedCommand.arguments.query),
            String(parsedCommand.arguments.category || 'all'),
            Number(parsedCommand.arguments.limit || 10)
          );
    
        case 'get_doc_content':
          return await this.documentationService.getDocumentationContent(
            String(parsedCommand.arguments.url),
            parsedCommand.arguments.section ? String(parsedCommand.arguments.section) : undefined
          );
    
        case 'list_categories':
          return await this.documentationService.listCategories();
    
        default:
          throw new Error(`Unknown parsed tool: ${parsedCommand.tool}`);
      }
  • Input schema definition for the 'natural_language_query' tool, registered in the ListTools response.
      name: 'natural_language_query',
      description: 'Process natural language queries like "Search livery op msfs sdk"',
      inputSchema: {
        type: 'object',
        properties: {
          query: {
            type: 'string',
            description: 'Natural language query (e.g., "Search livery op msfs sdk")',
          }
        },
        required: ['query']
      }
    },
  • src/index.ts:34-120 (registration)
    Registration of the tool list including 'natural_language_query' in the ListToolsRequestHandler.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: [
          {
            name: 'search_msfs_docs',
            description: 'Search MSFS SDK documentation for specific topics',
            inputSchema: {
              type: 'object',
              properties: {
                query: {
                  type: 'string',
                  description: 'Search query for MSFS SDK documentation',
                },
                category: {
                  type: 'string',
                  description: 'Optional category filter (e.g., "contents", "index", "glossary")',
                  enum: ['contents', 'index', 'glossary', 'all']
                },
                limit: {
                  type: 'number',
                  description: 'Maximum number of results to return',
                  minimum: 1,
                  maximum: 20,
                  default: 10
                }
              },
              required: ['query']
            }
          },
          {
            name: 'get_doc_content',
            description: 'Get detailed content from a specific MSFS SDK documentation page',
            inputSchema: {
              type: 'object',
              properties: {
                url: {
                  type: 'string',
                  description: 'URL of the documentation page to retrieve',
                },
                section: {
                  type: 'string',
                  description: 'Specific section to extract (e.g., "overview", "examples", "api-reference")',
                }
              },
              required: ['url']
            }
          },
          {
            name: 'list_categories',
            description: 'List all available MSFS SDK documentation categories',
            inputSchema: {
              type: 'object',
              properties: {}
            }
          },
          {
            name: 'natural_language_query',
            description: 'Process natural language queries like "Search livery op msfs sdk"',
            inputSchema: {
              type: 'object',
              properties: {
                query: {
                  type: 'string',
                  description: 'Natural language query (e.g., "Search livery op msfs sdk")',
                }
              },
              required: ['query']
            }
          },
          {
            name: 'list_category_items',
            description: 'Returns all items for a given documentation category',
            inputSchema: {
              type: 'object',
              properties: {
                category: {
                  type: 'string',
                  description: 'Category to list items from (index, contents, or glossary)',
                  enum: ['index', 'contents', 'glossary']
                }
              },
              required: ['category']
            }
          }
        ],
      };
    });
  • Core parsing logic for natural language queries, mapping phrases to tool names and arguments using regex patterns.
    static parse(command: string): { tool: string; arguments: any } | null {
      // Match "Search [term] op msfs sdk"
      const searchPattern = /^Search\s+(.+?)\s+op\s+msfs\s+sdk\s*$/i;
      const match = command.match(searchPattern);
      
      if (match) {
        const query = match[1];
        return {
          tool: "search_msfs_docs",
          arguments: {
            query: query,
            category: "all",
            limit: 5
          }
        };
      }
      
      // Match "Get content for [url]"
      const contentPattern = /^Get\s+content\s+for\s+(https?:\/\/.+)$/i;
      const contentMatch = command.match(contentPattern);
      
      if (contentMatch) {
        const url = contentMatch[1];
        return {
          tool: "get_doc_content",
          arguments: {
            url: url
          }
        };
      }
      
      // Match "List categories"
      if (command.toLowerCase() === "list categories") {
        return {
          tool: "list_categories",
          arguments: {}
        };
      }
      
      // Match "Show categories"
      if (command.toLowerCase() === "show categories") {
        return {
          tool: "list_categories",
          arguments: {}
        };
      }
      
      // Match "Search [term] in [category]"
      const categorySearchPattern = /^Search\s+(.+?)\s+in\s+(aircraft|scenery|simvars|panels|missions|packaging|tools|general)$/i;
      const categoryMatch = command.match(categorySearchPattern);
      
      if (categoryMatch) {
        const query = categoryMatch[1];
        const category = categoryMatch[2].toLowerCase();
        return {
          tool: "search_msfs_docs",
          arguments: {
            query: query,
            category: category,
            limit: 5
          }
        };
      }
      
      return null; // Onbekend commando
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the tool 'processes' queries but gives no behavioral details: no indication of what processing entails (e.g., parsing, interpreting, returning results), whether it's read-only or mutative, what permissions are needed, or what the output looks like. The example implies MSFS SDK context but doesn't clarify if this is required or just an example.

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 extremely concise with just one sentence and zero wasted words. It's front-loaded with the core purpose and includes a helpful example. Every element earns its place without redundancy or unnecessary elaboration.

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?

For a tool with no annotations and no output schema, the description is incomplete. It doesn't explain what 'processing' means behaviorally, what results to expect, or how this differs from sibling tools. The example suggests MSFS SDK context but leaves this ambiguous. More context is needed given the lack of structured metadata.

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%, so the schema already fully documents the single 'query' parameter. The description adds minimal value beyond the schema by providing an example query ('Search livery op msfs sdk'), but doesn't explain parameter semantics like format expectations, length limits, or special handling. Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Process natural language queries' with a specific example. It uses a verb ('process') and identifies the resource ('natural language queries'), but doesn't explicitly differentiate from sibling tools like 'search_msfs_docs' which might handle similar content.

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. It doesn't mention sibling tools like 'search_msfs_docs' or explain what makes this tool different (e.g., handling unstructured queries vs. structured searches). The example query suggests MSFS SDK context, but this isn't stated as a requirement or limitation.

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/90barricade93/MSFS-SDK-MCP'

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