Skip to main content
Glama

validate_documentation_metadata

Validate that documentation files contain required metadata fields to ensure completeness and consistency across documents.

Instructions

Ensure all documents have required metadata fields.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNo
basePathNo
requiredFieldsNo

Implementation Reference

  • The core handler function that implements the tool logic: scans all .md files in the basePath (default docs dir), parses frontmatter using parseFrontmatter helper, checks for required metadata fields (default: title, description, status), collects missing ones, computes completeness percentage, and returns a ToolResponse with results.
    /** * Validate metadata in documentation */ async validateMetadata( basePath = "", requiredFields?: string[] ): Promise<ToolResponse> { try { const validBasePath = await this.validatePath(basePath || this.docsDir); // Default required fields if not specified const fields = requiredFields || ["title", "description", "status"]; // Find all markdown files const files = await glob("**/*.md", { cwd: validBasePath }); const missingMetadata: Array<{ file: string; missingFields: string[]; }> = []; // Check each file for metadata for (const file of files) { const filePath = path.join(validBasePath, file); const content = await fs.readFile(filePath, "utf-8"); // Parse frontmatter const { frontmatter } = parseFrontmatter(content); // Check for required fields const missing = fields.filter((field) => !frontmatter[field]); if (missing.length > 0) { missingMetadata.push({ file: path.relative(this.docsDir, filePath), missingFields: missing, }); } } // Calculate completeness percentage const totalFields = files.length * fields.length; const missingFields = missingMetadata.reduce( (sum, item) => sum + item.missingFields.length, 0 ); const completenessPercentage = totalFields > 0 ? Math.round(((totalFields - missingFields) / totalFields) * 100) : 100; return { content: [ { type: "text", text: missingMetadata.length > 0 ? `Found ${missingMetadata.length} files with missing metadata. Completeness: ${completenessPercentage}%` : `All ${files.length} files have complete metadata. Completeness: 100%`, }, ], metadata: { missingMetadata, filesChecked: files.length, requiredFields: fields, completenessPercentage, basePath: path.relative(this.docsDir, validBasePath), }, }; } catch (error) { const errorMessage = error instanceof Error ? error.message : String(error); return { content: [ { type: "text", text: `Error validating metadata: ${errorMessage}` }, ], isError: true, }; } }
  • Zod schema defining the input parameters for the tool: optional basePath (defaults to root) and optional array of requiredFields.
    export const ValidateMetadataSchema = ToolInputSchema.extend({ basePath: z.string().optional().default(""), requiredFields: z.array(z.string()).optional(), });
  • src/index.ts:290-294 (registration)
    Tool registration in the MCP server's listTools handler, specifying name, description, and input schema.
    { name: "validate_documentation_metadata", description: "Ensure all documents have required metadata fields.", inputSchema: zodToJsonSchema(ValidateMetadataSchema) as any, },
  • Dispatch handler in the main CallToolRequestSchema switch statement that validates input and calls the DocumentHandler's validateMetadata method.
    case "validate_documentation_metadata": { const parsed = ValidateMetadataSchema.safeParse(args); if (!parsed.success) { throw new Error( `Invalid arguments for validate_metadata: ${parsed.error}` ); } return await documentHandler.validateMetadata( parsed.data.basePath, parsed.data.requiredFields ); }
  • Helper function used by validateMetadata to parse YAML frontmatter from markdown files and extract metadata fields.
    export function parseFrontmatter(content: string): { frontmatter: Record<string, any>; content: string; } { const frontmatterRegex = /^---\s*\n([\s\S]*?)\n---\s*\n/; const match = content.match(frontmatterRegex); if (!match) { return { frontmatter: {}, content }; } const frontmatterStr = match[1]; const contentWithoutFrontmatter = content.slice(match[0].length); // Parse frontmatter as key-value pairs const frontmatter: Record<string, any> = {}; const lines = frontmatterStr.split("\n"); for (const line of lines) { const colonIndex = line.indexOf(":"); if (colonIndex !== -1) { const key = line.slice(0, colonIndex).trim(); let value = line.slice(colonIndex + 1).trim(); // Handle quoted values if (value.startsWith('"') && value.endsWith('"')) { value = value.slice(1, -1); } // Handle arrays if (value.startsWith("[") && value.endsWith("]")) { try { value = JSON.parse(value); } catch { // Keep as string if parsing fails } } frontmatter[key] = value; } } return { frontmatter, content: contentWithoutFrontmatter }; }

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/alekspetrov/mcp-docs-service'

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