Skip to main content
Glama

search-yuque-docs

Search for documents within Yuque knowledge bases by matching keywords in titles and descriptions to quickly find relevant documentation.

Instructions

在指定的知识库中搜索文档。

会在文档标题和描述中进行关键词匹配。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes搜索关键词
namespaceNo知识库命名空间 (例如: username/repo),如果未提供则使用默认命名空间

Implementation Reference

  • The handler function for the 'search-yuque-docs' tool. Resolves the namespace, performs the search using the browser-based helper, formats the results as Markdown list, and returns structured content.
    async ({ query, namespace }) => { try { const finalNamespace = namespace || YUQUE_CONFIG.namespace; if (!finalNamespace) { return { content: [ { type: "text", text: `错误: 请提供知识库命名空间。\n\n示例: "username/repo"`, }, ], }; } if (!isValidNamespace(finalNamespace)) { return { content: [ { type: "text", text: `错误: 命名空间格式无效。\n\n命名空间应该是 "username/repo" 的格式。`, }, ], }; } // 搜索文档(使用无头浏览器) const docs = await searchYuqueDocsByBrowser(finalNamespace, query, YUQUE_CONFIG); if (docs.length === 0) { return { content: [ { type: "text", text: `没有找到匹配 "${query}" 的文档。\n\n知识库: ${finalNamespace}`, }, ], }; } // 格式化输出 let output = `# 搜索结果\n\n`; output += `**关键词**: ${query}\n`; output += `**知识库**: ${finalNamespace}\n`; output += `**找到**: ${docs.length} 个文档\n\n`; output += `---\n\n`; docs.forEach((doc, index) => { output += formatDocListItem(doc, index + 1); }); return { content: [ { type: "text", text: output, }, ], }; } catch (error) { return { content: [ { type: "text", text: `错误: ${error instanceof Error ? error.message : "未知错误"}`, }, ], }; } }
  • Input schema definition for the tool, including title, description, and Zod validation for 'query' (required string) and 'namespace' (optional string).
    { title: "搜索语雀文档", description: `在指定的知识库中搜索文档。 会在文档标题和描述中进行关键词匹配。`, inputSchema: { query: z.string().describe("搜索关键词"), namespace: z .string() .optional() .describe("知识库命名空间 (例如: username/repo),如果未提供则使用默认命名空间"), }, },
  • src/index.ts:308-393 (registration)
    Registers the 'search-yuque-docs' tool with the MCP server using server.registerTool, specifying name, schema, and handler.
    server.registerTool( "search-yuque-docs", { title: "搜索语雀文档", description: `在指定的知识库中搜索文档。 会在文档标题和描述中进行关键词匹配。`, inputSchema: { query: z.string().describe("搜索关键词"), namespace: z .string() .optional() .describe("知识库命名空间 (例如: username/repo),如果未提供则使用默认命名空间"), }, }, async ({ query, namespace }) => { try { const finalNamespace = namespace || YUQUE_CONFIG.namespace; if (!finalNamespace) { return { content: [ { type: "text", text: `错误: 请提供知识库命名空间。\n\n示例: "username/repo"`, }, ], }; } if (!isValidNamespace(finalNamespace)) { return { content: [ { type: "text", text: `错误: 命名空间格式无效。\n\n命名空间应该是 "username/repo" 的格式。`, }, ], }; } // 搜索文档(使用无头浏览器) const docs = await searchYuqueDocsByBrowser(finalNamespace, query, YUQUE_CONFIG); if (docs.length === 0) { return { content: [ { type: "text", text: `没有找到匹配 "${query}" 的文档。\n\n知识库: ${finalNamespace}`, }, ], }; } // 格式化输出 let output = `# 搜索结果\n\n`; output += `**关键词**: ${query}\n`; output += `**知识库**: ${finalNamespace}\n`; output += `**找到**: ${docs.length} 个文档\n\n`; output += `---\n\n`; docs.forEach((doc, index) => { output += formatDocListItem(doc, index + 1); }); return { content: [ { type: "text", text: output, }, ], }; } catch (error) { return { content: [ { type: "text", text: `错误: ${error instanceof Error ? error.message : "未知错误"}`, }, ], }; } } );
  • Helper function implementing the search logic: lists all documents in the namespace using browser scraping and filters those whose title contains the query keyword (case-insensitive).
    export async function searchYuqueDocsByBrowser( namespace: string, query: string, config: YuqueConfig ): Promise<YuqueDocListItem[]> { // 先获取所有文档,然后在客户端过滤 const allDocs = await listYuqueDocsByBrowser(namespace, config); return allDocs.filter((doc) => doc.title.toLowerCase().includes(query.toLowerCase()) ); }
  • Utility function to format each document in the search results as a Markdown list item with key metadata.
    export function formatDocListItem(doc: YuqueDocListItem, index?: number): string { let output = ""; if (index !== undefined) { output += `## ${index}. `; } output += `${doc.title}\n\n`; output += `- **Slug**: ${doc.slug}\n`; output += `- **格式**: ${doc.format}\n`; output += `- **字数**: ${doc.word_count}\n`; output += `- **更新时间**: ${new Date(doc.updated_at).toLocaleString("zh-CN")}\n`; output += `- **浏览量**: ${doc.hits}\n`; if (doc.description) { output += `- **描述**: ${doc.description}\n`; } output += `\n`; return output;

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/saoqixiaomm/yuque-mcp'

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