Skip to main content
Glama

ai_search_juejin

Search Juejin technical community articles to find programming resources. This tool generates search URLs for accessing Chinese developer content through the Smart Search MCP server.

Instructions

💎 掘金搜索 - 搜索掘金技术社区文章

【重要】此工具会返回掘金搜索URL,Claude Code应该使用WebFetch工具访问该URL以获取真实搜索结果。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes搜索关键词
sortNo排序方式hot

Implementation Reference

  • Shared handler logic for ai_search_juejin and other Chinese platforms. Normalizes query, maps to Juejin search URL, uses platform-specific config, generates detailed Markdown response with WebFetch instructions, saves to file.
    case 'ai_search_csdn':
    case 'ai_search_juejin':
    case 'ai_search_segmentfault':
    case 'ai_search_cnblogs':
    case 'ai_search_oschina':
    case 'ai_search_aliyun_docs':
    case 'ai_search_tencent_docs': {
      const rawQuery = normalizeString(args.query);
    
      if (!rawQuery) {
        throw new Error('搜索关键词不能为空');
      }
    
      const searchUrls = {
        ai_search_csdn: `https://so.csdn.net/so/search?q=${encodeURIComponent(rawQuery)}`,
        ai_search_juejin: `https://juejin.cn/search?query=${encodeURIComponent(rawQuery)}`,
        ai_search_segmentfault: `https://segmentfault.com/search?q=${encodeURIComponent(rawQuery)}`,
        ai_search_cnblogs: `https://zzk.cnblogs.com/s?w=${encodeURIComponent(rawQuery)}`,
        ai_search_oschina: `https://www.oschina.net/search?scope=all&q=${encodeURIComponent(rawQuery)}`,
        ai_search_aliyun_docs: `https://help.aliyun.com/search?spm=a2c4g.11186623.0.0&k=${encodeURIComponent(rawQuery)}`,
        ai_search_tencent_docs: `https://cloud.tencent.com/search?s=doc&keyword=${encodeURIComponent(rawQuery)}`
      };
    
      const platformInfo = {
        ai_search_csdn: {
          name: 'CSDN',
          icon: '📝',
          description: '中国最大的IT社区和服务平台',
          tips: ['博客文章', '技术问答', '代码片段', '下载资源'],
          homepage: 'https://www.csdn.net/',
          toolKey: 'csdn-search'
        },
        ai_search_juejin: {
          name: '掘金',
          icon: '💎',
          description: '面向开发者的技术内容分享平台',
          tips: ['前端开发', '后端开发', 'Android', 'iOS', '人工智能'],
          homepage: 'https://juejin.cn/',
          toolKey: 'juejin-search'
        },
        ai_search_segmentfault: {
          name: 'SegmentFault',
          icon: '🔧',
          description: '中文技术问答社区',
          tips: ['技术问答', '技术文章', '活动沙龙', '编程挑战'],
          homepage: 'https://segmentfault.com/',
          toolKey: 'sf-search'
        },
        ai_search_cnblogs: {
          name: '博客园',
          icon: '📚',
          description: '开发者的网上家园',
          tips: ['.NET', 'C#', 'Java', 'Python', '数据库'],
          homepage: 'https://www.cnblogs.com/',
          toolKey: 'cnblogs-search'
        },
        ai_search_oschina: {
          name: '开源中国',
          icon: '🌐',
          description: '中国最大的开源技术社区',
          tips: ['开源项目', '技术资讯', '代码托管', '协作翻译'],
          homepage: 'https://www.oschina.net/',
          toolKey: 'oschina-search'
        },
        ai_search_aliyun_docs: {
          name: '阿里云文档',
          icon: '☁️',
          description: '阿里云产品文档中心',
          tips: ['ECS', 'OSS', 'RDS', 'SLB', '容器服务'],
          homepage: 'https://help.aliyun.com/',
          toolKey: 'aliyun-docs'
        },
        ai_search_tencent_docs: {
          name: '腾讯云文档',
          icon: '☁️',
          description: '腾讯云产品文档中心',
          tips: ['CVM', 'COS', 'CDN', 'SCF', '数据库'],
          homepage: 'https://cloud.tencent.com/document/product',
          toolKey: 'tencent-docs'
        }
      };
    
      const info = platformInfo[name];
      const searchUrl = searchUrls[name];
    
      const detailsContent = `${info.icon} ${info.name} 搜索\n\n` +
        `**搜索关键词**: ${rawQuery}\n` +
        `**平台介绍**: ${info.description}\n\n` +
        `---\n\n` +
        `🔗 **搜索链接**: ${searchUrl}\n\n` +
        `⚠️ **请使用 WebFetch 工具获取搜索结果**:\n` +
        `\`\`\`javascript\n` +
        `WebFetch({\n` +
        `  url: "${searchUrl}",\n` +
        `  prompt: "提取前10条搜索结果(标题、作者、发布时间、摘要、链接)"\n` +
        `})\n` +
        `\`\`\`\n\n` +
        `---\n\n` +
        `💡 **${info.name} 热门主题**:\n` +
        info.tips.map(tip => `• ${tip}`).join(' | ') +
        `\n\n🏠 **平台首页**: ${info.homepage}\n\n` +
        `📌 **搜索建议**:\n` +
        `• 使用精确关键词获得更好的结果\n` +
        `• 结合多个平台搜索可获得更全面的信息\n` +
        `• 关注文章的发布时间,优先查看最新内容`;
    
      const filepath = await saveSearchResult(info.toolKey, rawQuery, detailsContent);
    
      return makeTextResponse(
        `${info.icon} **${info.name}搜索**\n\n` +
        `**关键词**: ${rawQuery}\n` +
        `**搜索链接**: ${searchUrl}\n\n` +
        `✅ 详细信息已保存至: ${filepath || '保存失败'}\n` +
        `💡 使用 WebFetch 工具访问搜索链接获取结果`
      );
    }
  • Input schema validation for ai_search_juejin: requires 'query' string, optional 'sort' enum ['hot', 'time', 'like'] with default 'hot'.
    inputSchema: {
      type: 'object',
      properties: {
        query: { type: 'string', description: '搜索关键词' },
        sort: { type: 'string', enum: ['hot', 'time', 'like'], description: '排序方式', default: 'hot' }
      },
      required: ['query']
  • Tool definition object for ai_search_juejin including name, description, and inputSchema, included in AI_TOOLS array for server registration.
    {
      name: 'ai_search_juejin',
      description: '💎 掘金搜索 - 搜索掘金技术社区文章\n\n【重要】此工具会返回掘金搜索URL,Claude Code应该使用WebFetch工具访问该URL以获取真实搜索结果。',
      inputSchema: {
        type: 'object',
        properties: {
          query: { type: 'string', description: '搜索关键词' },
          sort: { type: 'string', enum: ['hot', 'time', 'like'], description: '排序方式', default: 'hot' }
        },
        required: ['query']
      }
    },
  • Registers the list of tools (including ai_search_juejin) with the MCP server for ListToolsRequestSchema.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: AI_TOOLS,
    }));
  • Platform-specific configuration helper for ai_search_juejin used in the handler to customize response content.
    ai_search_juejin: {
      name: '掘金',
      icon: '💎',
      description: '面向开发者的技术内容分享平台',
      tips: ['前端开发', '后端开发', 'Android', 'iOS', '人工智能'],
      homepage: 'https://juejin.cn/',
      toolKey: 'juejin-search'
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 does an excellent job describing the key behavioral trait: that this tool returns a URL rather than direct search results, and that Claude Code should use WebFetch to access the actual results. This is crucial information not apparent from the input schema alone. It doesn't mention rate limits, authentication needs, or error handling, but provides the most critical behavioral information.

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 concise and well-structured. The first sentence states the core purpose. The second sentence provides the critical behavioral information about URL returns and WebFetch usage. Every sentence earns its place with essential information. The emoji adds visual distinction without compromising clarity.

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?

Given the tool's moderate complexity (search with parameters), no annotations, and no output schema, the description does quite well. It explains the purpose, provides crucial behavioral context about URL returns, and gives usage guidance. It doesn't explain return values, but with no output schema, some mention of expected results would be helpful. The description is mostly complete but could benefit from mentioning what kind of information the URL contains.

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 both parameters (query and sort with enum values). The description adds no additional parameter information beyond what's in the schema. According to the scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter info in the description, which applies here.

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 searches for articles on the Juejin technical community with the phrase '搜索掘金技术社区文章'. It uses a specific verb ('搜索' - search) and identifies the resource ('掘金技术社区文章' - Juejin technical community articles). However, it doesn't explicitly differentiate from sibling tools like ai_search_csdn or ai_search_segmentfault that also search Chinese technical communities, missing full sibling distinction.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool: searching Juejin articles. The second sentence offers important guidance about the output format (returns a URL) and how to proceed (use WebFetch tool). However, it doesn't explicitly state when NOT to use it or name specific alternatives among the many sibling search tools, which would be needed for a perfect score.

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/adminhuan/smart-search-mcp'

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