Skip to main content
Glama
baranwang

Trends Hub

get-36kr-trending

Fetch trending content from 36Kr to access startup, business, and technology insights including investment updates, emerging industry analysis, and business model innovations.

Instructions

获取 36 氪热榜,提供创业、商业、科技领域的热门资讯,包含投融资动态、新兴产业分析和商业模式创新信息

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNo分类hot

Implementation Reference

  • The async function that implements the tool logic: parses input with schema, fetches data from 36kr API via POST request, processes the response data into a list of trending items with fields like title, cover, author, etc.
    func: async (args) => {
      const { type } = get36krRequestSchema.parse(args);
    
      const resp = await http.post<{
        data: Record<string, any[]>;
      }>(
        `https://gateway.36kr.com/api/mis/nav/home/nav/rank/${type}`,
        {
          partner_id: 'wap',
          param: {
            siteId: 1,
            platformId: 2,
          },
          timestamp: Date.now(),
        },
        {
          headers: {
            'Content-Type': 'application/json; charset=utf-8',
          },
        },
      );
    
      return resp.data.data[LIST_TYPE_MAP[type]].map((item) => {
        const data = item.templateMaterial;
        return {
          title: data.widgetTitle,
          cover: data.widgetImage,
          author: data.authorName,
          publish_time: dayjs(data.publishTime).toISOString(),
          read_count: data.statRead,
          collect_count: data.statCollect,
          comment_count: data.statComment,
          praise_count: data.statPraise,
          link: `https://www.36kr.com/p/${data.itemId}`,
        };
      });
    },
  • Zod schema for input: object with optional 'type' union of 'hot', 'video', 'comment', 'collect' defaulting to 'hot'.
    const get36krRequestSchema = z.object({
      type: z
        .union([
          z.literal('hot').describe('人气榜'),
          z.literal('video').describe('视频榜'),
          z.literal('comment').describe('热议榜'),
          z.literal('collect').describe('收藏榜'),
        ])
        .optional()
        .default('hot')
        .describe('分类'),
    });
  • Tool registration using defineToolConfig with name 'get-36kr-trending', description, zodSchema, and func handler.
    export default defineToolConfig({
      name: 'get-36kr-trending',
      description: '获取 36 氪热榜,提供创业、商业、科技领域的热门资讯,包含投融资动态、新兴产业分析和商业模式创新信息',
      zodSchema: get36krRequestSchema,
      func: async (args) => {
        const { type } = get36krRequestSchema.parse(args);
    
        const resp = await http.post<{
          data: Record<string, any[]>;
        }>(
          `https://gateway.36kr.com/api/mis/nav/home/nav/rank/${type}`,
          {
            partner_id: 'wap',
            param: {
              siteId: 1,
              platformId: 2,
            },
            timestamp: Date.now(),
          },
          {
            headers: {
              'Content-Type': 'application/json; charset=utf-8',
            },
          },
        );
    
        return resp.data.data[LIST_TYPE_MAP[type]].map((item) => {
          const data = item.templateMaterial;
          return {
            title: data.widgetTitle,
            cover: data.widgetImage,
            author: data.authorName,
            publish_time: dayjs(data.publishTime).toISOString(),
            read_count: data.statRead,
            collect_count: data.statCollect,
            comment_count: data.statComment,
            praise_count: data.statPraise,
            link: `https://www.36kr.com/p/${data.itemId}`,
          };
        });
      },
    });
  • Mapping of type to list key in API response, e.g., hot -> 'hotRankList'.
    const LIST_TYPE_MAP: Record<z.infer<typeof get36krRequestSchema>['type'], string> = {
      hot: 'hotRankList',
      video: 'videoList',
      comment: 'remarkList',
      collect: 'collectList',
    };
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It describes what content is returned but lacks critical behavioral information: no mention of rate limits, authentication requirements, pagination, freshness/timing of data, or error conditions. The description doesn't contradict annotations (none exist), but provides minimal behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single Chinese sentence efficiently conveys the core purpose and content scope. No wasted words or redundant information. Could be slightly improved by front-loading the main action more explicitly, but overall well-structured and appropriately sized for a simple retrieval tool.

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, no output schema, and 19 similar sibling tools, the description is insufficiently complete. It doesn't explain what format the trending data returns (list of articles? rankings with scores?), how many items, update frequency, or how this differs from other Chinese news/trending tools. The agent lacks critical context to use this tool effectively versus alternatives.

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% with the single 'type' parameter fully documented in the schema. The description adds no parameter-specific information beyond what's in the schema. With high schema coverage and only one parameter, the baseline of 3 is appropriate - the description doesn't add value but doesn't need to compensate for schema gaps.

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: '获取 36 氪热榜' (get 36Kr trending list) with specific content domains (创业、商业、科技领域的热门资讯). It distinguishes from siblings by specifying the 36Kr source, but doesn't explicitly differentiate functionality from other news/trending tools beyond the source name.

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?

No guidance on when to use this tool versus the 19 sibling tools. The description mentions content domains (创业、商业、科技), but doesn't explain when to choose 36Kr over other Chinese news sources like Weibo, Douyin, or Zhihu trending tools. No explicit alternatives or exclusions are provided.

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/baranwang/mcp-trends-hub'

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