Skip to main content
Glama
devabdultech

Hacker News MCP Server

by devabdultech

getStories

Retrieve Hacker News stories by category (top, new, best, ask, show, job) to access trending discussions and content from the community.

Instructions

Get multiple stories by type (top, new, best, ask, show, job)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeYesThe type of stories to fetch
limitNoThe maximum number of stories to fetch

Implementation Reference

  • src/index.ts:91-111 (registration)
    Registration of the 'getStories' tool in the ListToolsRequestSchema handler, including name, description, and input schema definition.
    {
      name: "getStories",
      description:
        "Get multiple stories by type (top, new, best, ask, show, job)",
      inputSchema: {
        type: "object",
        properties: {
          type: {
            type: "string",
            enum: ["top", "new", "best", "ask", "show", "job"],
            description: "The type of stories to fetch",
          },
          limit: {
            type: "number",
            description: "The maximum number of stories to fetch",
            default: 30,
          },
        },
        required: ["type"],
      },
    },
  • The primary handler for the 'getStories' tool in the CallToolRequestSchema switch statement. Fetches story IDs by type from HN API, retrieves items, formats stories, and constructs a response with a numbered list.
    case "getStories": {
      const { type, limit = 30 } = args as {
        type: "top" | "new" | "best" | "ask" | "show" | "job";
        limit?: number;
      };
      try {
        let storyIds: number[] = [];
    
        switch (type) {
          case "top":
            storyIds = await hnApi.getTopStories(limit);
            break;
          case "new":
            storyIds = await hnApi.getNewStories(limit);
            break;
          case "best":
            storyIds = await hnApi.getBestStories(limit);
            break;
          case "ask":
            storyIds = await hnApi.getAskStories(limit);
            break;
          case "show":
            storyIds = await hnApi.getShowStories(limit);
            break;
          case "job":
            storyIds = await hnApi.getJobStories(limit);
            break;
        }
    
        const items = await hnApi.getItems(storyIds);
        const stories = items
          .filter((item) => item && item.type === "story")
          .map(formatStory);
    
        if (stories.length === 0) {
          return {
            content: [{ type: "text", text: "No stories found." }],
          };
        }
    
        const text = stories
          .map(
            (story, index) =>
              `${index + 1}. ${story.title}\n` +
              `   ID: ${story.id}\n` +
              `   URL: ${story.url || "(text post)"}\n` +
              `   Points: ${story.score} | Author: ${story.by} | Comments: ${story.descendants}\n\n`
          )
          .join("");
    
        return {
          content: [{ type: "text", text: text.trim() }],
        };
      } catch (err) {
        const error = err as Error;
        throw new McpError(
          ErrorCode.InternalError,
          `Failed to fetch stories: ${error.message}`
        );
      }
    }
  • Helper function used by the handler to format raw Hacker News story items into a standardized Story object.
    export function formatStory(item: any): Story {
      return {
        id: item.id,
        title: item.title,
        url: item.url,
        text: item.text,
        by: item.by,
        score: item.score || 0,
        time: item.time,
        descendants: item.descendants || 0,
        kids: item.kids || [],
        type: "story",
      };
    }
  • Helper methods in HackerNewsAPI class to fetch story ID lists for different categories (top, new, best, ask, show, job), used by the getStories handler.
    async getTopStories(limit: number = 30): Promise<number[]> {
      const response = await fetch(`${API_BASE_URL}/topstories.json`);
      const ids = (await response.json()) as number[];
      return ids.slice(0, limit);
    }
    
    /**
     * Fetch new stories
     */
    async getNewStories(limit: number = 30): Promise<number[]> {
      const response = await fetch(`${API_BASE_URL}/newstories.json`);
      const ids = (await response.json()) as number[];
      return ids.slice(0, limit);
    }
    
    /**
     * Fetch best stories
     */
    async getBestStories(limit: number = 30): Promise<number[]> {
      const response = await fetch(`${API_BASE_URL}/beststories.json`);
      const ids = (await response.json()) as number[];
      return ids.slice(0, limit);
    }
    
    /**
     * Fetch ask stories
     */
    async getAskStories(limit: number = 30): Promise<number[]> {
      const response = await fetch(`${API_BASE_URL}/askstories.json`);
      const ids = (await response.json()) as number[];
      return ids.slice(0, limit);
    }
    
    /**
     * Fetch show stories
     */
    async getShowStories(limit: number = 30): Promise<number[]> {
      const response = await fetch(`${API_BASE_URL}/showstories.json`);
      const ids = (await response.json()) as number[];
      return ids.slice(0, limit);
    }
    
    /**
     * Fetch job stories
     */
    async getJobStories(limit: number = 30): Promise<number[]> {
      const response = await fetch(`${API_BASE_URL}/jobstories.json`);
      const ids = (await response.json()) as number[];
      return ids.slice(0, limit);
    }
  • Helper method to batch fetch multiple HN items by IDs, used in the getStories handler.
    async getItems(ids: number[]): Promise<any[]> {
      return Promise.all(ids.map((id) => this.getItem(id)));
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior3/5

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

No annotations are provided, so the description must convey all behavioral traits. It states 'get multiple stories' but does not disclose ordering, pagination, rate limits, or the format of returned data (e.g., story IDs vs full objects). The limit parameter is described in the schema, but behavioral details are lacking.

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 a single sentence of 9 words, efficiently conveying the tool's purpose. No extraneous information is included.

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?

For a simple retrieval tool with two parameters and no output schema, the description is moderately complete. It covers the core functionality, but omits details about the output format (list of story objects or IDs) and potential behavior with invalid types or limits. Slightly more context would improve completeness.

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 explains both parameters. The description adds no additional meaning beyond listing the enum values, which are also in the schema. The baseline score of 3 is appropriate.

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

Purpose5/5

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

The description clearly states the tool retrieves multiple stories and specifies the exact story types (top, new, best, ask, show, job). It distinguishes from sibling tools like getStory (single story) and getComments, making the purpose unambiguous.

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 indicates when to use the tool (by story type) but does not explicitly mention when not to use it or provide alternatives. However, the sibling tool names suggest getStory for a single story, so the usage context is implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.