unofficial-HackerNews-MCP-CLI

Get stories

get_stories

Read-onlyIdempotent

Retrieve HackerNews stories from top, new, best, ask, show, or job categories with title, URL, score, author, comment count, and discussion link. Set limit and offset to control results.

Instructions

Get a list of HackerNews stories from a category, with full details.

'top', 'new' and 'best' draw from up to 500 stories; 'ask', 'show' and 'job' from up to 200. Each result includes title, url, score, author, comment count and the canonical HN discussion link.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	How many stories to return (1-500).
`offset`	No	Skip this many stories from the top of the list.
`category`	No	Which list: top, new, best, ask, show, or job stories.	top
`strip_html`	No	Return plain text instead of HTML in text and title.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.0Sep 21, 2026

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Skip this many stories from the top of the list.",
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / strip_html

Added value: +{
+  "default": false,
+  "description": "Return plain text instead of HTML in text and title.",
+  "type": "boolean"
+}

Changed3 schema fields changedv0.2.0Sep 7, 2026

addedOutput schema / properties / result / items / description

Added value: +"A HackerNews item: story, comment, job, poll, or poll option."

addedOutput schema / properties / result / items / properties

Added value: +{
+  "by": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The username of the item's author."
+  },
+  "dead": {
+    "anyOf": [
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "True if the item is dead."
+  },
+  "deleted": {
+    "anyOf": [
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "True if the item is deleted."
+  },
+  "descendants": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "In the case of stories or polls, the total comment count."
+  },
+  "hn_url": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "Canonical HackerNews discussion link.",
+    "readOnly": true
+  },
+  "id": {
+    "description": "The item's unique id.",
+    "type": "integer"
+  },
+  "kids": {
+    "anyOf": [
+      {
+        "items": {
+          "type": "integer"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The ids of the item's comments, in ranked display order."
+  },
+  "parent": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The comment's parent: either another comment or the story."
+  },
+  "parts": {
+    "anyOf": [
+      {
+        "items": {
+          "type": "integer"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "A list of related pollopts, in display order."
+  },
+  "poll": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The pollopt's associated poll."
+  },
+  "score": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The story's score, or poll option votes."
+  },
+  "text": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The comment, story or poll text (HTML)."
+  },
+  "time": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Creation date, in Unix time."
+  },
+  "title": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The title of the story, poll or job (HTML)."
+  },
+  "type": {
+    "anyOf": [
+      {
+        "enum": [
+          "job",
+          "story",
+          "comment",
+          "poll",
+          "pollopt"
+        ],
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "One of 'job', 'story', 'comment', 'poll', 'pollopt'."
+  },
+  "url": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "The URL of the story."
+  }
+}

addedOutput schema / properties / result / items / required
```
Added value: +[
+  "id",
+  "hn_url"
+]
```

First observedv0.1.0Jul 14, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds meaningful behavioral context beyond the annotations, such as per-category upper bounds (500 vs 200 stories) and the specific fields returned in each result.

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 compact and front-loaded with the core action, followed by two sentences of helpful specifics. Every sentence earns its place, and there is no redundant repetition of schema or annotation content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a read-only list tool given the rich annotations and full schema coverage. It explains category-specific limits, what fields appear in results, and the general scope, so an agent has enough context to invoke the tool correctly.

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?

Input schema coverage is 100%, with descriptions already provided for limit, offset, category, and strip_html. The description does not add significant parameter-level semantics beyond the schema; it mentions categories and result details but not new guidance on how parameters should be used.

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 uses a specific verb-resource pair ('Get a list of HackerNews stories') and immediately clarifies it returns full details per story. It distinguishes itself from sibling tools like get_item, get_comments, and get_user by focusing on category-based story lists.

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

Usage Guidelines3/5

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

The description makes usage context clear: it is for retrieving stories by category, and it names the supported categories. However, it does not explicitly tell the agent when to choose this over get_items or get_item, so guidance on alternatives is only implied by the sibling tool names.

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

Deploy Server