Skip to main content
Glama
malkreide

hn-tech-signal-mcp

by malkreide
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

hn_top_stories

Read-onlyIdempotent

Fetch HackerNews front-page stories by feed (top, best, new, ask, show, job), filter by score, and set limits to track tech and AI signals.

Instructions

Fetch stories from any of the six HackerNews front-page feeds.

Feeds: 'top' (frontpage), 'best' (highest voted), 'new' (latest), 'ask' (Ask HN — questions to the community), 'show' (Show HN — projects people are shipping), 'job' (YC company job posts).

'show' is the strongest signal for what practitioners are actually building; 'ask' for what they are stuck on. Upstream, 'ask' and 'job' hold only ~30 items, so a large limit may return fewer results.

Args: params (HnTopStoriesInput): - feed (str): 'top', 'best', 'new', 'ask', 'show', or 'job' - limit (int): Stories to return (1–30) - min_score (int): Minimum score filter (job posts score 1)

Returns: str: JSON with feed, count, stories[]. Each story: id, type, title, url, score, comments, by, posted, hn_link.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
feedYes
countYes
storiesYes
fetched_atYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv0.5.0
    • addedOutput schema / $defs
      Added value: +{
+  "HnStory": {
+    "additionalProperties": false,
+    "properties": {
+      "by": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "title": "By"
+      },
+      "comments": {
+        "title": "Comments",
+        "type": "integer"
+      },
+      "hn_link": {
+        "title": "Hn Link",
+        "type": "string"
+      },
+      "id": {
+        "anyOf": [
+          {
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "title": "Id"
+      },
+      "posted": {
+        "description": "UTC timestamp, or 'unknown'",
+        "title": "Posted",
+        "type": "string"
+      },
+      "score": {
+        "title": "Score",
+        "type": "integer"
+      },
+      "title": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "title": "Title"
+      },
+      "type": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "'story' or 'job'",
+        "title": "Type"
+      },
+      "url": {
+        "description": "Linked article, or the HN item itself for Ask HN",
+        "title": "Url",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "type",
+      "title",
+      "url",
+      "score",
+      "comments",
+      "by",
+      "posted",
+      "hn_link"
+    ],
+    "title": "HnStory",
+    "type": "object"
+  }
+}
    • addedOutput schema / additionalProperties
      Added value: +false
    • addedOutput schema / properties / count
      Added value: +{
+  "title": "Count",
+  "type": "integer"
+}
    • addedOutput schema / properties / feed
      Added value: +{
+  "title": "Feed",
+  "type": "string"
+}
    • addedOutput schema / properties / fetched_at
      Added value: +{
+  "title": "Fetched At",
+  "type": "string"
+}
    • removedOutput schema / properties / result
      Removed value: -{
-  "title": "Result",
-  "type": "string"
-}
    • addedOutput schema / properties / stories
      Added value: +{
+  "items": {
+    "$ref": "#/$defs/HnStory"
+  },
+  "title": "Stories",
+  "type": "array"
+}
    • changedOutput schema / required
      Previous value: -[
-  "result"
-]New value: +[
+  "feed",
+  "fetched_at",
+  "count",
+  "stories"
+]
    • changedOutput schema / title
      Previous value: -"hn_top_storiesOutput"New value: +"HnTopStoriesOutput"
  2. Changed2 schema fields changedv0.3.0
    • changedInput schema / $defs / HnTopStoriesInput / properties / feed / description
      Previous value: -"Feed type: 'top' (frontpage), 'best' (highest voted), 'new' (latest)"New value: +"Feed type: 'top' (frontpage), 'best' (highest voted), 'new' (latest), 'ask' (Ask HN questions), 'show' (Show HN projects), 'job' (YC job posts). Note: 'ask' and 'job' are short feeds (~30 items upstream)."
    • changedInput schema / $defs / HnTopStoriesInput / properties / feed / pattern
      Previous value: -"^(top|best|new)$"New value: +"^(top|best|new|ask|show|job)$"
  3. First observedv0.2.4

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, so the bar is lower. The description adds a valuable upstream constraint not in annotations: 'ask' and 'job' hold only ~30 items so large limits may under-deliver. Doesn't mention rate limits or pagination, but the feed-shortness caveat is meaningful beyond what structured fields provide.

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?

Front-loaded purpose, feed glossary, and return shape are clearly structured. The practitioner-signal commentary and Args/Returns sections are useful, though the Args section restates schema content and slightly inflates length.

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?

An output schema exists, so return-shape detail is redundant but harmless. Feed semantics and the upstream

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 0% per context signals, partly because the params are nested under a $ref. The schema does contain descriptions for feed/limit/min_score, so the description largely duplicates them. It adds one extra bit ('job posts score 1') but does not add meaning beyond the schema's own wording.

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?

States a specific verb+resource ('Fetch stories from any of the six HackerNews front-page feeds') and enumerates each feed with its meaning. Distinguished from siblings like hn_search and hn_discussion by being the feed lister.

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?

Explicitly signals when each feed is most useful ('show' is strongest for what practitioners build, 'ask' for what they're stuck on), giving selection guidance. However, no explicit comparison to hn_search or hn_discussion for when to use this over those alternatives.

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

Deploy Server

Other Tools