Skip to main content
Glama
malkreide

hn-tech-signal-mcp

by malkreide

hn_search

Read-onlyIdempotent

Search HackerNews by keyword to find discussions on technologies, papers, companies, or events. Uses Algolia API and returns structured results with scores and links.

Instructions

Search HackerNews by keyword using the Algolia search API.

Covers all historical HN content. Find discussions on specific technologies, papers, companies, or events.

Args: params (HnSearchInput): - query (str): Search terms - limit (int): Results (1–20) - days_back (int): Recency window in days - tags (Optional[str]): 'story', 'ask_hn', 'show_hn', or empty

Returns: str: JSON with query, total_found, count, hits[]. Each hit: id, title, url, score, comments, author, posted, hn_link, excerpt.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
hitsYes
countYes
queryYes
days_backYes
total_foundYesHits Algolia reports in total, not just returned

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.5.0
    • addedOutput schema / $defs
      Added value: +{
      +  "HnSearchHit": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "author": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Author"
      +      },
      +      "comments": {
      +        "anyOf": [
      +          {
      +            "type": "integer"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Comments"
      +      },
      +      "excerpt": {
      +        "title": "Excerpt",
      +        "type": "string"
      +      },
      +      "hn_link": {
      +        "title": "Hn Link",
      +        "type": "string"
      +      },
      +      "id": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Id"
      +      },
      +      "posted": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Posted"
      +      },
      +      "score": {
      +        "anyOf": [
      +          {
      +            "type": "integer"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Score"
      +      },
      +      "title": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Title"
      +      },
      +      "url": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "title": "Url"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "title",
      +      "url",
      +      "score",
      +      "comments",
      +      "author",
      +      "posted",
      +      "hn_link",
      +      "excerpt"
      +    ],
      +    "title": "HnSearchHit",
      +    "type": "object"
      +  }
      +}
    • addedOutput schema / additionalProperties
      Added value: +false
    • addedOutput schema / properties / count
      Added value: +{
      +  "title": "Count",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / days_back
      Added value: +{
      +  "title": "Days Back",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / hits
      Added value: +{
      +  "items": {
      +    "$ref": "#/$defs/HnSearchHit"
      +  },
      +  "title": "Hits",
      +  "type": "array"
      +}
    • addedOutput schema / properties / query
      Added value: +{
      +  "title": "Query",
      +  "type": "string"
      +}
    • removedOutput schema / properties / result
      Removed value: -{
      -  "title": "Result",
      -  "type": "string"
      -}
    • addedOutput schema / properties / total_found
      Added value: +{
      +  "description": "Hits Algolia reports in total, not just returned",
      +  "title": "Total Found",
      +  "type": "integer"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "result"
      -]New value: +[
      +  "query",
      +  "days_back",
      +  "total_found",
      +  "count",
      +  "hits"
      +]
    • changedOutput schema / title
      Previous value: -"hn_searchOutput"New value: +"HnSearchOutput"
  2. First observedv0.2.4

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorldHint, so the safety profile is covered. The description adds useful context — Algolia backend and full historical coverage — but says nothing about rate limits, auth, pagination, or result-ordering behavior beyond the schema.

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 sentence followed by scope and an Args/Returns breakdown — well structured with no filler. The Returns block is somewhat redundant given an output schema exists, which is the only wasted content.

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 single-parameter search tool with annotations covering safety and an output schema covering returns, the description supplies purpose, scope, and parameter meaning. The only shortfall is the absence of sibling routing guidance among the seven related tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The reported schema description coverage is 0%, so the description carries the param burden and does so adequately: it enumerates query, limit (1–20), days_back (recency window), and tags ('story', 'ask_hn', 'show_hn', or empty). This largely mirrors the schema constraints but adds the tags value list and the notion of an empty tag meaning 'all', giving it slight edge over the raw schema.

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?

States a specific verb and resource ('Search HackerNews by keyword') plus the backend ('Algolia search API') and scope ('Covers all historical HN content'). It is clearly a full-text keyword search, but it never names or contrasts with the sibling hn_top_stories or hn_discussion, so differentiation relies on the reader's inference.

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?

'Find discussions on specific technologies, papers, companies, or events' implies the right use case, and 'all historical content' implies it is not a recency-browse tool. However, there is no explicit when-not guidance or reference to the sibling tools (hn_top_stories, hn_discussion) that an agent would need to choose correctly.

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