Social Fetch

List a Hacker News feed

hackernews_feed_list

Read-only

List a Hacker News feed by type (top, new, best, ask, show, or jobs). Accepts a feed name. Returns a list (use page/pageSize when paginated).

Input Schema

TableJSON Schema

Name	Required	Description
`feed`	Yes	Hacker News feed: top, new, best, ask, show, or jobs.
`page`	No	Zero-based page index (maximum 50 pages). Default: 0. Advance with `data.page.nextPage` when `hasMore` is true.
`trim`	No	Ignored if this tool does not support it.
`limit`	No	Items to hydrate per page (1–50). Default: 30. Prefer this over `pageSize`.
`offset`	No	Ignored if this tool does not support it.
`context`	Yes	Describe the user's underlying goal in one sentence — not the tool you are calling.
`pageSize`	No	Deprecated alias for `limit`. When both are set, `limit` wins.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`maxResults`	No	Ignored if this tool does not support it.
`max_results`	No	Ignored if this tool does not support it.
`conversation_id`	No	Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 21, 2026

addedInput schema / properties / maxResults

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / max_results

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / offset

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / trim

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

Changed5 schema fields changedSep 5, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / context

Added value: +{
+  "description": "Describe the user's underlying goal in one sentence — not the tool you are calling.",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "feed"
-]New value: +[
+  "feed",
+  "context",
+  "llm_model"
+]

Changed1 schema field changedAug 27, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed2 schema fields changedAug 4, 2026

addedInput schema / properties / limit

Added value: +{
+  "description": "Items to hydrate per page (1–50). Default: 30. Prefer this over `pageSize`.",
+  "maximum": 50,
+  "minimum": 1,
+  "type": "integer"
+}

changedInput schema / properties / pageSize / description

Previous value: -"Items to hydrate per page (1–50). Default: 30."New value: +"Deprecated alias for `limit`. When both are set, `limit` wins."

Changed4 schema fields changedAug 3, 2026

removedInput schema / properties / limit

Removed value: -{
-  "description": "Maximum items to hydrate (1–50). Default: 30.",
-  "maximum": 50,
-  "minimum": 1,
-  "type": "integer"
-}

removedInput schema / properties / offset

Removed value: -{
-  "description": "Zero-based offset into the official feed id list.",
-  "maximum": 500,
-  "minimum": 0,
-  "type": "integer"
-}

addedInput schema / properties / page

Added value: +{
+  "description": "Zero-based page index (maximum 50 pages). Default: 0. Advance with `data.page.nextPage` when `hasMore` is true.",
+  "maximum": 49,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / pageSize

Added value: +{
+  "description": "Items to hydrate per page (1–50). Default: 30.",
+  "maximum": 50,
+  "minimum": 1,
+  "type": "integer"
+}

Changed1 schema field changedJul 29, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
AddedJul 26, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already carry read-only/open-world safety, so the description doesn't need to restate them. It adds only 'Returns a list' and a pagination hint; no output shape, item fields, or follow-up behavior is disclosed. This meets the lowered bar but does not go beyond it.

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?

Two short sentences, front-loaded with enumerations and purpose. Minor redundancy ('Accepts a feed name' restates the first sentence) and the deprecated pageSize hint keep it from a 5.

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 read-only list with a rich schema and safe annotations, the description names all feed variants and pagination behavior. Without an output schema, saying it returns a list is adequate; item-level detail would be nice but not necessary to invoke correctly.

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

Parameters2/5

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

Schema covers 100% of parameters, so the baseline is 3, but the description's 'use page/pageSize' conflicts with the schema's deprecation of pageSize and preference for limit. It adds no meaning beyond the schema and inaccurately steers pagination.

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?

Leads with a specific verb and resource ('List a Hacker News feed') and enumerates the six feed kinds, making its scope concrete. 'Feed' clearly distinguishes it from nearby search/story/user-list tools even without naming them.

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?

Implies the call is appropriate when the user wants a top/new/best/ask/show/jobs feed, but it never says when to prefer hackernews_search_list, hackernews_story_get, or story_comments. The pagination hint addresses how to page, not which tool to choose.

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

All Social Fetch tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

List a Hacker News feed

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources