whale-insights

feed_archive

Read-onlyIdempotent

News feed archive — paginated 30-day history (public, MCP-compatible) — Returns a paginated archive of crypto news articles, analysis, and AI-generated summaries from the CryptoWhaleInsights feed, covering the last 30 days. Whale movement events are excluded — use /api/public/whale-movements for on-chain flow data. AI agents can use this to read the latest crypto news, market analysis, and AI-generated summaries without any credentials. Optional type filter: news (RSS articles), ai (AI-generated summaries), manual (analyst notes). Default: all non-whale-move items. Optional keyword search: q (max 100 chars) filters by token name or keyword — case-insensitive match on title and summary (e.g. q=ETH returns only ETH-related items). Pagination: page (1-indexed, default 1), pageSize fixed at 20. period filter: 7d | 30d (default 30d — maximum public window). Response: { items[], total, page, pageSize, hasMore, updatedAt }. Each item: id (number), title (string), summary (string), source (string — feed source name e

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "feed_archive"
  }
}

Input Schema

Name	Required	Description	Default
`q`	No	Keyword or token name search (max 100 chars). Case-insensitive match on title and summary. Example: q=ETH returns only items mentioning ETH.
`page`	No	Page number (1-indexed, default 1).
`type`	No	Filter by article type: news (RSS), ai (AI-generated), manual (analyst notes). Default: all types.
`period`	No	Time window: 7d \| 30d (default 30d — the maximum public window).	30d

Output Schema

Name	Required	Description
`page`	No	Current page (1-indexed)
`items`	No	News articles and analysis items in reverse-chronological order.
`total`	No	Total matching articles in the window
`hasMore`	No	Whether more pages are available
`pageSize`	No	Fixed at 20 records per page
`updatedAt`	No
`attribution`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "attribution": {
+      "$ref": "#/components/schemas/Attribution"
+    },
+    "hasMore": {
+      "description": "Whether more pages are available",
+      "type": "boolean"
+    },
+    "items": {
+      "description": "News articles and analysis items in reverse-chronological order.",
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Unique feed item row ID",
+            "type": "number"
+          },
+          "publishedAt": {
+            "description": "Publication timestamp",
+            "format": "date-time",
+            "nullable": true,
+            "type": "string"
+          },
+          "source": {
+            "description": "Feed source name, e.g. 'CoinDesk', 'CoinTelegraph'",
+            "type": "string"
+          },
+          "summary": {
+            "description": "Article summary or AI-generated digest",
+            "type": "string"
+          },
+          "title": {
+            "description": "Article or summary title",
+            "type": "string"
+          },
+          "type": {
+            "description": "'news_summary' | 'ai_insights' | 'analysis'",
+            "type": "string"
+          },
+          "url": {
+            "description": "Original article URL, if available",
+            "nullable": true,
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "page": {
+      "description": "Current page (1-indexed)",
+      "type": "number"
+    },
+    "pageSize": {
+      "description": "Fixed at 20 records per page",
+      "type": "number"
+    },
+    "total": {
+      "description": "Total matching articles in the window",
+      "type": "number"
+    },
+    "updatedAt": {
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedJun 24, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The annotations already declare read-only, idempotent, non-destructive behavior, and the description adds substantial context beyond them: no credentials required, pageSize fixed at 20, 30-day maximum public window, case-insensitive q matching, and the response/item shape. There is no contradiction with the annotations.

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?

The description is front-loaded with purpose and efficiently covers filters, pagination, and response details. It is slightly redundant at the opening ('News feed archive — paginated 30-day history... Returns a paginated archive...' repeats paginated/30-day/archive), and the final field explanation appears truncated, but overall each section earns its place.

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?

For a four-parameter read-only feed tool with an output schema, the description covers every invocation concern: all parameters with defaults, max window, fixed page size, credential-free access, exclusions/alternatives, and response fields. No required call-time information appears to be missing.

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

Parameters5/5

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

Schema coverage is already 100%, but the description adds meaningful value by explaining q with an example and case-insensitivity, defining type values (news RSS, ai AI-generated, manual analyst notes), noting page is 1-indexed, and revealing that 30d is the maximum public window. This goes well beyond the schema baseline.

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 ('Returns') and names the exact resource: a paginated archive of crypto news, analysis, and AI-generated summaries from the CryptoWhaleInsights feed. It also explicitly carves out whale-movement events and points to a different endpoint, which distinguishes it from the whale-related siblings.

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?

It clearly frames when to use the tool ('AI agents can use this to read the latest crypto news... without any credentials') and gives a direct alternative for whale-movement data ('use /api/public/whale-movements'). However, it does not distinguish this archive from the closely related analyst_archive sibling for analyst-note content, so the routing guidance is not fully complete.

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

All whale-insights 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.

Resources

Need Help?