FeedKeeper RSS/Atom reader and remote MCP Server

Digest of recent articles grouped by feed

get_digest

Scan recent articles grouped by subscribed feed with short summaries, newest first and unread by default, to review what is new before fetching full article bodies.

Instructions

Returns recent articles grouped by subscribed feed with short summaries (newest first). This is the fastest and most token-efficient way to scan what is new. Defaults to unread articles. Do NOT use this tool for pagination, full text, or deep filtering—use list_items for cursor pagination or get_new_items for unread filtering, and follow up with get_item for full article bodies.

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": "get_digest"
  }
}

Input Schema

Name	Required	Description
`hours`	No	Only include articles published in the last N hours (e.g. 24)
`since`	No	Only articles published at or after this ISO date or date-time (overrides hours)
`feedId`	No	Optional feed ID to limit the digest to a single feed
`folderId`	No	Optional folder ID to limit the digest to feeds in that folder
`unreadOnly`	No	When true (default), includes only unread articles; set false to include read articles
`snippetChars`	No	Maximum character length of each article summary snippet (default: 200)
`maxItemsPerFeed`	No	Maximum number of articles to include per feed (default: 5)

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.36.4Nov 9, 2026

addedInput schema / properties / feedId / description

Added value: +"Optional feed ID to limit the digest to a single feed"

addedInput schema / properties / folderId / description

Added value: +"Optional folder ID to limit the digest to feeds in that folder"

changedInput schema / properties / hours / description

Previous value: -"Only articles published in the last N hours"New value: +"Only include articles published in the last N hours (e.g. 24)"

changedInput schema / properties / maxItemsPerFeed / description

Previous value: -"Articles listed per feed (default: 5)"New value: +"Maximum number of articles to include per feed (default: 5)"

changedInput schema / properties / snippetChars / description

Previous value: -"Length of each snippet (default: 200)"New value: +"Maximum character length of each article summary snippet (default: 200)"

changedInput schema / properties / unreadOnly / description

Previous value: -"Include read articles too when false (default: true)"New value: +"When true (default), includes only unread articles; set false to include read articles"

First observedv0.36.3Nov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it discloses the default of unread-only, newest-first ordering, that summaries are short, and that this is the most token-efficient path. It does not explicitly state that the call is read-only and has no side effects (e.g. whether it affects unread state), leaving one meaningful behavioral gap for a tool with zero annotation coverage.

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?

Three sentences, front-loaded with the core behavior, then the value proposition, then the routing exclusions. Every clause earns its place and there is no restatement of the tool name.

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 7-parameter tool with no output schema, the description explains the shape of the result at a high level (grouped by feed, short summaries, newest first) and how to get full bodies by following up. It stops short of describing the per-feed grouping structure or result-count limits, which an agent without an output schema would benefit from.

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 100%, so every parameter (hours, since, feedId, folderId, unreadOnly, snippetChars, maxItemsPerFeed) is already documented with defaults and overrides. The description only reinforces the unreadOnly default and adds no syntax or usage detail beyond the schema, so the baseline 3 applies.

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 opens with a specific verb and resource ('Returns recent articles grouped by subscribed feed with short summaries') plus ordering ('newest first'), which lets an agent distinguish it immediately from list_items, get_new_items, and get_item. It also frames the tool's purpose as a fast scanning digest rather than a retrieval primitive.

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

Usage Guidelines5/5

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

It names both when to use (fast, token-efficient scan of what's new) and when not to use, with explicit alternatives: list_items for cursor pagination, get_new_items for unread filtering, get_item for full bodies. The exclusions are concrete enough that an agent won't misroute.

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