FeedKeeper RSS/Atom reader and remote MCP Server

List unread articles with optional filters

get_new_items

Retrieve unread RSS/Atom articles as a flat list filtered by feed, folder, search query, bookmarks, or date range, with optional HTML content for follow-up reading.

Instructions

Returns a flat list of unread articles matching specified filters (feed, folder, search query, bookmarked status, date range). Use this tool when you specifically need unread articles as a flat list or need article HTML content. Unlike get_digest, articles are flat rather than grouped. Unlike list_items, this tool returns only unread articles and does not use cursors. Follow up with get_item for individual full articles.

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_new_items"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of unread items to return (1 to 200, default: 50)
`since`	No	Filter for items published at or after this ISO date or date-time
`until`	No	Filter for items published at or before this ISO date or date-time
`feedId`	No	Optional feed ID filter
`search`	No	Optional search phrase to match against title or summary
`folderId`	No	Optional folder ID filter
`snippetChars`	No	Truncate each item summary to this many characters
`bookmarkedOnly`	No	When true, only returns unread articles that are bookmarked
`includeContent`	No	When false, omits article HTML content to save tokens (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.36.4Nov 9, 2026

addedInput schema / properties / bookmarkedOnly / description

Added value: +"When true, only returns unread articles that are bookmarked"

addedInput schema / properties / feedId / description
```
Added value: +"Optional feed ID filter"
```
addedInput schema / properties / folderId / description
```
Added value: +"Optional folder ID filter"
```

changedInput schema / properties / includeContent / description

Previous value: -"Set to false to leave out the article HTML and save tokens (default: true)"New value: +"When false, omits article HTML content to save tokens (default: true)"

addedInput schema / properties / limit / description

Added value: +"Maximum number of unread items to return (1 to 200, default: 50)"

addedInput schema / properties / search / description

Added value: +"Optional search phrase to match against title or summary"

changedInput schema / properties / since / description

Previous value: -"Only items published at or after this ISO date or date-time"New value: +"Filter for items published at or after this ISO date or date-time"

changedInput schema / properties / snippetChars / description

Previous value: -"Shorten each item's summary to this many characters"New value: +"Truncate each item summary to this many characters"

changedInput schema / properties / until / description

Previous value: -"Only items published at or before this ISO date or date-time"New value: +"Filter for items published at or before this ISO date or date-time"

First observedv0.36.3Nov 9, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full load and does well: it discloses the read-only nature implicitly, that results are a flat list rather than grouped, that no cursors are used (so no pagination loop is needed), and that HTML content can be included or omitted to save tokens. It stops short of stating ordering of results, whether unread status is ever mutated, or what an item record contains beyond content.

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?

Three sentences, front-loaded with the core purpose and followed by differentiation and a follow-up hint; no filler or restated title. The filter enumeration is slightly redundant with the schema, which keeps it from a perfect score.

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 9-parameter, zero-annotation, no-output-schema tool, the description covers purpose, result shape, token-saving content behavior, and the natural next call (get_item). The main remaining gap is the item structure and ordering, which nothing else in the definition supplies.

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 including limit, since/until, and includeContent is already documented in the schema. The description enumerates the filter families (feed, folder, search, bookmarked, date range) matching the schema keys but adds no syntax, defaults, or interaction rules beyond it, which is exactly the baseline-3 case.

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 and resource ("Returns a flat list of unread articles") plus the filter dimensions available, and explicitly contrasts itself with three siblings by name (get_digest, list_items, get_item). An agent can identify this tool and differentiate it from neighbors without consulting any schema.

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?

Gives an explicit selection condition ("when you specifically need unread articles as a flat list or need article HTML content") and names the alternatives with the property that separates them: get_digest returns grouped output, list_items uses cursors, get_item fetches full single articles. When-to-use, when-not-to-use, and next-step routing are all present.

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