FeedKeeper RSS/Atom reader and remote MCP Server

Save article or clipping to Universal Inbox

save_to_inbox

Save web article URLs, HTML, text/markdown clippings, or personal notes directly to your Universal Inbox for later reading and organization.

Instructions

Saves a web article URL, raw HTML, plain text/markdown clipping, or personal note directly into the user's Universal Inbox. At least one of url, contentHtml, or textContent must be provided. Returns { success: true, itemId: number, title: string, url: string, hasNote: boolean }.

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": "save_to_inbox"
  }
}

Input Schema

Name	Required	Description
`url`	No	Web page URL to fetch, extract via Readability, and save
`note`	No	Optional personal note or editorial summary attached to the saved item
`title`	No	Optional custom title for the saved inbox item
`contentHtml`	No	Optional pre-rendered HTML content for the clipping
`textContent`	No	Optional plain text or markdown clipping content

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.36.4Nov 9, 2026

changedInput schema / properties / contentHtml / description

Previous value: -"Optional pre-rendered HTML content"New value: +"Optional pre-rendered HTML content for the clipping"

changedInput schema / properties / note / description

Previous value: -"Optional note or summary attached to the saved item"New value: +"Optional personal note or editorial summary attached to the saved item"

changedInput schema / properties / textContent / description

Previous value: -"Optional plain text or markdown clipping"New value: +"Optional plain text or markdown clipping content"

changedInput schema / properties / title / description

Previous value: -"Optional custom title"New value: +"Optional custom title for the saved inbox item"

changedInput schema / properties / url / description

Previous value: -"Web page URL to fetch, extract, and save"New value: +"Web page URL to fetch, extract via Readability, and save"

First observedv0.36.3Nov 9, 2026

TDQS

A4.2/5.0

Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the side effect (creates an item in the user's inbox) and even spells out the return shape. It says nothing about failure modes — e.g. what happens when the URL cannot be fetched, whether duplicates are created, or whether authentication/plan limits apply — which are the behaviors an agent most needs before writing.

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 short sentences: purpose first, validity constraint second, return contract third. Every sentence carries load and nothing is repeated from the schema property descriptions.

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 5-parameter write tool with no annotations and no output schema, the description covers purpose, the required-input rule, and the response fields inline. The remaining gap is error/edge-case behavior (failed fetch, duplicate saves, note-only calls), which a mutation tool arguably should address.

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?

Schema coverage is 100%, so the baseline is 3, and the description earns above that by stating a cross-parameter constraint the schema cannot express: zero required fields, yet at least one of url/contentHtml/textContent must be present. That is genuine added meaning about how the parameters combine.

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 ('Saves') plus the exact resource ('Universal Inbox') and enumerates the four accepted input kinds (URL, raw HTML, text/markdown clipping, personal note). No sibling tool in the list performs an ingest/save operation, so the boundary is unambiguous even without naming an alternative.

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?

Gives a concrete precondition: 'At least one of url, contentHtml, or textContent must be provided', which tells the agent how to assemble a valid call. It does not explain what to do when multiple content sources are supplied simultaneously or how this relates to any capture workflow, so it stops short of explicit alternatives/exclusions.

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