inoreader-mcp

Search articles

search_articles

Read-onlyIdempotent

Search articles by keyword across all RSS feeds, with date filters, pagination, and compact results. Use it to find specific content in your Inoreader subscriptions by topic or term.

Instructions

Search for articles by keyword across all feeds. Costs 1 Zone 1 request per page. Uses undocumented but stable search endpoint. Base costs exclude safe-read retries (up to 4 attempts, each counted); honor cached status/cooldown. Never blindly replay uncertain writes. See inoreader://usage for limits, URI examples and prompts.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_articles"
  }
}

Input Schema

Name	Required	Description
`count`	No	Number of results to return (1-100, default 20)
`query`	Yes	Search query string
`since`	No	ISO date string - only return articles published after this date
`compact`	No	Return only id, title, source, is_starred, is_kept (default false).
`continuation`	No	Continuation token for pagination (from previous response)

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.6.1Nov 3, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Adds real information beyond the annotations: per-page Zone 1 cost, up to 4 counted retry attempts, cooldown/cached-status handling, and that the endpoint is undocumented but stable. The sentence "Never blindly replay uncertain writes" is confusing boilerplate on a readOnlyHint=true tool and dilutes trust, which keeps this from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and dense, with the core purpose first and cost second. However, the trailing write-safety and resource-pointer sentences feel grafted on from a shared boilerplate block and do not earn their place for a keyword search.

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 read tool with a fully documented schema and no output schema, the description covers cost, retry behavior, and pagination awareness adequately. It does not say what a result contains (id/title/source per the compact flag), but the schema's compact description covers that gap.

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 coverage is 100%, so query/since/count/compact/continuation are already fully described in the schema. The description only indirectly touches parameters by saying "per page," which links cost to count/continuation but adds no syntax or usage detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Search for articles by keyword across all feeds"), which is unambiguous about scope. It does not differentiate itself from the obvious siblings get_articles and get_article_ids, so an agent must infer that this is the keyword-query path versus plain listing.

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?

Usage is implied by "by keyword across all feeds" and the cost note hints at a budget-aware context, but there is no explicit statement of when to prefer this over get_articles/get_article_ids, nor any exclusion. The pointer to inoreader://usage offloads guidance to a resource rather than giving it inline.

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