add_keyword

shallow

dev.rumoro/mcp · Verify this server

Creates a keyword to track. kind is "brand" (default), "competitor" or "topic". platforms limits where it runs, all by default. New posts with the term are matched, classified and delivered. To narrow a common word, set `matching` (requiredTerms with requiredMode any or all, excludedTerms with a `*` wildcard at either end, excludedAuthors, caseSensitive). Rejected posts are never stored or billed. `context` is one sentence for this keyword's classifier, such as "Basil is our deploy tool, not the herb." `cap` ({ mentions: N }) sets a monthly limit on matches. A capped keyword stops matching until the 1st (UTC) or a higher cap, and is still charged daily. `groupId` picks a group from list_groups, otherwise the default group. A term can exist once per group. `reviewSources` adds review pages, each as a url (App Store or Google Play app, Trustpilot page, Google Maps place or maps.app.goo.gl link) or a platform (appstore, googleplay, trustpilot, googlemaps) and id. App stores also take countries (two-letter, default us), and Google Play a language (default en). Every review becomes a mention, pages are read daily, and the last 30 days (up to 100 reviews) arrive free at once. `feeds` reads RSS or Atom feeds, each as { url }: a feed's address, or a page's (a forum, a community, a blog) whose advertised feed is used; an address with no feed is refused. An item is a mention when it holds the term, feeds are read every hour, and the newest 10 matching items of the last 30 days arrive at once, billed like any mention. `platforms: []` makes a reviews-only or feeds-only keyword. `comments` ({ enabled: true, maxPerPost: N }, off by default) reads the comments under its relevant mentions from 30 minutes after each post while its platform's conversations last, at most maxPerPost (default 20) per mention, $0.008 per comment delivered; list them with list_mention_comments.

100.0/100

1 trials · measured today

add_keyword scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against dev.rumoro/mcp, measured 20 Oct 2026 under methodology v0.2.0. Every measured component scored 100.

Component breakdown

ComponentWeightValue
Reliability35%not applicable
Schema integrity25%100.0
Failure behaviour15%not applicable
Latency15%not applicable
Concurrency10%not applicable

Tool details

Transport
remote
Credential class
gated
Input schema
not declared
Output schema
not declared
Side-effect classification
unclassified

Score history

DayScoreTierMethodology
2026-10-20100.0shallowv0.2.0

Probe evidence

ProbeOutcomes
schema_integritypass: 1

Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.

Embed this score

Available for every tool, scored or not — not a verification perk. Always links back to this page.

Vouch score: add_keyword
[![Vouch score](https://vouch.tools/api/tools/58f9bc95-9aa4-4ab5-a627-cd9836380452/badge.svg)](https://vouch.tools/tools/58f9bc95-9aa4-4ab5-a627-cd9836380452)
add_keyword — Vouch