search_mentions
shallowdev.rumoro/mcp · Verify this server
Searches the workspace's mentions. You can filter by keyword, platform, status (open, ignored, done), relevant, minimum relevance, minimum confidence (0 to 1), sentiment, intent, text (q, in the post or the author's name) and time range (ISO 8601). You can also filter by one person (personId from list_people), assignee (assigneeId), author followers (minFollowers, maxFollowers), engagement counts from the platform (minLikes, minReposts, minReplies, minQuotes, minViews, minBookmarks, where posts without that count are left out), review stars (ratings, or notRatings to exclude some), author tags (tags, any of them), linked hosts (linkHosts, a host or its subdomains), replies or not (isReply), and machine-made posts (automated true or false). alertId applies an alert's whole filter, giving the mentions it would send. viewId applies a saved view from list_views on top of the rest. keywordKinds filters by the kind of keyword that matched (brand, competitor, topic), and groupIds or notGroupIds by the keyword's group (ids from list_groups). All filters are joined by AND. For OR, anyOf takes up to 10 groups of the same conditions, each an object whose conditions are joined by AND, and keeps a mention when one group matches as well as the rest. For example anyOf=[{platforms:["github"],intents:["bug_report"]},{sentiments:["negative"]}]. Snoozed mentions are hidden unless snoozed=true. sort is "newest" (the default) or "priority", an attention score built from relevance, author reach, intent and age that covers only the past 30 days of matches and comes on each mention as `priority`. Returns 10 mentions by default, up to 100 with limit. Each mention contains post, author, classification and triage.
1 trials · measured today
search_mentions 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
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- gated
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-10-20 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 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.
[](https://vouch.tools/tools/e006adce-adc2-4dc8-8a5a-6df8daea1dcc)