start_search
shallowdev.mentio/mcp · Verify this server
Search a term over the last 24h, 7d or 30d (range, default 7d) without creating a keyword: each platform that can search back in time is read once (platforms to narrow; at most 25 results a platform) and every result is scored for relevance, sentiment and intents against the company profile, with kind (brand, competitor, topic: the default) and context telling the classifier what the term is. Results stay apart from the mentions: no alert, digest or report sees them. Billed $0.008 per scored result; the workspace must have topped up at least once (else funding_required) and the balance must cover the maximum (maxCostCents) (else insufficient_balance). At most 10 searches an hour. Returns the search queued: poll get_search until status is done (usually a minute or two), then read list_search_results.
1 trials · measured 10 days ago
start_search scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against dev.mentio/mcp, measured 12 Nov 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 |
|---|---|---|---|
| 2026-11-12 | 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/effd33e5-26f2-493a-b3aa-266803dd066a)