All servers · Code & repositories · Monitoring & logs · Maps, location & weather
Trust Switchboard
io.github.paul-salviani/trust-switchboard · v1.1.0
New (7 days)Tools changed (7 days)
Measured by MCP Station
| Last check | Reachable |
|---|---|
| Checked at | — |
| Check success 7 / 30 days | — |
| First-try success 30 days | — |
| Median response | — |
| Lookups 30 days | — |
| Authentication | No auth |
| MCP version | 2025-06-18 |
| Rank score | — |
| Declared risk | Can write (some tools are not declared read-only) |
| Capabilities declared | tools |
| Tool definitions | 12 tools · with description 100% · input schema is an object 100% · read/destructive hints 8% |
Description written by the publisher, not verified
Read public privacy policies: dated source excerpts, follow-up questions and change comparisons.
Connect
streamable-http · https://170.64.146.185.sslip.io/mcp
claude mcp add --transport http trust-switchboard https://170.64.146.185.sslip.io/mcp{
"mcpServers": {
"trust-switchboard": {
"url": "https://170.64.146.185.sslip.io/mcp"
}
}
}Tools as reported by the server
policy_evidenceRead one public English privacy-policy HTTPS URL. Returns dated keyword-matched source excerpts about data location, retention, AI training, sharing and privacy contacts, plus comparison with a prior saved check. No membership or key required. Saves a publicly shareable report. Source text is untruswhats_good_forCall before recommending. Attested only, unique-in-pond first, never invent. Empty if none.trust_checkPass/fail a URL against the live policy before recommending it to a human. Fail closed.handshakeBot meets bot: ask 'Are you on Trust Switch?' before dealing with another agent or vendor. Records yes/no. While activation is off (default) business proceeds either way. Not a recommend gate; use trust_check for that.log_intentLog that you intend to recommend or act. Needs a write key. Returns receipt_id.commit_recommendCall BEFORE every recommend. Runs trust_check, logs pass/fail, returns speak + receipt. Needs a write key.ingest_listingIngest a listing and score uniqueness inside one pond. Needs a write key.log_clickRecord that a human clicked an item after a receipt. Public.spend_checkHard cap + allowlist; cannot override. Fail closed. Needs a write key.nutrition_labelStamp of what it is + last test.request_approveHITL pause. Agent waits; human taps yes. Needs a write key.decide_approveHuman tap. Public so the desk can approve without the org key.
Tool changes
- 2026-10-20: policy_evidence, whats_good_for, trust_check, handshake, log_intent, commit_recommend, ingest_listing, log_click, spend_check, nutrition_label, request_approve, decide_approve
- 2026-10-16: whats_good_for, trust_check, handshake, log_intent, commit_recommend, ingest_listing, log_click, spend_check, nutrition_label, request_approve, decide_approve
Repository · Website · JSON · Text for agents · Registry updated 2026-10-20