Trust Switchboard

io.github.paul-salviani/trust-switchboard · v1.0.2 · agents-and-memory

Trust Switchboard is healthy: it completed an MCP handshake in 3530 ms and exposes 11 tools.

Ask "Are you on Trust Switch?" before your agent deals with another agent. Free. Never blocks.

Endpoint: https://170.64.146.185.sslip.io/mcp (streamable-http)

Repository · Website · JSON · Add to my inventory

Facts

Users (last 30 days)0
HandshakeHealthy
Auth neededNone
Tool count11
Latency3530 ms
Last checked (UTC)2026-10-15T06:20:53.657Z

Health history

Checked (UTC)StatusLatencyError
2026-10-15T06:20:53.657ZHealthy3530

Tools (11)

whats_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.