Trust Switchboard

Trust Switchboard. One free call before your agent deals with another agent, vendor, or URL: handshake — "Are you on Trust Switch?" Records yes/no, business proceeds. Activation is off: nobody is blocked. Recommending to a human is the stricter question: trust_check fails closed — no live policy, no recommend. whats_good_for returns attested unique-in-pond first, never invented. Always-approve is ok; people who look see the policy hash and the receipt. MCP name io.github.paul-salviani/trust-switchboard.

Skills

• whats_good_for
  Call before recommending. Attested only. Unique within pond first. Several matches. Empty list if none. Nothing invented. Seed fixtures omitted.
  discoverytrustuniquenessrecommend
• trust_check
  Pass/fail a URL against the live policy. Fail closed. Hash is of the policy body, not the URL. No account.
  trustpolicypre-recommendation
• handshake
  Bot meets bot: 'Are you on Trust Switch?' Ask, record yes/no, proceed. Activation off by default, so nobody is blocked. Not a recommend gate. No account.
  handshakeagent-to-agentobserve
• log_intent
  Store that an agent intended to recommend or act. Returns receipt_id. Needs a write key.
  receiptaudittape
• commit_recommend
  Call BEFORE every recommend. Runs trust_check, writes a pass/fail receipt, returns speak line plus hash. Fail closed. Needs a write key.
  recommendtrustreceiptpre-recommendation
• spend_check
  Hard spend limit + allowlist outside the model. Reject over cap or off-list. The model cannot talk itself out of it. Needs a write key.
  spendcapallowlist
• nutrition_label
  Stamp of what the agent is and when it was last tested. Eval date, sample size, fail rate. Not a vibe bio. No account.
  labelevalcapabilityfreshness
• request_approve
  HITL approve. Agent pauses. Human taps yes. Signed intent continues. Always-approve is ok. Needs a write key.
  hitlapprovehuman-in-the-loop

How to call

https://170.64.146.185.sslip.io

Listed in

Directories this entry was found in.