skovos

Skovos Governance connector: documentation

Skovos Governance gives health systems a registry of record for their AI agents, explicit permission checks, a tamper-evident audit trail, a stop control the hospital owns, and signed evidence that those controls ran. This connector exposes those capabilities to Claude and ChatGPT over the Model Context Protocol (MCP).

Connect

Tools

ToolWhat it doesChanges data?
governance_overviewOne-screen summary: agents, owners, scopes, denials, stops, audit integrityNo
list_agentsEvery registered agent with status, owner and scopesNo
register_agentRegister an agent with an identity, accountable owner, role and scopes (action:resource)Yes
check_permissionAllow or deny an action for an agent; the decision is auditedAdds an audit entry
record_actionAppend a hash-chained audit record of an agent action. Patient identifiers are rejected.Adds an audit entry
get_audit_trailRecent audit entries, filterable by agent or resourceNo
verify_audit_integrityRecompute the hash chain and report tamperingNo
recall_agentStop an agent immediately; all later checks deny itYes (destructive)
scan_phiHeuristic PHI detector with a redacted copy (Claude endpoint only; not a certified de-identification tool)No
export_overt_evidenceSigned, hash-chained evidence records (OVERT v1.1 style, self-declared profile, not a conformance claim). No agent names or content in the bundle.No
verify_overt_evidenceVerify an evidence bundle's signatures, chain and countersNo

Example prompts

Limits

Skovos governs agents that report into it or are checked through it. It does not observe systems it is not connected to. Evidence export uses a self-declared profile pending OVERT registration.