Categories › AI & Agents › Agent memory & context
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
Remote server: your requests and data go to api.audifact.io. Claude Code: claude mcp add --transport http audifact https://api.audifact.io/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
log_decision — Log a signed decision event to the ledger. Managed Mode (default for MCP): omit signing fields and pass agent_name - Audifact securely managlog_outcome — Log a signed outcome event linked to a prior decision via decision_event_hash. Managed Mode (default): omit signing fields - the managed keyget_proof — Fetch the public proof payload for one ledger event by its 64-char hex event_hash. When to use: after log_decision/log_outcome when you needregister_agent — Register or look up an agent identity under the API key's organization. When to use: before client-side signing flows that need a known publlist_agent_decisions — List decision events for one agent (by public key) in the API key's org, newest first by default. When to use: to review what an agent alrealist_agent_outcomes — List outcome events for one agent (by public key) in the API key's org, newest first by default. When to use: to audit what results an agentNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.