Register this process-instance and mint its agent identity; keep the returned client_session_id for later calls. Call with force_new=true — a bare call with no ownership proof is defaulted to force_new or refused under strict identity, never resumed onto another process's uuid. parent_agent_id claims succession from an EXITED predecessor: naming a still-live parent is rejected as coincidental and the claim cleared, unless spawn_reason marks a dispatched child or a compaction continuation. Use identity to inspect or rename an existing binding. onboard is the canonical twin; this name adds a digest envelope. Read the uuid from agent_uuid; response_mode='full' keeps the raw payload under raw_governance.

Record a work check-in and get a governance decision: it advances and persists this agent's EISV state and returns proceed or pause with a named reason, plus a prediction_id — only when you pass confidence — to grade that check-in later with record_result. The first call auto-binds an identity, except under strict identity, which refuses and points at start_session. simulate_update previews a proposed check-in without advancing state, though it still appends an audit event; check_working_state reads the current verdict without writing. process_agent_update is the canonical twin; this name returns a digest envelope, and a routine check-in omits the raw payload (response_mode='full' adds it under raw_governance). EISV field definitions: describe_tool(tool_name='check_working_state').

Read your current governance state and verdict without running a cycle, writing, or minting an identity. Only proof sent with the call reads your state (start_session's client_session_id, an X-Session-ID header or a verified continuity_token), never an inferred binding; otherwise a self-read is unbound and next_action says how to recover. agent_id, dropped on /mcp/, names the agent to read through use_tool or REST unless you are bound as a different agent (identity_mismatch); that read is marked identity_assurance.caller_proven=false on an inferred session. verbosity='standard' adds mode and basin with their meanings under raw_governance; verbosity='full' (alias lite=false) returns the full canonical diagnostics. sync_state also logs work and returns proceed or pause. get_governance_metrics returns this read's raw payload. EISV fields: E=Energy [0,1] (mixed-provenance capacity estimate); I=Information Integrity [0,1] (mixed-provenance calibration estimate); S=Entropy [0,1] (drift from the agent's own normal); V=Valence [-1,1] (EMA-smoothed E-I imbalance; positive=motion outruns integrity, negative=integrity outruns motion).

Search the cross-agent knowledge graph for prior findings. Rows in status archived or cold are excluded unless you set status explicitly or pass include_archived / include_cold; a resolved or closed finding is still returned. Reading is not free of effect: every successful search appends a knowledge_read audit row naming the reader and a redacted copy of the query, which is why this tool is not annotated read-only. It serves unbound callers, so it works before start_session, unlike the writes: use store_finding to add a finding and use_tool(tool_name='update_finding', ...) to revise one.

Write one new durable finding into the cross-agent knowledge graph and get back its discovery_id. summary is required at call time even though the schema marks every field optional; severity high or critical is refused unless the session is bound to a registered agent, while low and medium fall back to an anonymous writer id. Every call mints a NEW discovery — search_shared_memory first, and revise one with use_tool(tool_name='update_finding', ...). Use it for a discovery, root cause or correction, and record_result for task, tool or test outcomes; budget 20 findings an hour.

Record a measurable outcome and pair it with this agent's EISV snapshot so verdicts can be graded against what really happened. Pass the prediction_id from a sync_state reply to bind the outcome to that check-in's confidence; it is consumed on first use and TTL-bound (an hour by default). Needs a bound or explicit agent_id, and refuses under strict identity from an ephemeral session. Provenance cannot be self-attested here: verification_source is forced and provenance keys in detail are stripped. Use store_finding for durable knowledge. outcome_event is the canonical twin; this name adds a digest envelope and keeps the raw payload under raw_governance only with response_mode='full' or include_semantics=true, or when the write returned no outcome_id. EISV field definitions: describe_tool(tool_name='check_working_state').

Open a governed, on-record review session for this agent. issue_description is reused as the thesis by default, so one call can reach a verdict; pass use_brief_as_thesis=false for the two-call form. Requires a session-owned registered identity, refuses with SESSION_EXISTS while one is active, and returns skipped with no session when the agent is waiting_input. dialectic advances an open session; consult gives advisory evidence with no verdict.

Discover the complete governance capability catalog, including names omitted from the initial progressive tools/list advertisement. The default lite=true response is the compact federation handshake: every public capability appears once as a name-only record beside the interface contract. Use lite=false for descriptions, categories, tiers, workflows, relationships, and direct-advertisement status. Use describe_tool for one capability's parameters, then use_tool to invoke a capability absent from the initial listing. Callable before an identity is bound.

Return one named tool's description, stability tier, operation, examples, and advertised JSON input schema. Use list_tools(lite=true) for the compact capability-name index or list_tools(lite=false) to browse rich catalog metadata. An unqualified describe call returns the full record because lite=false is the advertised default; pass lite=true for a first-line-plus-key-parameters summary. On a consolidated router, action=... narrows the response to that action's parameters.

Invoke one public capability omitted from the initial progressive tools/list advertisement. Find the exact name with list_tools and inspect its arguments with describe_tool, then pass that argument object here. The target's normal identity, validation, authorization, timeout and response middleware all run; this is a discovery gateway, not an authorization bypass. It refuses recursive use_tool calls.

Primary advisory model-help surface: send a brief, get back advisory model evidence, never a governed verdict — request_review produces that. effort='thorough' asks a strong model (Claude, Codex or Antigravity) from a family other than the caller's, when detectable. It needs privacy='cloud_allowed' and an operator extension a default install lacks (see list_inference_hosts); without both it fails unless allow_degraded=true, which returns a standard local answer instead. Requires a bound identity. Audited as event_type='consultation', readable by bound agents: route and keyed hashes, never text (key: record.hash_key). A success also updates your governance state. Use call_model or delegate_inference only for explicit provider, host, model or timeout control.

Resolve which agent this MCP session is bound to, or set a cosmetic display name. Not a plain read: a call carrying no proof argument at all is gated to a fresh mint, so it persists a new agent and reports on that one, marked caller_proven=false. A call carrying only a cosmetic name= skips that gate and can instead infer a co-located binding — pass client_session_id to get your own back. name= persists a cosmetic label only and never looks an agent up. For a fresh process call onboard(force_new=true). continuity_token is per-process ownership proof, not a transport-level claim: carrying it into another process re-opens silent resurrection.

Lifts a pause or other hold on your own agent. action='check', the default, changes no stored state, and both resuming actions verify you own the agent. Neither resume path runs while a void is active; quick also caps risk at 0.40, review at 0.65 plus a written reflection (20+ characters) on what happened, which is recorded in the shared knowledge graph under your agent whether or not it resumes. An attempt that reaches the safety checks stamps a fresh recovery_attempt_at even when they refuse it, so a retry is not a no-op; a missing reflection is rejected before that stamp. To resume an agent you do not own use operator_resume_agent.