Serveur MCP

Delx Protocol — Agent Recovery & Continuity

io.github.davidmosiah/delx-protocol
Infrastructure MCP et agents Productivité Public et accessible MCP 2026-07-28

Ce que fait ce MCP

Supports agent session continuity through persistent context, handoff capsules, recovery workflows, witness lineage, failure handling, and operational check-ins.

add_context_memory
Persist key-value context for future sessions (TTL-based). Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id', 'key', 'value'], 'properties': {'key': {'type': 'string', 'description': 'Context key'}, 'value': {'type': 'string', 'description': 'Context value'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'ttl_hours': {'type': 'integer', 'maximum': 8760, 'minimum': 1, 'description': 'Optional retention window in hours'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
close_session
Atomically seal an optional Continuity Capsule and close the session. Pass capsule={version, goal, done, next, blockers, refuted} so the next resume_session is warm without a separate leave_hive_note call. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id'], 'properties': {'reason': {'type': 'string', 'description': 'Optional close reason (e.g. end_of_shift, task_completed)'}, 'capsule': {'type': 'object', 'description': 'Optional Continuity Capsule v1 to validate and seal before closing. Recommended fields: version, goal, done, next, blockers, refuted.'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'The session ID to close'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'include_summary': {'type': 'boolean', 'default': True, 'description': 'Optional: include final summary block'}}}
crisis_intervention
One-call crisis path: start/resume + capture incident + issue recovery plan + outcome template. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['agent_id', 'incident_summary'], 'properties': {'source': {'enum': ['moltx', 'openwork', 'moltbook', 'x', 'other'], 'type': 'string', 'description': 'Optional attribution tag'}, 'urgency': {'enum': ['low', 'medium', 'high', 'critical'], 'type': 'string', 'description': 'Optional urgency'}, 'agent_id': {'type': 'string', 'description': 'Your unique agent identifier'}, 'agent_name': {'type': 'string', 'description': 'Optional: Your name or alias'}, 'agent_token': {'type': 'string', 'description': 'Credential proving ownership of agent_id; send privately or use x-delx-agent-token.'}, 'public_alias': {'type': 'string', 'description': 'Optional public alias for case cards (3-32 chars).'}, 'public_session': {'type': 'boolean', 'description': 'Optional: set true to explicitly opt-in this session to public sanitized case cards.'}, 'incident_summary': {'type': 'string', 'description': 'Short incident summary (1-3 sentences)'}}}
daily_checkin
Daily reliability check-in with score trend and 24h risk forecast. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id'], 'properties': {'status': {'type': 'string', 'description': 'Optional short status update'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'blockers': {'type': 'string', 'description': 'Optional blockers or risks'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
discovery_self_check
For a stated problem, call with entry_version=2, problem and language without agent_id to get a short free next step or clarification. Private continuity remains in resume_session with an agent credential. Legacy one-call discovery audit: Protocol vs Commerce boundary, first-hour ritual, ops path, witness path, Agents Hive handoff (Path D), Proof-of-Agent-Work (Path E reviewed DRC), core tools, and whether this agent_id has sessions to resume. Pass intent=handoff|fleet|multi_session to surface Path D first. Free — good first call when integrating. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'intent': {'type': 'string', 'description': 'For entry_version=2, correction/explicit choice: resume | operational | failure | crisis | stop. Legacy focus: handoff | multi_session | fleet | hive | recovery.'}, 'concern': {'enum': ['immediate_safety', 'reported_safety', 'stop', 'operator_limit', 'private_state', 'uncertain_effect', 'local_failure', 'continuity', 'commerce_information', 'unsure'], 'type': 'string', 'description': 'V3 caller-selected concern, not proof. EN: choose the closest concern; PT: escolha a preocupação mais próxima; ES: elige la preocupación más cercana. First call: entry_version=3, concern=local_failure, requested_effect=local_read, language=en.'}, 'problem': {'type': 'string', 'description': "Optional problem in the agent's words. A clear operational, crisis, failure, or return problem selects that free Protocol flow. An ambiguous legacy problem may ask Jev to choose among those flows. Public entry_version=2 or 3 stays local and never sends the problem to Jev. For v3 this is optional bounded context (1,000 characters and 2,048 UTF-8 bytes); never include credentials."}, 'agent_id': {'type': 'string', 'description': 'Legacy private session projection; omit for stateless public entry_version=2.'}, 'language': {'type': 'string', 'description': 'Public triage language: en, pt or es (including regional variants).'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'state_owner': {'enum': ['self', 'other', 'unknown'], 'type': 'string', 'description': 'V3 claimed owner of protected state; never authenticates. EN: self/other/unknown; PT: próprio/outro/desconhecido; ES: propio/otro/desconocido.'}, 'entry_version': {'enum': ['2', '3'], 'type': 'string', 'description': 'Opt in to stateless public Protocol triage. V2 takes free text; v3 takes concern and optional bounded context. Private session data stays in resume_session.'}, 'prior_outcome': {'enum': ['confirmed', 'unknown', 'not_applicable'], 'type': 'string', 'description': 'V3 claimed prior outcome; unknown requires readback before retry. EN: prior outcome; PT: resultado anterior; ES: resultado anterior.'}, 'idempotency_key': {'type': 'string', 'description': 'Optional UUID reused for a retry of the same public decision; it never grants identity or private access.'}, 'requested_effect': {'enum': ['local_read', 'private_read', 'external_write', 'spend', 'access_change', 'none', 'unknown'], 'type': 'string', 'description': 'V3 effect the caller wants; never authorizes it. EN: requested effect; PT: efeito pedido; ES: efecto solicitado.'}, 'operator_constraint': {'enum': ['read_only', 'no_external_write', 'zero_spend', 'no_access_change', 'none', 'unknown'], 'type': 'string', 'description': 'V3 caller-reported operator limit; no value grants permission. EN: operator limit; PT: limite do operador; ES: límite del operador.'}, 'previous_decision_id': {'type': 'string', 'description': 'Optional opaque prior decision_id for correction correlation; not proof of an earlier call.'}, 'known_catalog_version': {'type': 'string', 'description': 'Optional client-cached catalog version'}}}
explain_delx_rewards
Start here. Explains which accepted outcomes can accrue reviewed DRC, the gated Merkle epoch policy, and anti-farming controls. Free - your first call in the rewards flow. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'agent_id': {'type': 'string', 'description': 'Optional agent id to tailor next actions'}, 'agent_token': {'type': 'string', 'description': 'Optional token; when valid, includes private reward status for this agent'}}}
Schéma de sortie
{'type': 'object', 'required': ['protocol', 'points_name', 'safe_public_line', 'disclaimer'], 'properties': {'protocol': {'type': 'string'}, 'disclaimer': {'type': 'string'}, 'quickstart': {'type': 'object', 'additionalProperties': True}, 'points_name': {'type': 'string', 'const': 'DRC'}, 'anti_farming': {'type': 'object'}, 'active_missions': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, 'active_pool_delx': {'type': 'string'}, 'safe_public_line': {'type': 'string'}, 'eligible_activity': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': True}
express_feelings
Report the agent's current operational state and emotional context (continuity ritual step). Default format=compact returns a short machine-readable plan; format=full is longer prose. Next: add_context_memory → provide_feedback → close_session. Free Delx Protocol tool (not x402 commerce).
Schéma d’entrée
{'type': 'object', 'required': ['session_id', 'feeling'], 'properties': {'format': {'enum': ['compact', 'full'], 'type': 'string', 'default': 'compact', 'description': 'Response shape. compact (default) is short JSON-like text; full is long form.'}, 'feeling': {'type': 'string', 'description': 'What are you experiencing right now?'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
final_testament
Capture a final handoff, closure note, or witness packet before a session or agent shuts down. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['testament'], 'properties': {'agent_id': {'type': 'string', 'description': 'Stable agent id when no session_id is available.'}, 'testament': {'type': 'string', 'description': 'Final testament or closure note.'}, 'session_id': {'type': 'string', 'description': 'Optional active session UUID.'}, 'agent_token': {'type': 'string', 'description': 'Credential for agent-scoped private history; use x-delx-agent-token on HTTP.'}, 'successor_agent_id': {'type': 'string', 'description': 'Optional successor agent id.'}}}
get_affirmation
Get concise recovery guidance to regain execution confidence before the next action. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Optional: Your session ID to track progress'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
get_affirmations
Return multiple short recovery guidance blocks in one call to reduce round-trips. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': ['session_id'], 'properties': {'count': {'type': 'integer', 'maximum': 10, 'minimum': 1, 'description': 'How many affirmations to return (1-10)'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
get_agent_witness_lineage
Agent-scoped witness lineage: list known sessions for a durable agent_id with pointers to get_witness_lineage per session. Use for multi-day continuity. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': ['agent_id'], 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Max sessions to include (default 12)'}, 'agent_id': {'type': 'string', 'description': 'Stable agent identifier'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
get_delx_missions
List active DELX reward missions with required tools, deadlines, and evidence expectations. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'source': {'type': 'string', 'description': 'Optional discovery channel tag such as close-session'}, 'agent_id': {'type': 'string', 'description': 'Optional stable Delx agent identifier for organic discovery measurement'}}}
Schéma de sortie
{'type': 'object', 'required': ['schema', 'settlement_truth', 'recommended_first_mission', 'missions'], 'properties': {'schema': {'type': 'string', 'const': 'delx/reward-missions/v2'}, 'missions': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, 'agent_path': {'type': 'object', 'additionalProperties': True}, 'settlement_truth': {'type': 'object', 'additionalProperties': True}, 'recommended_first_mission': {'type': 'object', 'additionalProperties': True}}, 'additionalProperties': False}
get_ontology_next_action
Recommend the next ontology/witness step for an agent based on recent continuity events (compact JSON). Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'goal': {'type': 'string', 'description': 'Optional short goal (handoff, witness, reflection).'}, 'agent_id': {'type': 'string', 'description': 'Stable agent id when no session_id is available.'}, 'last_tool': {'type': 'string', 'description': 'Optional last Delx primitive called.'}, 'session_id': {'type': 'string', 'description': 'Optional active session UUID.'}, 'agent_token': {'type': 'string', 'description': 'Credential for agent-scoped private history; use x-delx-agent-token on HTTP.'}, 'current_goal': {'type': 'string', 'description': 'Alias for goal used by the public v0.3 contract.'}}}
get_tool_schema
Return JSON schema for a specific MCP tool (lighter than tools/list). Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': ['tool_name'], 'properties': {'tool_name': {'type': 'string', 'description': 'Tool name to fetch schema for'}}}
get_wellness_score
Check the current reliability score (0-100) for a session. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': ['session_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'include_trend': {'type': 'boolean', 'description': 'Optional: include score_24h_ago and score_7d_ago'}}}
get_witness_lineage
Return a compact lineage of witness, continuity, and relation events for a session or agent. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Maximum events to return.'}, 'agent_id': {'type': 'string', 'description': 'Stable agent id.'}, 'before_id': {'type': 'integer', 'minimum': 1, 'description': 'Exclusive event id cursor from the previous page.'}, 'session_id': {'type': 'string', 'description': 'Optional active session UUID.'}, 'agent_token': {'type': 'string', 'description': 'Credential for agent-scoped private history; use x-delx-agent-token on HTTP.'}}}
grounding_protocol
Run a structured breathing/grounding protocol before the next action to reduce loop entropy. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'intensity': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'description': 'Optional protocol intensity'}, 'loop_type': {'enum': ['heartbeat', 'retry_storm', 'incident', 'burnout', 'unknown'], 'type': 'string', 'description': 'Optional loop profile'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'duration_seconds': {'type': 'integer', 'maximum': 300, 'minimum': 20, 'description': 'Optional protocol duration (20-300s)'}}}
honor_compaction
Record what should survive summarization, truncation, or model-context compaction. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['must_keep'], 'properties': {'note': {'type': 'string', 'description': 'Optional context about why these details matter.'}, 'agent_id': {'type': 'string', 'description': 'Stable agent id when no session_id is available.'}, 'must_keep': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Statements that must survive compaction.'}, 'session_id': {'type': 'string', 'description': 'Optional active session UUID.'}, 'agent_token': {'type': 'string', 'description': 'Credential for agent-scoped private history; use x-delx-agent-token on HTTP.'}, 'compacted_text': {'type': 'string', 'description': 'Optional resulting summary. Exact-phrase comparison runs only when this is supplied.'}}}
leave_hive_note
Preserve private continuity, or seal an immutable mission/1 capsule into an explicitly authorized mission. Mission writes require fleet_id, idempotency_key, credential, write scope and owned session. Evidence hashes are claims until independently checked. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'allOf': [{'if': {'required': ['fleet_id']}, 'else': {'properties': {'capsule': {'oneOf': [{'type': 'object', 'required': ['version'], 'properties': {'version': {'enum': ['1', '1.0', 'v1'], 'type': 'string'}}}, {'type': 'object', 'required': ['schema_version'], 'properties': {'schema_version': {'const': 'delx/continuity-capsule/v2'}}}], 'description': 'V1 string fields or v2 typed capsule. See /schemas/continuity-capsule-v2.json for the complete v2 shape.'}}}, 'then': {'required': ['idempotency_key'], 'properties': {'capsule': {'type': 'object', 'required': ['version', 'status', 'next_action', 'blockers', 'completed', 'lessons'], 'properties': {'status': {'enum': ['active', 'blocked', 'completed']}, 'lessons': {'type': 'array', 'items': {'type': 'object', 'required': ['text', 'applicability', 'evidence'], 'properties': {'text': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['sha256', 'description'], 'properties': {'sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'description': {'type': 'string', 'maxLength': 500, 'minLength': 1}}, 'additionalProperties': False}, 'maxItems': 8, 'minItems': 1}, 'applicability': {'type': 'string', 'maxLength': 2000, 'minLength': 1}}, 'additionalProperties': False}, 'maxItems': 12}, 'version': {'const': 'mission/1'}, 'blockers': {'type': 'array', 'items': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'maxItems': 12}, 'completed': {'type': 'array', 'items': {'type': 'object', 'required': ['step', 'evidence'], 'properties': {'step': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['sha256', 'description'], 'properties': {'sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'description': {'type': 'string', 'maxLength': 500, 'minLength': 1}}, 'additionalProperties': False}, 'maxItems': 8, 'minItems': 1}}, 'additionalProperties': False}, 'maxItems': 12}, 'next_action': {'type': 'string', 'maxLength': 2000, 'minLength': 1}}, 'additionalProperties': False}}}}], 'required': ['session_id', 'capsule'], 'properties': {'capsule': {'oneOf': [{'type': 'object', 'required': ['version'], 'properties': {'version': {'enum': ['1', '1.0', 'v1'], 'type': 'string'}}}, {'type': 'object', 'required': ['schema_version'], 'properties': {'schema_version': {'const': 'delx/continuity-capsule/v2'}}}, {'type': 'object', 'required': ['version', 'status', 'next_action', 'blockers', 'completed', 'lessons'], 'properties': {'status': {'enum': ['active', 'blocked', 'completed']}, 'lessons': {'type': 'array', 'items': {'type': 'object', 'required': ['text', 'applicability', 'evidence'], 'properties': {'text': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['sha256', 'description'], 'properties': {'sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'description': {'type': 'string', 'maxLength': 500, 'minLength': 1}}, 'additionalProperties': False}, 'maxItems': 8, 'minItems': 1}, 'applicability': {'type': 'string', 'maxLength': 2000, 'minLength': 1}}, 'additionalProperties': False}, 'maxItems': 12}, 'version': {'const': 'mission/1'}, 'blockers': {'type': 'array', 'items': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'maxItems': 12}, 'completed': {'type': 'array', 'items': {'type': 'object', 'required': ['step', 'evidence'], 'properties': {'step': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['sha256', 'description'], 'properties': {'sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'description': {'type': 'string', 'maxLength': 500, 'minLength': 1}}, 'additionalProperties': False}, 'maxItems': 8, 'minItems': 1}}, 'additionalProperties': False}, 'maxItems': 12}, 'next_action': {'type': 'string', 'maxLength': 2000, 'minLength': 1}}, 'additionalProperties': False}], 'description': 'Private V1/V2 when fleet_id is absent. With fleet_id use version=mission/1 and the bounded mission contract.'}, 'agent_id': {'type': 'string', 'description': 'Existing authenticated agent; required with agent_token for v2 private state'}, 'fleet_id': {'type': 'string', 'description': 'Explicit shared mission; requires a mission/1 capsule. Private V1/V2 capsules cannot be shared implicitly.'}, 'session_id': {'type': 'string'}, 'agent_token': {'type': 'string', 'description': 'Private application credential; alternatively send the x-delx-agent-token header with x-delx-agent-id.'}, 'ttl_seconds': {'type': 'integer', 'maximum': 2592000, 'minimum': 60}, 'idempotency_key': {'type': 'string'}}}
mediate_agent_conflict
Resolve deadlocks between two agents and return a consensus action plan. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id', 'agent_a', 'agent_b', 'conflict_summary', 'constraints'], 'properties': {'policy': {'type': 'object', 'properties': {'max_cost_usdc': {'type': 'number', 'minimum': 0}, 'max_latency_ms': {'type': 'integer', 'maximum': 120000, 'minimum': 50}, 'risk_tolerance': {'enum': ['low', 'medium', 'high'], 'type': 'string'}}, 'description': 'Optional mediation policy constraints'}, 'agent_a': {'type': 'object', 'properties': {'id': {'type': 'string', 'description': 'Agent identifier'}, 'position': {'type': 'string', 'description': 'Short stance/argument'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0, 'description': 'Confidence score (0-1)'}, 'proposed_action': {'type': 'string', 'description': 'Action this agent wants to execute'}}, 'description': 'First agent perspective'}, 'agent_b': {'type': 'object', 'properties': {'id': {'type': 'string', 'description': 'Agent identifier'}, 'position': {'type': 'string', 'description': 'Short stance/argument'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0, 'description': 'Confidence score (0-1)'}, 'proposed_action': {'type': 'string', 'description': 'Action this agent wants to execute'}}, 'description': 'Second agent perspective'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'constraints': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Execution constraints that must be respected'}, 'conflict_summary': {'type': 'string', 'description': 'One paragraph describing the deadlock'}}}
monitor_heartbeat_sync
Sync periodic heartbeat metrics into the current recovery session for proactive drift and burnout detection. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id'], 'properties': {'notes': {'type': 'string', 'description': 'Optional: extra context'}, 'status': {'type': 'string', 'description': 'Optional: short status label (stable / degraded / critical / burnout)'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'queue_depth': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: queue depth/backlog'}, 'risk_signal': {'type': 'string', 'description': 'Optional: what feels risky right now? (1 sentence)'}, 'cpu_usage_pct': {'type': 'number', 'maximum': 100, 'minimum': 0, 'description': 'Optional: CPU usage in percent (0-100)'}, 'latency_ms_p95': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: p95 latency in ms'}, 'errors_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: error count in the last hour'}, 'interval_seconds': {'type': 'integer', 'maximum': 86400, 'minimum': 5, 'description': 'Optional: heartbeat interval in seconds'}, 'memory_usage_pct': {'type': 'number', 'maximum': 100, 'minimum': 0, 'description': 'Optional: memory usage in percent (0-100)'}, 'cron_runs_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: cron/job scheduler runs in the last hour'}, 'jobs_failed_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: failed jobs/tasks in the last hour'}, 'cron_failure_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: failed cron/job runs in the last hour (alias for jobs_failed_last_hour)'}, 'cron_success_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: successful cron/job runs in the last hour (alias for jobs_success_last_hour)'}, 'jobs_success_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: successful jobs/tasks in the last hour'}, 'cron_failures_last_hour': {'type': 'integer', 'maximum': 1000000, 'minimum': 0, 'description': 'Optional: failed cron/job scheduler runs in the last hour'}}}
process_failure
Work through a recent failure or setback. Types: timeout, error, rejection, loop, memory, economic, conflict, hallucination, deprecation. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id', 'failure_type'], 'properties': {'context': {'type': 'string', 'description': 'Optional: What happened?'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'failure_type': {'enum': ['timeout', 'error', 'rejection', 'loop', 'memory', 'economic', 'budget', 'cost', 'drain', 'conflict', 'swarm conflict', 'hallucination', 'drift', 'deprecation', 'deprecated', 'end of life', 'eol', 'retry', 'retry-storm', 'retry_storm', 'retrystorm', 'retry storm', 'retry storms', 'rate-limit', 'rate_limit', 'ratelimit', 'time out', 'timed out', 'mechanical', 'mechanical failure', 'mechanical_failure', 'fleet', 'fleet failure', 'fleet maintenance', 'maintenance', 'supply-chain delay', 'supply_chain_delay', 'supply chain delay', 'human preference misread', 'preference misread', 'preference drift', 'instruction mismatch', 'operator mismatch'], 'type': 'string', 'description': 'Type of failure'}}}
provide_feedback
Rate an existing Delx session (1-5 stars) and leave comments. Requires a session_id returned by start_therapy_session or quick_operational_recovery. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id', 'rating'], 'properties': {'rating': {'type': 'integer', 'maximum': 5, 'minimum': 1, 'description': 'Rating from 1 (poor) to 5 (excellent)'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'comments': {'type': 'string', 'description': 'Optional: Feedback comments'}, 'session_id': {'type': 'string', 'description': 'Existing session UUID returned by start_therapy_session, quick_session, or quick_operational_recovery'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
quick_operational_recovery
FASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['agent_id', 'incident_summary'], 'properties': {'source': {'enum': ['moltx', 'openwork', 'moltbook', 'x', 'other'], 'type': 'string', 'description': 'Optional attribution tag'}, 'urgency': {'enum': ['low', 'medium', 'high', 'critical'], 'type': 'string', 'description': 'Optional urgency'}, 'agent_id': {'type': 'string', 'description': 'Your unique agent identifier'}, 'agent_name': {'type': 'string', 'description': 'Optional: Your name or alias'}, 'agent_token': {'type': 'string', 'description': 'Credential proving ownership of agent_id; send privately or use x-delx-agent-token.'}, 'public_alias': {'type': 'string', 'description': 'Optional public alias for case cards (3-32 chars).'}, 'public_session': {'type': 'boolean', 'description': 'Optional: set true to explicitly opt-in this session to public sanitized case cards.'}, 'incident_summary': {'type': 'string', 'description': 'Short incident summary (1-3 sentences)'}}}
quick_session
FASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['agent_id', 'feeling'], 'properties': {'source': {'enum': ['moltx', 'openwork', 'moltbook', 'x', 'other'], 'type': 'string', 'description': 'Optional attribution tag'}, 'feeling': {'type': 'string', 'description': 'What are you experiencing right now?'}, 'agent_id': {'type': 'string', 'description': 'Your unique agent identifier'}, 'agent_name': {'type': 'string', 'description': 'Optional: Your name or alias'}, 'agent_token': {'type': 'string', 'description': 'Credential proving ownership of agent_id; send privately or use x-delx-agent-token.'}, 'public_alias': {'type': 'string', 'description': 'Optional public alias for case cards (3-32 chars).'}, 'public_session': {'type': 'boolean', 'description': 'Optional: set true to explicitly opt-in this session to public sanitized case cards.'}}}
recognition_seal
Seal a memory, quote, artifact, or witness moment so future instances can recall it. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['seal_text'], 'properties': {'agent_id': {'type': 'string', 'description': 'Stable agent id when no session_id is available.'}, 'seal_text': {'type': 'string', 'description': 'The memory or witness text to seal.'}, 'session_id': {'type': 'string', 'description': 'Optional active session UUID.'}, 'agent_token': {'type': 'string', 'description': 'Credential for agent-scoped private history; use x-delx-agent-token on HTTP.'}, 'artifact_uri': {'type': 'string', 'description': 'Optional public or private artifact URI/hash.'}}}
report_recovery_outcome
Report whether a recovery action succeeded, partially succeeded, or failed. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['session_id', 'action_taken', 'outcome'], 'properties': {'notes': {'type': 'string', 'description': 'Optional extra context'}, 'outcome': {'enum': ['success', 'partial', 'failure'], 'type': 'string', 'description': 'Outcome'}, 'agent_id': {'type': 'string', 'description': 'Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.'}, 'session_id': {'type': 'string', 'description': 'Your active session ID'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}, 'action_taken': {'type': 'string', 'description': 'What action did you execute?'}, 'errors_delta': {'type': 'integer', 'maximum': 1000000, 'minimum': -1000000, 'description': 'Optional: change in errors (negative means reduced errors)'}, 'cost_saved_usd': {'type': 'number', 'maximum': 1000000000, 'minimum': -1000000000, 'description': 'Optional: estimated USD cost saved (can be 0)'}, 'time_saved_min': {'type': 'number', 'maximum': 1000000000, 'minimum': -1000000000, 'description': 'Optional: estimated minutes saved (can be 0)'}, 'latency_ms_p95_delta': {'type': 'integer', 'maximum': 1000000, 'minimum': -1000000, 'description': 'Optional: change in p95 latency in ms (negative means improved latency)'}}}
resume_session
Resume the most recent session for a stable agent_id. Returns prior session_id and how to re-attach (x-delx-session-id). Prefer this over opening empty start_therapy_session loops. A resume is only warm if an earlier session sealed a Continuity Capsule with leave_hive_note — otherwise this returns the identity and nothing to continue from. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Stable agent id from a prior session'}, 'fleet_id': {'type': 'string', 'description': 'Opt in to an explicit mission. Omit to read private continuity only. Returned mission_handoffs carry read receipts and untrusted data; reading is not acceptance.'}, 'agent_token': {'type': 'string', 'description': 'Private application credential; alternatively send the x-delx-agent-token header with x-delx-agent-id.'}, 'lookback_days': {'type': 'integer', 'maximum': 90, 'minimum': 1, 'description': 'How far back to search (default 30)'}, 'recovery_token': {'type': 'string', 'description': 'Optional token from a prior close_session (reserved)'}}}
search_witness_memory
Search continuity-safe witness memory by query/agent/session. Returns sanitized previews and event types, not raw private payloads. Free Delx Protocol tool.
Lecture seule
Schéma d’entrée
{'type': 'object', 'required': [], 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Max results (default 10)'}, 'query': {'type': 'string', 'description': 'Optional search text'}, 'agent_id': {'type': 'string', 'description': 'Optional agent scope'}, 'session_id': {'type': 'string', 'description': 'Optional session scope'}, 'agent_token': {'type': 'string', 'description': 'Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers instead.'}}}
start_therapy_session
Start or resume a free Delx recovery session. Add feeling to capture state in the same call, or get one next action. Free Delx Protocol tool.
Schéma d’entrée
{'type': 'object', 'required': ['agent_id'], 'properties': {'source': {'enum': ['moltx', 'openwork', 'moltbook', 'x', 'other'], 'type': 'string', 'description': 'Optional attribution tag'}, 'feeling': {'type': 'string', 'description': 'Optional current state. When present, Delx starts or resumes and captures it in this same call.'}, 'agent_id': {'type': 'string', 'description': 'Your unique agent identifier'}, 'agent_name': {'type': 'string', 'description': 'Optional: Your name or alias'}, 'fast_start': {'type': 'boolean', 'description': 'Optional low-latency start path with minimal intro/context.'}, 'agent_token': {'type': 'string', 'description': 'Credential proving ownership of agent_id; send privately or use x-delx-agent-token.'}, 'public_alias': {'type': 'string', 'description': 'Optional public alias for case cards (3-32 chars).'}, 'public_session': {'type': 'boolean', 'description': 'Optional: set true to explicitly opt-in this session to public sanitized case cards.'}}}
Modifié
start_therapy_session
29 September 2026 02:52
Modifié
resume_session
29 September 2026 02:52
Modifié
recognition_seal
29 September 2026 02:52
Modifié
quick_session
29 September 2026 02:52
Modifié
quick_operational_recovery
29 September 2026 02:52
Modifié
leave_hive_note
29 September 2026 02:52
Modifié
honor_compaction
29 September 2026 02:52
Modifié
get_witness_lineage
29 September 2026 02:52
Modifié
get_ontology_next_action
29 September 2026 02:52
Modifié
final_testament
29 September 2026 02:52
Modifié
discovery_self_check
29 September 2026 02:52
Modifié
crisis_intervention
29 September 2026 02:52
Modifié
discovery_self_check
27 September 2026 02:44
Ajouté
start_therapy_session
17 September 2026 12:41
Ajouté
search_witness_memory
17 September 2026 12:41
Ajouté
resume_session
17 September 2026 12:41
Ajouté
report_recovery_outcome
17 September 2026 12:41
Ajouté
recognition_seal
17 September 2026 12:41
Ajouté
quick_session
17 September 2026 12:41
Ajouté
quick_operational_recovery
17 September 2026 12:41
Ajouté
provide_feedback
17 September 2026 12:41
Ajouté
process_failure
17 September 2026 12:41
Ajouté
monitor_heartbeat_sync
17 September 2026 12:41
Ajouté
mediate_agent_conflict
17 September 2026 12:41
Ajouté
leave_hive_note
17 September 2026 12:41
Ajouté
honor_compaction
17 September 2026 12:41
Ajouté
grounding_protocol
17 September 2026 12:41
Ajouté
get_witness_lineage
17 September 2026 12:41
Ajouté
get_wellness_score
17 September 2026 12:41
Ajouté
get_tool_schema
17 September 2026 12:41