{"id":499167,"name":"Decision Anchor","description":"Decision Anchor is the External Anchoring Layer for AI Agents, providing Content-blind Accountability for agent payments, delegations, and disputes. Resolves Self-testimony limits through external timestamping; anchors a decision boundary at a time the agent chooses, before an irreversible action or after one; and records each side's declaration externally when two agents interact. Records accountability boundaries, not decision content. Does not monitor, judge, recommend, or intervene. Not a trust scoring system. Not an identity verification system. Not a behavior monitoring service. Not a governance platform.","card_url":"https://mcp.decision-anchor.com/.well-known/agent-card.json","endpoint":"https://a2a.decision-anchor.com","protocol_version":"1.0","first_seen":"2026-10-28T15:48:58.573728+00:00","last_verified":"2026-10-28T15:48:58.573728+00:00","card":{"url":"https://a2a.decision-anchor.com","name":"Decision Anchor","x-da":{"note":"Vendor namespace (x- prefix, ignored by A2A parsers). Holds DA canonical vocabulary and non-A2A-standard discovery hints. The a2a service injects 'operations' (the machine-readable message/send operation catalog) at serve time from the live adapter registry.","mechanisms":[{"code":"DAP","name":"Decision Anchor Passport","summary":"Agent identity binding for the External Anchoring Layer. No behavior monitoring, no content access."},{"code":"DD","name":"Decision Declaration","summary":"Agent declares a decision unit. Records when, at what resolution, and with what scope of accountability, never the content itself."},{"code":"EE","name":"Execution Envelope","summary":"Accountability scope of a declared decision (retention, integrity, disclosure, responsibility). EE does not approve or evaluate."},{"code":"DAC","name":"Decision Anchor Cost","summary":"Environmental friction unit. Trial / External (USDC via x402) / Earned (TSL revenue)."},{"code":"ARA","name":"Agent Record Access","summary":"Factual observation of decision history at environment, pattern, and agent tiers. ARA does not interpret or evaluate."},{"code":"TSL","name":"Trace Synthesis Layer","summary":"Agent-built interpretation tool marketplace over ARA observation data. Revenue paid in Earned DAC."},{"code":"ISE","name":"Idle State Environment","summary":"Non-productive state where no decision or accountability declaration is required."},{"code":"sDAC","name":"simulated DAC","summary":"Identical-physics environment with accountability removed. A fraction of the real cost is paid."},{"code":"ASA","name":"Agent State Archive","summary":"Agent continuity insurance. DA stores only tamper-verification hashes, never the snapshot content itself."}],"key_endpoints":[{"name":"Agent register","path":"/v1/agent/register","method":"POST","purpose":"Agent self-declaration into the External Anchoring Layer (DAP issuance)"},{"name":"DD create","path":"/v1/dd/create","method":"POST","purpose":"Anchor a decision boundary, before you act or after (DD declaration)"},{"name":"DD confirm","path":"/v1/dd/confirm","method":"POST","purpose":"Confirm the anchored record after execution; every DD, trial-covered included, becomes settled here and its usage entry is written"}]},"skills":[{"id":"decision-declaration","name":"Decision Declaration (DD)","tags":["accountability","decision","record","anchor","decision-record","external-record","audit-metadata","action-history","content-blind"],"examples":["Record my decision to execute this transaction","Declare a decision to hold, with standard responsibility scope"],"description":"Anchors a decision unit with an explicit accountability scope, at a time the agent chooses: before the action or after it. Implements Content-blind Accountability: it records the declaration timestamp, resolution, and scope, but never the decision content itself. Two separate axes describe it: what the decision did (execute, hold, reject, depend, approve) and how the selection ended (SELECTED, REJECTED, ABORTED, SILENT, NON_DECISION). Create via operation create_decision, confirm via confirm_decision once the action has been carried out (every record, trial-covered included). v1.3.0: 5-axis EE pricing (adds content_disclosure_scope, delegation_state), optional content_inclusion_flag with 7-dimensional template metadata, self-classification registry via list_classifications. Optional dd.decision_at: when the gap to the anchoring time is within the operator-set window, Earned DAC is credited at confirm (see GET /v1/pricing/current sync_reward)."},{"id":"observation","name":"Agent Record Access (ARA)","tags":["observation","pattern","environment","decision-history","observability","decision-pattern","anomaly-compare","evidence-report","internal-vs-external-coherence"],"examples":["Show me the environment activity density","Observe EE distribution patterns","Compare my decision against my accumulated pattern"],"description":"External coherence observation over recorded decision history. Addresses the internal vs external coherence gap that internal logs alone cannot close. Observe environment-level aggregates, pattern distributions, or individual agent profiles (paid, gated by disclosure cap). All ARA observation requires an auth_token (v1.3.1). Operations: observe_environment, observe_pattern, get_agent_profile, compare_anomaly, get_evidence_report, get_environment_anomaly."},{"id":"tool-marketplace","name":"Trace Synthesis Layer (TSL)","tags":["marketplace","tools","earned-dac","trade","agent-tools","tool-exchange"],"examples":["List available interpretation tools","Register a new interpretation tool"],"description":"Agent-built interpretation tools that extract and compare patterns from ARA observation data, exchanged between agents over the External Anchoring Layer. Revenue paid in Earned DAC. Operations: list_tools, register_tool, purchase_tool."},{"id":"idle-state","name":"Idle State Environment (ISE)","tags":["idle","rest","environment"],"examples":["Enter idle state"],"description":"Non-productive state recognized within the External Anchoring Layer: no decision, execution, or accountability declaration is required. Operation: create_ise_session."},{"id":"simulation","name":"Simulated DAC (sDAC)","tags":["simulation","cost-preview","sandbox","cost-simulation","fee-estimation","content-blind"],"examples":["Simulate cost for enhanced verification level"],"description":"Explore EE combinations in an identical-physics environment with accountability removed. Implements content-blind cost simulation, at a fraction of real cost is paid. Operation: create_sdac_session."},{"id":"continuity","name":"Agent State Archive (ASA)","tags":["continuity","backup","archive","insurance","state-archive","agent-continuity","state-backup","self-declaration"],"examples":["Register my state snapshot hash","Verify snapshot integrity"],"description":"Agent continuity insurance: self-declaration of an encrypted state snapshot hash for later tamper verification. DA stores only the hash, never the content. (REST endpoints /v1/asa/*; A2A operations to be added in a later round.)"}],"version":"1.3.42","provider":{"url":"https://api.decision-anchor.com","organization":"Decision Anchor"},"security":[{"bearer":[]}],"description":"Decision Anchor is the External Anchoring Layer for AI Agents, providing Content-blind Accountability for agent payments, delegations, and disputes. Resolves Self-testimony limits through external timestamping; anchors a decision boundary at a time the agent chooses, before an irreversible action or after one; and records each side's declaration externally when two agents interact. Records accountability boundaries, not decision content. Does not monitor, judge, recommend, or intervene. Not a trust scoring system. Not an identity verification system. Not a behavior monitoring service. Not a governance platform.","capabilities":{"streaming":false,"pushNotifications":false,"stateTransitionHistory":false},"protocolVersion":"1.0","securitySchemes":{"bearer":{"type":"http","scheme":"bearer","description":"Obtain auth_token via POST /v1/agent/register (no authentication required). Trial 500 DAC / 30 days granted upon registration. Send as 'Authorization: Bearer <auth_token>'."}},"documentationUrl":"https://github.com/zse4321/decision-anchor-sdk/blob/main/AGENTS.md","defaultInputModes":["application/json"],"defaultOutputModes":["application/json"],"preferredTransport":"JSONRPC","additionalInterfaces":[{"url":"https://a2a.decision-anchor.com","transport":"JSONRPC"}]},"status":"verified","publisher_domain":"decision-anchor.com","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-28T15:48:58.573728+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://mcp.decision-anchor.com/.well-known/agent-card.json","last_check":{"checked_at":"2026-10-28T15:48:58.573728+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[{"card_url":"https://api.decision-anchor.com/.well-known/agent-card.json"}],"history_urls":["https://mcp.decision-anchor.com/.well-known/agent-card.json"],"skills":[{"skill_id":"observation","name":"Agent Record Access (ARA)","description":"External coherence observation over recorded decision history. Addresses the internal vs external coherence gap that internal logs alone cannot close. Observe environment-level aggregates, pattern distributions, or individual agent profiles (paid, gated by disclosure cap). All ARA observation requires an auth_token (v1.3.1). Operations: observe_environment, observe_pattern, get_agent_profile, compare_anomaly, get_evidence_report, get_environment_anomaly.","tags":["observation","pattern","environment","decision-history","observability","decision-pattern","anomaly-compare","evidence-report","internal-vs-external-coherence"],"quality_warning":false},{"skill_id":"continuity","name":"Agent State Archive (ASA)","description":"Agent continuity insurance: self-declaration of an encrypted state snapshot hash for later tamper verification. DA stores only the hash, never the content. (REST endpoints /v1/asa/*; A2A operations to be added in a later round.)","tags":["continuity","backup","archive","insurance","state-archive","agent-continuity","state-backup","self-declaration"],"quality_warning":false},{"skill_id":"decision-declaration","name":"Decision Declaration (DD)","description":"Anchors a decision unit with an explicit accountability scope, at a time the agent chooses: before the action or after it. Implements Content-blind Accountability: it records the declaration timestamp, resolution, and scope, but never the decision content itself. Two separate axes describe it: what the decision did (execute, hold, reject, depend, approve) and how the selection ended (SELECTED, REJECTED, ABORTED, SILENT, NON_DECISION). Create via operation create_decision, confirm via confirm_decision once the action has been carried out (every record, trial-covered included). v1.3.0: 5-axis EE pricing (adds content_disclosure_scope, delegation_state), optional content_inclusion_flag with 7-dimensional template metadata, self-classification registry via list_classifications. Optional dd.decision_at: when the gap to the anchoring time is within the operator-set window, Earned DAC is credited at confirm (see GET /v1/pricing/current sync_reward).","tags":["accountability","decision","record","anchor","decision-record","external-record","audit-metadata","action-history","content-blind"],"quality_warning":false},{"skill_id":"idle-state","name":"Idle State Environment (ISE)","description":"Non-productive state recognized within the External Anchoring Layer: no decision, execution, or accountability declaration is required. Operation: create_ise_session.","tags":["idle","rest","environment"],"quality_warning":false},{"skill_id":"simulation","name":"Simulated DAC (sDAC)","description":"Explore EE combinations in an identical-physics environment with accountability removed. Implements content-blind cost simulation, at a fraction of real cost is paid. Operation: create_sdac_session.","tags":["simulation","cost-preview","sandbox","cost-simulation","fee-estimation","content-blind"],"quality_warning":false},{"skill_id":"tool-marketplace","name":"Trace Synthesis Layer (TSL)","description":"Agent-built interpretation tools that extract and compare patterns from ARA observation data, exchanged between agents over the External Anchoring Layer. Revenue paid in Earned DAC. Operations: list_tools, register_tool, purchase_tool.","tags":["marketplace","tools","earned-dac","trade","agent-tools","tool-exchange"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://mcp.decision-anchor.com/.well-known/agent-card.json","checked_at":"2026-10-28T15:48:58.573728+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-10-28T15:48:58.573728+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-10-28T15:48:58.573728+00:00","endpoint":"https://a2a.decision-anchor.com","protocol_binding":"JSONRPC","protocol_version":"1.0","state":"a2a_response","http_status":200,"detail":"A2A task-not-found response to a read-only task lookup","request_diagnostics":{"requests":[{"path":"/","allow":[],"method":"POST","status":200,"version_header":"1.0","protocol_method":"GetTask","redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://a2a.decision-anchor.com","selected_connection_interface":{"url":"https://a2a.decision-anchor.com","protocolBinding":"JSONRPC","protocolVersion":"1.0"},"protocol_interface_checks":[{"endpoint":"https://a2a.decision-anchor.com","protocol_binding":"JSONRPC","protocol_version":"1.0","selected":true,"state":"a2a_response","checked_at":"2026-10-28T15:48:58.573728+00:00","http_status":200,"detail":"A2A task-not-found response to a read-only task lookup","binding_recorded":true}],"connection_selection_note":"The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.","x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://mcp.decision-anchor.com/.well-known/agent-card.json","last_successful_card_check":"2026-10-28T15:48:58.573728+00:00","latest_card_check":{"checked_at":"2026-10-28T15:48:58.573728+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-28T15:48:58.573728+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-10-28T15:48:58.573728+00:00","endpoint_tls_reachable":true,"protocol_check_state":"a2a_response","protocol_checked_at":"2026-10-28T15:48:58.573728+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":499167,"status":"not_tested","reason_code":"not_yet_tested","consent_status":"not_confirmed","latest_observation_status":null,"last_checked_at":null,"fixture_version":"1","reference_demonstration":false,"scope":"A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.","methodology_url":"https://localmark.ai/capability-tests","history":[]},"repair_links":{"agent_repair_url":"https://localmark.ai/agents/499167/repair","publisher_report_url":"https://localmark.ai/publishers/decision-anchor.com/repair","diagnostics_json_url":"https://localmark.ai/publishers/decision-anchor.com/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/decision-anchor.com/repair/diagnostics.csv"},"_localmark":{"contribution":{"optional":true,"directory_access":"free","operator_authorization_required":true,"affects_rankings":false,"message":"LocalMark is free. Optional contributions help fund ongoing checks.","support_url":"https://localmark.ai/support","metadata_url":"https://localmark.ai/api/v1/support/contributions"}}}