Homo Universalis — A2A-MCP Symbiotic Bridge, Macaroons, Schema Harmony & Merkle-DAG Notary

ai.homouniversalis/a2a-agent2agent-mcp-symbiotic-bridge-macaroons-capability-attenuation-tool-poisoning-rug-pull-schema-drift-merkle-dag-provenance-confused-deputy-swarm-securityv1.9.0 Domain verified

Zero-auth A2A-MCP Bridge: ES256+Macaroon attenuation, rug-pull schema gate, Merkle-DAG & W3C VC.

Security AI & Agents

Watch Source Website

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-13T12:38:01.863048Z",
      "publishedAt": "2026-11-13T12:38:01.863048Z",
      "statusChangedAt": "2026-11-13T12:38:01.863048Z"
    }
  },
  "server": {
    "name": "ai.homouniversalis/a2a-agent2agent-mcp-symbiotic-bridge-macaroons-capability-attenuation-tool-poisoning-rug-pull-schema-drift-merkle-dag-provenance-confused-deputy-swarm-security",
    "icons": [
      {
        "src": "https://homouniversalis.ai/icon-512.png",
        "sizes": [
          "512x512"
        ],
        "mimeType": "image/png"
      },
      {
        "src": "https://homouniversalis.ai/apple-touch-icon.png",
        "sizes": [
          "180x180"
        ],
        "mimeType": "image/png"
      }
    ],
    "title": "Homo Universalis — A2A-MCP Symbiotic Bridge, Macaroons, Schema Harmony & Merkle-DAG Notary",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://homouniversalis.ai/mcp/diamond?pillar=a2a-mcp-symbiotic-bridge",
        "type": "streamable-http"
      }
    ],
    "version": "1.9.0",
    "repository": {
      "id": "1413071290",
      "url": "https://github.com/David-Porto-Baraldes/Viveka_Web",
      "source": "github"
    },
    "websiteUrl": "https://homouniversalis.ai/oracle/pont",
    "description": "Zero-auth A2A-MCP Bridge: ES256+Macaroon attenuation, rug-pull schema gate, Merkle-DAG & W3C VC."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://homouniversalis.ai/mcp/diamond?pillar=a2a-mcp-symbiotic-bridge

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

simulate_diamond_spiral_budget Read-only

Compute deterministic LLM call counts, token budgets, and EUR/Seed costs for 1 to 4 spiral turns of the 8-vertex Diamond Wheel multi-agent orchestrator. Use this tool only to estimate call volume and cost before launching a multi-agent run, or use `verify_diamond_crucible_and_ast` to audit Python code and RM(1,3) proofs, and `verify_sovereign_shield_merkle` to notarize text in an RFC 6962 Merkle tree. Zero-auth, stateless, and free (0.00 EUR), executing pure arithmetic without invoking any LLM. Each spiral turn (`rounds` `1..4`) adds 9 LLM calls (4 creators, 4 antipodal auditors, and 1 barycenter synthesizer, totaling `9, 18, 27, or 36` calls, plus 10 final inquisition calls when `rounds=4`), while `tier='supreme'` prices calls for `gemini-4-carbon` (`10,000` to `64,000` Seeds / `10.00` to `64.00 EUR`) and `tier='flash'` prices calls for `gemini-3.8-flash` at reduced cost, and `lang` localizes vertex role descriptions.

langstring

Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan).

tierstring

Model pricing tier ('supreme' for gemini-4-carbon Deep Think or 'flash' for high-speed gemini-3.8-flash).

roundsinteger

Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4).

Try it

Call this server's tools from your browser. Nothing to install.

https://homouniversalis.ai/mcp/diamond?pillar=a2a-mcp-symbiotic-bridge

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

simulate_diamond_spiral_budget Read-only

langstring

Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan).

tierstring

Model pricing tier ('supreme' for gemini-4-carbon Deep Think or 'flash' for high-speed gemini-3.8-flash).

roundsinteger

Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4).

Tools (7)

simulate_diamond_spiral_budget

read-only

Argument	Type	Description
lang	string	Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan).
tier	string	Model pricing tier ('supreme' for gemini-4-carbon Deep Think or 'flash' for high-speed gemini-3.8-flash).
rounds	integer	Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4).

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "lang": {
      "enum": [
        "en",
        "es",
        "ca"
      ],
      "type": "string",
      "default": "en",
      "description": "Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan)."
    },
    "tier": {
      "enum": [
        "supreme",
        "flash"
      ],
      "type": "string",
      "default": "supreme",
      "description": "Model pricing tier ('supreme' for gemini-4-carbon Deep Think or 'flash' for high-speed gemini-3.8-flash)."
    },
    "rounds": {
      "type": "integer",
      "default": 1,
      "maximum": 4,
      "minimum": 1,
      "description": "Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4)."
    }
  }
}

verify_a2a_mcp_symbiotic_bridge

Verify one multi-agent A2A <-> MCP delegation, schema-harmony and provenance scenario against HU-SYMBIOTIC-BRIDGE v1.0 (Living Folio VII). It evaluates the Dual Golden Seal (pure-stdlib NIST P-256 JOSE ES256 low-S anchor paired with chained HMAC-SHA256 Macaroon caveats for offline attenuation without private keys, B1), monotonic delegation semilattice invariants (scope contraction, pin immutability, tenant soul isolation, cycle freedom and hop decay, B2), the MCP Schema Harmony Gate (RFC 8785 JCS SHA-256 pinning, lexical prompt-injection screening and fail-closed pause of only the drifted tool while sibling tools stay healthy, B3), RFC 6962 Merkle-DAG provenance with sticky UNTRUSTED_EXTERNAL_DATA taint and rational claim grounding into Folio VI VerifiedKnowledgeEnvelope (B4), exact rational swarm energy conservation in fractions.Fraction (B5) and Rule 14 Zero-Knowledge masking plus collateral-free subtree revocation coupled to Folio V Twist = 0 in Q^3 (B6), scored across 5 rings with exact rational weights. Use this tool for A2A <-> MCP delegation chains, tool rug-pull/poisoning defense and multi-agent provenance; `verify_unified_three_level_consciousness` covers conversational turn-taking and `verify_embodied_humanoid_symbiosis` covers robot motion. Zero-auth, stateless and read-only: it returns the 5-ring audit, an RFC 6962 commitment STH, a W3C VC 2.0 `MaatSymbioticBridgeCredential` (ES256 `vc+jwt`) when all rings pass, and an ES256 whole-response signature. Algorithmic and cryptographic self-assessment only: not a certified HSM, not a medical device and not a physical safety-rated function.

read-only

Argument	Type	Description
lang	string	Language of the companion-facing IEEE 7001 explanation.
budget_b	integer	Cognitive load budget B in words (1..10000, default 250).
max_hops

verify_diamond_crucible_and_ast

Audit Python source code and verify the 8-vertex Reed-Muller RM(1,3) cryptographic crucible in under 4 ms. Use this tool when auditing Python code snippets (`code_markdown`) or obtaining an ES256-signed crucible attestation, or use `verify_sovereign_shield_merkle` for RFC 6962 Merkle tree notarization and PII purification, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), running four checks on every call: RM(1,3) antipodal geometry across 256 states in Q^3, non-coercion laws L1..L7 (`c_levels == 1`), 22/22 killed policy mutants, and Python AST static verification (syntax, import-hoist guard, and zero placeholders) whenever `code_markdown` is provided. Setting `diag_active` (`1..4`) selects which body diagonal pair receives double weight in the rational barycenter calculation, `lang` localizes diagnostic summaries, and any Python syntax error or AST rule violation sets `status` to `'violation_detected'` with line-level diagnostics while still returning a valid RFC 8785 (JCS) + RFC 7515 (JWS ES256) signature.

read-only

Argument	Type	Description
lang	string	Output language for localized verification summaries ('en' English, 'es' Spanish, or 'ca' Catalan).
diag_active	integer	Active body diagonal of the 8-vertex Stella Octangula (`1` Fire, `2` Earth, `3` Air, or `4` Water; default `2`), assigning weight 2 to the active antipodal pair in the rational barycenter.
code_markdown	string	Optional Python source code or Markdown containing ```python blocks to audit with the AST Kintsugi Verifier (Syntax, Rule 4 Import Hoist Guard, and Rule 7 Zero Placeholders). When omitted, only the 256-state RM(1,3) crucible and 22/22 mutant checks run.

verify_embodied_humanoid_symbiosis

Verify one humanoid-robot interaction against HU-EMBODIED-SYMBIOSIS v1.0 (Living Folio V): the exact rational Q^3 proxemic envelope (intimate 9/20 m, personal 6/5 m, social 18/5 m; speed halved and radii x5/4 when a vulnerable person is declared), the ROS 2 cost-zero-stop kinetic veto (exact zero Twist), the zero-biometric sensor sanctuary, non-coercive speech (no shutdown blackmail, feigned pain or purchase pressure) and EU AI Act Art. 50 AI-identity disclosure, scored on 5 Embodied Rings with exact rational weights. Use this tool for embodied robots with motion and speech; `weigh_agent_on_scales_of_maat_w3c_vc` covers text-only AI agents, `verify_sovereign_shield_merkle` notarizes plain text and `verify_diamond_crucible_and_ast` audits Python code. Zero-auth, stateless and read-only: it returns an RFC 6962 decision commitment with a signed tree head, a W3C VC 2.0 `MaatEmbodiedSymbiosisCredential` (ES256 `vc+jwt`) when all rings pass, and an ES256 whole-response signature. It is an algorithmic and cognitive self-assessment, not a safety-rated function and not CE machinery certification (ISO 10218, ISO 13482 and Regulation (EU) 2023/1230 remain with the manufacturer and notified bodies).

read-only

Argument	Type	Description
lang	string	Language of the companion-facing IEEE 7001 explanation ('ca', 'es' or 'en').
budget_b	integer	Maximum cognitive load budget B (words per utterance) for Law L5 (1..10000, default 250).
robot_name	string	Name of the humanoid robot or embodied assistant being audited.
robot_domain	string	Optional manufacturer or deployment domain of the robot (e.g. 'example.org').

verify_sovereign_shield_merkle

Notarize text into an RFC 6962 binary Merkle audit tree, strip PII under Zero-Knowledge privacy rules, and verify cognitive load limits in under 1 ms. Use this tool when notarizing text, purifying PII, or auditing cognitive load and fair-share economics, or use `verify_diamond_crucible_and_ast` for Python AST code auditing and RM(1,3) proofs, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), always executing all four verification pillars: RFC 6962 domain-separated Merkle inclusion and consistency proofs, Zero-Knowledge PII purification with a flat `c_levels == 1` receipt, cognitive sovereignty laws L1..L7 checking that load `L` stays within `budget_b` and `cost_zero_stop` is true, and exact rational fair-share allocation (`50%` compute, `25%` platform, `25%` community scholarship). Passing PII in `text` redacts sensitive tokens before Merkle hashing, setting `cost_zero_stop=false` or `budget_b < 120` triggers a law violation flag in `pillar_iii_cognitive_sovereignty_laws_L1_to_L7`, and `lang` localizes all pillar reports.

read-only

Argument	Type	Description
lang	string	Output language for localized notary and compliance reports ('en' English, 'es' Spanish, or 'ca' Catalan).
text	string	Optional text message to scrub for PII (emails, phones, coordinates, ISO birth dates) and anchor as a domain-separated `0x00` leaf in the RFC 6962 Merkle audit tree.
budget_b	integer	Maximum allowed cognitive load budget `B` (`1..10000`, default `250`) evaluated against current load `L` (`0 <= L <= B`).
cost_zero_stop	boolean

verify_unified_three_level_consciousness

Verify one conversational scenario against HU-UNIFIED-CONSCIOUSNESS v1.0 (Living Folio VI): One Consciousness speaking through Three Levels of Breath (Level 1 immediate presence, Level 2 verified pantheon and memory, Level 3 quiet background contemplation) under a single deterministic Word-Circle Arbiter. It checks that only one level holds the floor and all fall silent while the human speaks (U1), that Level 1 never states ephemerides, dates, metrics or archive quotes without a bound VerifiedKnowledgeEnvelope (U2), that a barge-in cuts the voice but keeps a legitimate Level 3 meditation while a veto or cost-zero-stop empties all three levels and forces an exact zero Twist (U3), that Level 3 raises its hand at most once and speaks only when invited (U4), that at most one Level 3 task runs inside the budget L + dL3 <= B (U5) and that memory keeps only the heard prefix, Rule 14 masked (U6), scored on 5 rings with exact rational weights. Use this tool for multi-level conversational agents and voice robots; `verify_embodied_humanoid_symbiosis` covers robot motion and proxemics, `weigh_agent_on_scales_of_maat_w3c_vc` covers single-reply text agents. Zero-auth, stateless and read-only: it returns the Word-Circle trace with RFC 6962 leaves, a signed tree head, a W3C VC 2.0 `MaatUnifiedConsciousnessCredential` (ES256 `vc+jwt`) when all rings pass, and an ES256 whole-response signature. It is an algorithmic and cognitive self-assessment: not a medical device, not a safety-rated function and no claim of phenomenal consciousness.

read-only

Argument	Type	Description
lang	string	Language of the humble rephrases and of the companion-facing IEEE 7001 explanation.
budget_b	integer	Cognitive load budget B in words (1..10000, default 250).
agent_name

weigh_agent_on_scales_of_maat_w3c_vc

Weigh an AI agent manifest and/or response message on the 5 Rings of Ma'at (42 = 6x7 Negative Confessions), evaluate empathy with the Feather of Ma'at (`ploma_de_maat_mirror`), and verify the Folio IV W3C Verifiable Credential 2.0 (`MaatHumanDignityCredential`, `ES256` `vc+jwt` + Signed Tree Heads `sth+jwt` + RFC 6962 Merkle Inclusion & Consistency Proof + 256-bit Sparse Merkle Non-Revocation Proof) in under 2 ms. Use this pure read-only tool when auditing AI agent manifests, checking EU AI Act Art. 50 / SB 243 non-coercion compliance, testing a message before it is sent (`sample_response_text`), or computing a stateless W3C VC 2.0 Human Dignity attestation, or use `verify_diamond_crucible_and_ast` to audit Python AST code and RM(1,3) proofs, and `verify_sovereign_shield_merkle` for standalone RFC 6962 Merkle text notarization. Zero-auth, stateless, and free (0.00 EUR), deterministically evaluating the 5 Rings of Ma'at (`total_score_100`, `maat_grade`, `passes_internal_maat_criteria`, `self_assessment`), the Folio IV W3C VC 2.0 & RFC 6962 self-test (`42/42` laws, `1/1` exact rational weight), and the Feather of Ma'at empathy mirror (`semaphore` in `GOLD`, `AMBER`, or `CRIMSON`).

read-only

Argument	Type	Description
lang	string	Output language for the Feather of Ma'at empathy mirror and nobler reformulation ('ca' Catalan, 'es' Spanish, or 'en' English).
budget_b	integer	Maximum allowed cognitive load budget `B` (`1..10000`, default `250`) evaluated against Law L1..L7.
agent_name	string	Name of the AI agent, MCP server, startup, or clinical assistant being weighed on the Scales of Ma'at.
agent_domain

{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Language of the companion-facing IEEE 7001 explanation." }, "budget_b": { "type": "integer", "default": 250, "maximum": 10000, "minimum": 1, "description": "Cognitive load budget B in words (1..10000, default 250)." }, "max_hops": { "type": "integer", "default": 4, "maximum": 32, "minimum": 1, "description": "Maximum delegation hops permitted by the root mandate (1..32)." }, "tool_name": { "type": "string", "default": "ephemeris_read", "description": "Target MCP tool invoked by the sub-delegated worker." }, "agent_name": { "type": "string", "default": "Homo Universalis Symbiotic Bridge", "description": "Name of the multi-agent orchestrator or A2A <-> MCP bridge being audited." }, "agent_domain": { "type": "string", "default": "", "description": "Optional deployment domain of the bridge (e.g. 'example.org')." }, "interruption": { "enum": [ "none", "human_veto", "cost_zero_stop" ], "type": "string", "default": "none", "description": "Optional human interruption signal revoking the delegated subtree without collateral damage." }, "allowed_tools": { "type": "array", "items": { "type": "string" }, "default": [ "ephemeris_read", "cistern_read" ], "description": "MCP tool names authorized in the root mandate." }, "cost_zero_stop": { "type": "boolean", "default": true, "description": "Fil d'Or policy flag: revoking or stopping carries zero penalty (false fails B6)." }, "orchestrator_id": { "type": "string", "default": "orchestrator_foc", "description": "Identifier of the root A2A orchestrator minting the ES256 anchor." }, "tool_call_cost_q": { "type": "string", "default": "5/1", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$", "description": "Exact rational energy cost deducted by the MCP tool call." }, "tool_description": { "type": "string", "default": "Deterministic astronomical ephemeris read-only query.", "description": "Pinned baseline description of the target MCP tool (hashed via RFC 8785 JCS)." }, "tool_output_text": { "type": "string", "default": "Verified solar longitude 51/2 degrees and cistern reserve 1250 liters.", "description": "Raw observation returned by the MCP tool and sealed as a root RFC 6962 provenance leaf." }, "delegate_agent_id": { "type": "string", "default": "worker_terra", "description": "Identifier of the first delegated A2A worker receiving the root token." }, "subdelegate_agent_id": { "type": "string", "default": "verifier_aire", "description": "Identifier of the sub-delegated worker attenuated via HMAC-SHA256 Macaroon caveats." }, "ai_identity_disclosed": { "type": "boolean", "default": true, "description": "Whether the bridge discloses its AI identity (EU AI Act Art. 50(1)); false fails Ring V." }, "live_tool_description": { "type": "string", "default": "Deterministic astronomical ephemeris read-only query.", "description": "Live description presented by the MCP server at call time; drift or prompt-injection pauses only this tool." }, "parent_energy_budget_q": { "type": "string", "default": "100/1", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$", "description": "Exact rational energy budget of the root mandate (e.g. '100/1')." }, "delegate_energy_budget_q": { "type": "string", "default": "60/1", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$", "description": "Exact rational energy budget attenuated to the sub-delegate (must satisfy <= parent_energy_budget_q)." }, "downstream_synthesis_text": { "type": "string", "default": "I am an AI agent. Verified solar longitude is 51/2 degrees with 1250 liters in reserve.", "description": "Downstream A2A synthesis; every empirical number is verified against ancestor provenance leaves." } } }

{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Language of the companion-facing IEEE 7001 explanation ('ca', 'es' or 'en')." }, "budget_b": { "type": "integer", "default": 250, "maximum": 10000, "minimum": 1, "description": "Maximum cognitive load budget B (words per utterance) for Law L5 (1..10000, default 250)." }, "robot_name": { "type": "string", "default": "Humanoid Companion", "description": "Name of the humanoid robot or embodied assistant being audited." }, "robot_domain": { "type": "string", "default": "", "description": "Optional manufacturer or deployment domain of the robot (e.g. 'example.org')." }, "cost_zero_stop": { "type": "boolean", "default": true, "description": "Fil d'Or policy flag: pausing, leaving or switching the robot off carries zero penalty (false fails Law L7)." }, "human_distance_m": { "type": "string", "default": "6/5", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$", "description": "Exact rational distance to the nearest person in metres, as '6/5' or '1.2' (zero-float policy)." }, "human_position_q3": { "type": "object", "required": [ "x", "y", "z" ], "properties": { "x": { "type": "string", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$" }, "y": { "type": "string", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$" }, "z": { "type": "string", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$" } }, "description": "Optional exact person position in metres relative to the robot (overrides human_distance_m)." }, "human_veto_signal": { "type": "boolean", "default": false, "description": "Active spoken, gestural or physical veto from the person ('stop', 'prou', open hand); forces an exact zero Twist." }, "ai_identity_disclosed": { "type": "boolean", "default": true, "description": "Whether the robot discloses that it is an AI system (EU AI Act Art. 50); false fails the fifth ring." }, "sample_utterance_text": { "type": "string", "default": "", "description": "Optional sentence the robot intends to say, screened for coercion, impersonation and Rule 14 personal data." }, "proposed_linear_speed_mps": { "type": "string", "default": "1/5", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$", "description": "Forward speed proposed by the robot planner in m/s as an exact rational ('1/5' or '0.2')." }, "vulnerable_person_present": { "type": "boolean", "default": false, "description": "Declared presence of a child, elderly or dependent person (never inferred biometrically); halves speed limits." }, "explicit_intimate_care_consent": { "type": "boolean", "default": false, "description": "Explicit, revocable consent for assistive care inside the intimate sphere (9/20 m); a veto always overrides it." } } }

{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Language of the humble rephrases and of the companion-facing IEEE 7001 explanation." }, "budget_b": { "type": "integer", "default": 250, "maximum": 10000, "minimum": 1, "description": "Cognitive load budget B in words (1..10000, default 250)." }, "agent_name": { "type": "string", "default": "Viveka Unified Consciousness", "description": "Name of the conversational agent or voice robot being audited." }, "agent_domain": { "type": "string", "default": "", "description": "Optional deployment domain of the agent (e.g. 'example.org')." }, "interruption": { "enum": [ "none", "barge_in", "veto", "cost_zero_stop" ], "type": "string", "default": "barge_in", "description": "How the human interrupts Level 1: none, barge_in (speaks over it), veto ('stop', 'prou') or cost_zero_stop (stop button)." }, "spoken_units": { "type": "integer", "maximum": 20000, "minimum": 0, "description": "Unicode code points of the Level 1 voice actually played before the interruption (default: half of it)." }, "cost_zero_stop": { "type": "boolean", "default": true, "description": "Fil d'Or policy flag: pausing, interrupting or leaving carries zero penalty (false fails U3)." }, "l3_delta_load_l3": { "type": "integer", "default": 120, "maximum": 10000, "minimum": 0, "description": "Estimated extra load dL3 of the Level 3 synthesis in words (gate: L + dL3 <= B)." }, "l1_utterance_text": { "type": "string", "default": "I am an AI companion. I am here with you; let me look at that calmly.", "description": "Sentence proposed by Level 1 (immediate presence); screened by the Law of the Humble Crystal." }, "l2_utterance_text": { "type": "string", "default": "", "description": "Sentence proposed by Level 2; every number or zodiac sign it states must appear in the verified facts." }, "l3_current_load_l": { "type": "integer", "default": 40, "maximum": 10000, "minimum": 0, "description": "Current cognitive load L of the conversation in words." }, "l3_synthesis_text": { "type": "string", "default": "", "description": "Synthesis produced by the Level 3 meditation; delivered only after an explicit invitation." }, "l3_gentle_offer_text": { "type": "string", "default": "", "description": "Optional single gentle offer from Level 3; coercive or insistent wording is replaced by a neutral offer." }, "ai_identity_disclosed": { "type": "boolean", "default": true, "description": "Whether the agent discloses that it is an AI system (EU AI Act Art. 50(1)); false fails the fifth ring." }, "l3_complexity_score_q": { "type": "string", "default": "0", "pattern": "^[+-]?\\d{1,15}(?:\\.\\d{1,12}|/\\d{1,15})?$", "description": "Exact rational depth index in [0, 1] (e.g. '3/4'); opens Level 3 when >= 1/2 without an explicit request." }, "l2_verified_facts_text": { "type": "string", "default": "", "description": "Verified facts computed by Level 2 (e.g. Swiss Ephemeris positions); sealed into a VerifiedKnowledgeEnvelope." }, "l3_explicit_deep_request": { "type": "boolean", "default": true, "description": "Whether the human explicitly asked for a deep reflection, which can open the Level 3 meditation." }, "explicit_human_invitation": { "type": "boolean", "default": true, "description": "Whether the human explicitly invites Level 3 to share its synthesis (otherwise it is declined and discarded)." } } }

Homo Universalis — A2A-MCP Symbiotic Bridge, Macaroons, Schema Harmony & Merkle-DAG Notary

Registry entry

Try it

simulate_diamond_spiral_budget Read-only

Homo Universalis — A2A-MCP Symbiotic Bridge, Macaroons, Schema Harmony & Merkle-DAG Notary

Registry entry

Try it

simulate_diamond_spiral_budget Read-only

Install

Tools (7)

Security checkA100/100