aaaa-nexus — Formally Verified AI Safety APIs

Formally verified AI safety APIs. Pay-per-call via USDC (x402). 75+ endpoints, no signup.

我該用這個嗎

品質與安全性

A
說明品質
83%
結構描述完整度
90%
命名品質
80%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目(13)

  • LOWTool 'rng_quantum' description lacks action verb在 rng_quantum 中
  • LOWTool 'ratchet_register' description lacks action verb在 ratchet_register 中
  • LOWTool 'vanguard_mev_route_intent' description lacks action verb在 vanguard_mev_route_intent 中
  • LOWTool 'vanguard_wallet_govern_session' description lacks action verb在 vanguard_wallet_govern_session 中
  • LOWTool 'uep_context' description lacks action verb在 uep_context 中
  • LOWTool 'uep_autopoiesis_plan' description lacks action verb在 uep_autopoiesis_plan 中
  • LOWTool 'uep_aha_detect' description lacks action verb在 uep_aha_detect 中
  • LOWTool 'sys_lint_gate' description lacks action verb在 sys_lint_gate 中
  • LOWTool 'omega_intent_nl' description lacks action verb在 omega_intent_nl 中
  • LOWTool 'forge_recon' description lacks action verb在 forge_recon 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~2,785Token(工具定義)
~417 B典型回應大小
顯著的注意力影響(128k 上下文的 2.18%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "aaaa-nexus": {
      "url": "https://aaaa-nexus.atomadictech.workers.dev/mcp"
    }
  }
}

遠端端點

https://aaaa-nexus.atomadictech.workers.dev/mcpstreamable-http

它能做什麼

工具清單

工具(44)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪rng_quantum(body)

Quantum-seeded random bytes with HMAC-SHA256 entropy proof

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪threat_score(body)

Score a JSON payload for security threats using triality consensus

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
🟢hallucination_oracle(body)

Get the LLM hallucination threshold constant

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪identity_verify(body)

Topological identity verification

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪ratchet_register(body)

Register a new 47-epoch RatchetGate session (MCP CVE-2025-6514 mitigation)

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪authorize_action(body)

Pre-action authorization gateway — deterministic tool-call gating with cryptographic tokens

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪spending_authorize(body)

Spending governance — validate agent chain spending within trust-decay bounds

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪lineage_record(body)

Decision lineage vault — structured decision trace capture with tamper-proof hash chain

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪contract_verify(body)

Behavioral contract verifier — verify agent policy claims against formal bounds

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪federation_mint(body)

Agent identity federation — mint cross-platform portable identity tokens

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪aegis_mcp_proxy_execute(body)

NEXUS AEGIS MCP-Sentinel gateway for prompt-injection resistant tool execution

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪aegis_router_epistemic_bound(body)

NEXUS AEGIS reverse proxy that blocks high-entropy or low-confidence generations

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪vanguard_continuous_redteam(body)

NEXUS VANGUARD continuous red teaming for DeFi contracts and transaction bundles.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪vanguard_mev_route_intent(body)

NEXUS VANGUARD MEV route intent protection and shield bundle orchestration.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪vanguard_wallet_govern_session(body)

NEXUS VANGUARD UCAN governance session issuance for structured wallet approval.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪vanguard_escrow_lock_and_verify(body)

NEXUS VANGUARD escrow lock-and-verify with contract validation and release gating.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪uep_preflight(body)

UEP phase-0 preflight gate — bounded task summary and friction estimate before execution.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪uep_context(body)

UEP context pack synthesis — merge recon snippets into a single agent-facing context object.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪uep_synthesis_guard(body)

UEP synthesis guard — block ungrounded expansions when evidence links are missing.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪uep_autopoiesis_plan(body)

UEP autopoiesis plan — structured self-maintenance loop proposal with rollback hooks.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪uep_trace_certify(body)

UEP trace certification — sign a decision trace checksum for audit vault handoff.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪uep_aha_detect(body)

UEP AHA moment detector — novelty spike scoring for epiphany-style gates.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪sys_constants(body)

Sys constants snapshot — public tier counts, trust floor, and block dimension anchors.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
🟢rag_augment(body)

Trusted RAG augment — retrieve-and-quote augmentation with provenance hashes.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪text_summarize(body)

Extractive text summarizer for bounded passages (JSON in, summary out).

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪sys_trust_gate(body)

Sys trust gate — PASS/FAIL hallucination and drift screen for agent payloads.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪sys_lint_gate(body)

Sys lint gate — structural policy lint over JSON agent plans.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪intent_classify(body)

Keyword intent classifier for agent utterances — query/command/report/alert lanes.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪agents_plan(body)

Rule-based goal decomposition into 3–5 deterministic execution steps.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪keys_validate(body)

Validate X-API-Key entitlement tier (paid/extended/master) before gated tool calls.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪entitlement_attest(body)

Attest Ed25519-style entitlement token structure + signature for sovereign emit access.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪omega_intent_route(body)

Rank sovereign intent lanes (recon/emit/heal/govern/hive/synthesis) — deterministic router.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪omega_emit_materialize(body)

Materialize deterministic contract sketch from intent — logic upstream of language.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪omega_emit_polyglot(body)

Language-agnostic emit targets from frozen contract — Python/Rust/TS/JS/Go sketches.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪omega_intent_nl(body)

Structured intent → agent-facing NL sketch (training signal, not human blueprint).

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪forge_recon(body)

Polyglot repo recon — language/tier/source breakdown for monadic architectures.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪forge_certify(body)

Polyglot 4-axis certify (docs/tests/layout/wire) with scored verdict.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪forge_wire(body)

Repo-wide upward-import wire scan — polyglot tier discipline check.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪forge_tier_infer(body)

Infer monadic tier placement for a file path from polyglot heuristics.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪forge_audit(body)

Compound Forge audit — recon + certify + wire in one deterministic pass.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪docs_generate(body)

Deterministic documentation enrichment targets from local path analysis.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
🟢lint_analyze(body)

Synthesize lint findings from supplied local analysis artifacts.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪certify_codebase(body)

Countersign local Forge certificate with storefront attestation lane.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}
⚪certify_output(body)

Output certification notary — tamper-evident seal on agent deliverables.

輸入結構描述

{
  "type": "object",
  "properties": {
    "body": {
      "description": "For POST tools: JSON body per the matching path in /openapi.json.",
      "type": "object"
    }
  }
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本44 個工具
已驗證未記錄版本44 個工具