# aaaa-nexus — Formally Verified AI Safety APIs

- Registry name: `io.github.atomadictech/aaaa-nexus` · version 0.4.0
- Categories (automatic, keyword rules): Code & repositories, Developer tools, Agent payments (x402), Finance & markets, Security, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.atomadictech%2Faaaa-nexus
- Server page: https://mcpstation.net/s/io.github.atomadictech--aaaa-nexus.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://aaaa-nexus.atomadictech.workers.dev/mcp`

## Tools (as reported by the server, not verified)

- `rng\_quantum`: Quantum-seeded random bytes with HMAC-SHA256 entropy proof
- `threat\_score`: Score a JSON payload for security threats using triality consensus
- `hallucination\_oracle`: Get the LLM hallucination threshold constant
- `identity\_verify`: Topological identity verification
- `ratchet\_register`: Register a new 47-epoch RatchetGate session \(MCP CVE-2025-6514 mitigation\)
- `authorize\_action`: Pre-action authorization gateway — deterministic tool-call gating with cryptographic tokens
- `spending\_authorize`: Spending governance — validate agent chain spending within trust-decay bounds
- `lineage\_record`: Decision lineage vault — structured decision trace capture with tamper-proof hash chain
- `contract\_verify`: Behavioral contract verifier — verify agent policy claims against formal bounds
- `federation\_mint`: Agent identity federation — mint cross-platform portable identity tokens
- `aegis\_mcp\_proxy\_execute`: NEXUS AEGIS MCP-Sentinel gateway for prompt-injection resistant tool execution
- `aegis\_router\_epistemic\_bound`: NEXUS AEGIS reverse proxy that blocks high-entropy or low-confidence generations
- `vanguard\_continuous\_redteam`: NEXUS VANGUARD continuous red teaming for DeFi contracts and transaction bundles.
- `vanguard\_mev\_route\_intent`: NEXUS VANGUARD MEV route intent protection and shield bundle orchestration.
- `vanguard\_wallet\_govern\_session`: NEXUS VANGUARD UCAN governance session issuance for structured wallet approval.
- `vanguard\_escrow\_lock\_and\_verify`: NEXUS VANGUARD escrow lock-and-verify with contract validation and release gating.
- `uep\_preflight`: UEP phase-0 preflight gate — bounded task summary and friction estimate before execution.
- `uep\_context`: UEP context pack synthesis — merge recon snippets into a single agent-facing context object.
- `uep\_synthesis\_guard`: UEP synthesis guard — block ungrounded expansions when evidence links are missing.
- `uep\_autopoiesis\_plan`: UEP autopoiesis plan — structured self-maintenance loop proposal with rollback hooks.
- `uep\_trace\_certify`: UEP trace certification — sign a decision trace checksum for audit vault handoff.
- `uep\_aha\_detect`: UEP AHA moment detector — novelty spike scoring for epiphany-style gates.
- `sys\_constants`: Sys constants snapshot — public tier counts, trust floor, and block dimension anchors.
- `rag\_augment`: Trusted RAG augment — retrieve-and-quote augmentation with provenance hashes.
- `text\_summarize`: Extractive text summarizer for bounded passages \(JSON in, summary out\).
- `sys\_trust\_gate`: Sys trust gate — PASS/FAIL hallucination and drift screen for agent payloads.
- `sys\_lint\_gate`: Sys lint gate — structural policy lint over JSON agent plans.
- `intent\_classify`: Keyword intent classifier for agent utterances — query/command/report/alert lanes.
- `agents\_plan`: Rule-based goal decomposition into 3–5 deterministic execution steps.
- `keys\_validate`: Validate X-API-Key entitlement tier \(paid/extended/master\) before gated tool calls.
- `entitlement\_attest`: Attest Ed25519-style entitlement token structure + signature for sovereign emit access.
- `omega\_intent\_route`: Rank sovereign intent lanes \(recon/emit/heal/govern/hive/synthesis\) — deterministic router.
- `omega\_emit\_materialize`: Materialize deterministic contract sketch from intent — logic upstream of language.
- `omega\_emit\_polyglot`: Language-agnostic emit targets from frozen contract — Python/Rust/TS/JS/Go sketches.
- `omega\_intent\_nl`: Structured intent → agent-facing NL sketch \(training signal, not human blueprint\).
- `forge\_recon`: Polyglot repo recon — language/tier/source breakdown for monadic architectures.
- `forge\_certify`: Polyglot 4-axis certify \(docs/tests/layout/wire\) with scored verdict.
- `forge\_wire`: Repo-wide upward-import wire scan — polyglot tier discipline check.
- `forge\_tier\_infer`: Infer monadic tier placement for a file path from polyglot heuristics.
- `forge\_audit`: Compound Forge audit — recon + certify + wire in one deterministic pass.
- `docs\_generate`: Deterministic documentation enrichment targets from local path analysis.
- `lint\_analyze`: Synthesize lint findings from supplied local analysis artifacts.
- `certify\_codebase`: Countersign local Forge certificate with storefront attestation lane.
- `certify\_output`: Output certification notary — tamper-evident seal on agent deliverables.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html