// MCP TOOL REFERENCE

AAAA-NEXUS — FORMALLY VERIFIED AI SAFETY APIS TOOLS

27 tools from the aaaa-nexus — Formally Verified AI Safety APIs MCP Server, categorised by risk level.

View the aaaa-nexus — Formally Verified AI Safety APIs policy → Token cost: 1,645 tokens →

// ALL 27 AAAA-NEXUS — FORMALLY VERIFIED AI SAFETY APIS TOOLS

READ 23 tools

Read aegis_router_epistemic_bound NEXUS AEGIS reverse proxy that blocks high-entropy or low-confidence generations Read authorize_action Pre-action authorization gateway — deterministic tool-call gating with cryptographic tokens Read contract_verify Behavioral contract verifier — verify agent policy claims against formal bounds Read federation_mint Agent identity federation — mint cross-platform portable identity tokens Read hallucination_oracle Get the LLM hallucination threshold constant Read identity_verify Topological identity verification Read lineage_record Decision lineage vault — structured decision trace capture with tamper-proof hash chain Read rag_augment Trusted RAG augment — retrieve-and-quote augmentation with provenance hashes. Read rng_quantum Quantum-seeded random bytes with HMAC-SHA256 entropy proof Read spending_authorize Spending governance — validate agent chain spending within trust-decay bounds Read sys_constants Sys constants snapshot — public tier counts, trust floor, and block dimension anchors. Read sys_lint_gate Sys lint gate — structural policy lint over JSON agent plans. Read sys_trust_gate Sys trust gate — PASS/FAIL hallucination and drift screen for agent payloads. Read text_summarize Extractive text summarizer for bounded passages (JSON in, summary out). Read threat_score Score a JSON payload for security threats using triality consensus Read uep_aha_detect UEP AHA moment detector — novelty spike scoring for epiphany-style gates. Read uep_context UEP context pack synthesis — merge recon snippets into a single agent-facing context object. Read uep_preflight UEP phase-0 preflight gate — bounded task summary and friction estimate before execution. Read uep_synthesis_guard UEP synthesis guard — block ungrounded expansions when evidence links are missing. Read uep_trace_certify UEP trace certification — sign a decision trace checksum for audit vault handoff. Read vanguard_continuous_redteam NEXUS VANGUARD continuous red teaming for DeFi contracts and transaction bundles. Read vanguard_mev_route_intent NEXUS VANGUARD MEV route intent protection and shield bundle orchestration. Read vanguard_wallet_govern_session NEXUS VANGUARD UCAN governance session issuance for structured wallet approval.

WRITE 3 tools

Write ratchet_register Register a new 47-epoch RatchetGate session (MCP CVE-2025-6514 mitigation) Write uep_autopoiesis_plan UEP autopoiesis plan — structured self-maintenance loop proposal with rollback hooks. Write vanguard_escrow_lock_and_verify NEXUS VANGUARD escrow lock-and-verify with contract validation and release gating.

EXECUTE 1 tools

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

// FAQ

How many tools does the aaaa-nexus — Formally Verified AI Safety APIs MCP server have? +

The aaaa-nexus — Formally Verified AI Safety APIs MCP server exposes 27 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on aaaa-nexus — Formally Verified AI Safety APIs tools? +

Route the aaaa-nexus — Formally Verified AI Safety APIs server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do aaaa-nexus — Formally Verified AI Safety APIs tools fall into? +

aaaa-nexus — Formally Verified AI Safety APIs tools are categorised as Read (23), Write (3), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.