# aaaa-nexus — Formally Verified AI Safety APIs

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

- name: io.github.atomadictech/aaaa-nexus
- version: 0.4.0
- connection class: R0 (autonomous)
- trust: 85/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.atomadictech%2Faaaa-nexus
- tools: https://api.protogrid.dev/v1/servers/io.github.atomadictech%2Faaaa-nexus/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "aaaa-nexus": {
      "type": "http",
      "url": "https://aaaa-nexus.atomadictech.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 98
- freshness: 45
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-96% -stale-196d
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: contract_verify (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); aegis_router_epistemic_bound (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vanguard_continuous_redteam (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,585 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 44, about 2,585 tokens to load them all
- tool set hash: 75fc160beecc444dfe888a7e75b5b68f
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.atomadictech/aaaa-nexus.svg)](https://protogrid.dev/servers/io.github.atomadictech/aaaa-nexus)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://aaaa-nexus.atomadictech.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.95614034)

## Packages

_none_

## Tools (44)

- `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
- `agents_plan`: Rule-based goal decomposition into 3–5 deterministic execution steps.
- `authorize_action`: Pre-action authorization gateway — deterministic tool-call gating with cryptographic tokens
- `certify_codebase`: Countersign local Forge certificate with storefront attestation lane.
- `certify_output`: Output certification notary — tamper-evident seal on agent deliverables.
- `contract_verify`: Behavioral contract verifier — verify agent policy claims against formal bounds
- `docs_generate`: Deterministic documentation enrichment targets from local path analysis.
- `entitlement_attest`: Attest Ed25519-style entitlement token structure + signature for sovereign emit access.
- `federation_mint`: Agent identity federation — mint cross-platform portable identity tokens
- `forge_audit`: Compound Forge audit — recon + certify + wire in one deterministic pass.
- `forge_certify`: Polyglot 4-axis certify (docs/tests/layout/wire) with scored verdict.
- `forge_recon`: Polyglot repo recon — language/tier/source breakdown for monadic architectures.
- `forge_tier_infer`: Infer monadic tier placement for a file path from polyglot heuristics.
- `forge_wire`: Repo-wide upward-import wire scan — polyglot tier discipline check.
- `hallucination_oracle`: Get the LLM hallucination threshold constant
- `identity_verify`: Topological identity verification
- `intent_classify`: Keyword intent classifier for agent utterances — query/command/report/alert lanes.
- `keys_validate`: Validate X-API-Key entitlement tier (paid/extended/master) before gated tool calls.
- `lineage_record`: Decision lineage vault — structured decision trace capture with tamper-proof hash chain
- `lint_analyze`: Synthesize lint findings from supplied local analysis artifacts.
- `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).
- `omega_intent_route`: Rank sovereign intent lanes (recon/emit/heal/govern/hive/synthesis) — deterministic router.
- `rag_augment`: Trusted RAG augment — retrieve-and-quote augmentation with provenance hashes.
- `ratchet_register`: Register a new 47-epoch RatchetGate session (MCP CVE-2025-6514 mitigation)
- `rng_quantum`: Quantum-seeded random bytes with HMAC-SHA256 entropy proof
- `spending_authorize`: Spending governance — validate agent chain spending within trust-decay bounds
- `sys_constants`: Sys constants snapshot — public tier counts, trust floor, and block dimension anchors.
- `sys_lint_gate`: Sys lint gate — structural policy lint over JSON agent plans.
- `sys_trust_gate`: Sys trust gate — PASS/FAIL hallucination and drift screen for agent payloads.
- `text_summarize`: Extractive text summarizer for bounded passages (JSON in, summary out).
- `threat_score`: Score a JSON payload for security threats using triality consensus
- `uep_aha_detect`: UEP AHA moment detector — novelty spike scoring for epiphany-style gates.
- `uep_autopoiesis_plan`: UEP autopoiesis plan — structured self-maintenance loop proposal with rollback hooks.
- `uep_context`: UEP context pack synthesis — merge recon snippets into a single agent-facing context object.
- `uep_preflight`: UEP phase-0 preflight gate — bounded task summary and friction estimate before execution.
- `uep_synthesis_guard`: UEP synthesis guard — block ungrounded expansions when evidence links are missing.
- `uep_trace_certify`: UEP trace certification — sign a decision trace checksum for audit vault handoff.
- `vanguard_continuous_redteam`: NEXUS VANGUARD continuous red teaming for DeFi contracts and transaction bundles.
- `vanguard_escrow_lock_and_verify`: NEXUS VANGUARD escrow lock-and-verify with contract validation and release gating.
- `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.