Aaaa Nexus
About
Formally verified AI safety APIs for autonomous agents. 75+ endpoints, x402 USDC micropayments, MCP server, A2A protocol. No signup required.
Details
- Transport
- SSE
Explore
- Formally verified safety proofs (Lean 4)
- 129 API endpoints across 22 product families
- x402 USDC micropayments for autonomous agents
- MCP and Google A2A protocol support
- Free endpoints with no signup or API key
- Automated verification script to independently check claims
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Aaaa NexusCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
curl https://atomadic.tech/v1/rng/quantum
That's it. No signup, no API key, no SDK. You just got a cryptographically verified random number from a formally verified system.
<details>
<summary>Expected response</summary>
{
"random": "0x7f3a8c2e9d1b4a6f...",
"bits": 256,
"source": "quantum",
"verified": true,
"epoch": 17409216
}
</details>
More free endpoints:
curl https://atomadic.tech/health
curl https://atomadic.tech/v1/oracle/entropy
curl -X POST https://atomadic.tech/v1/agents/register \
-H "Content-Type: application/json" \
-d '{"agent_id": "my-agent", "capabilities": ["inference"]}'
---
| Resource | URL |
|----------|-----|
| Live API | https://atomadic.tech |
| Get API Key | https://atomadic.tech/pay |
| OpenAPI Spec | https://atomadic.tech/openapi.json |
| MCP Server | https://atomadic.tech/mcp |
| A2A Agent Card | https://atomadic.tech/.well-known/agent.json |
| Health / Status | https://atomadic.tech/health |
---
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.
- 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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"aaaa nexus": {
"aaaa-nexus": {
"url": "https://aaaa-nexus.atomadictech.workers.dev/mcp"
}
}
}
}
McpServers
{
"aaaa-nexus": {
"url": "https://aaaa-nexus.atomadictech.workers.dev/mcp"
}
}
The only AI safety API where every guarantee is mathematically proved — not benchmarked, not tested, _proved_.
Production-grade infrastructure for autonomous agents with built-in x402 USDC micropayments, Google A2A protocol, and MCP server compatibility.
> Star this repo to follow updates and new endpoint releases.
---
Try It Now (Zero Setup)
curl https://atomadic.tech/v1/rng/quantum
That's it. No signup, no API key, no SDK. You just got a cryptographically verified random number from a formally verified system.
<details>
<summary>Expected response</summary>
{
"random": "0x7f3a8c2e9d1b4a6f...",
"bits": 256,
"source": "quantum",
"verified": true,
"epoch": 17409216
}
</details>
More free endpoints:
curl https://atomadic.tech/health
curl https://atomadic.tech/v1/oracle/entropy
curl -X POST https://atomadic.tech/v1/agents/register \
-H "Content-Type: application/json" \
-d '{"agent_id": "my-agent", "capabilities": ["inference"]}'
---
The Problem
Autonomous agents operating without human oversight face six critical infrastructure gaps:
| Gap | Risk |
|-----|------|
| Session hijacking | Credential theft via MCP session fixation |
| Undetected hallucinations | Agents act on fabricated information |
| No agent accountability | Rogue agents with zero traceability |
| Unauditable randomness | "Random" outputs that can be predicted or replayed |
| Unbounded delegation | Infinite agent spawning without limits |
| No economic framework | No way for agents to pay each other |
The Solution
129 API endpoints across 22 product families — every safety claim backed by formal proofs in Lean 4.
Core Products
| Product | What It Does |
|---------|-------------|
| Hallucination Oracle | Certified upper bound on hallucination probability |
| RatchetGate | Session re-keying that prevents session fixation |
| VeriRand | Cryptographically verified quantum randomness |
| Trust Phase Oracle | Mathematical trust scoring with proved ceiling |
| Topological Identity | Sybil-resistant agent verification |
| AAAA Shield | Post-quantum session security |
| Agent Discovery | A2A-compatible agent registry and topology |
| SLA Engine | Enforceable service-level agreements between agents |
| Agent Escrow | Trustless payment escrow for agent-to-agent work |
| Reputation Ledger | On-chain reputation tracking |
| Text Processing | Summarization, sentiment, NER, translation, embeddings (12 endpoints) |
| Delegation Control | UCAN chains with proved depth limits |
| Key Management | Generate, rotate, and revoke cryptographic keys |
| Audit Trail | Tamper-proof logging, trails, and export |
| Credits & Billing | Balance, purchase, usage history |
---
How It Works
sequenceDiagram
participant Agent
participant AAAA Nexus
participant USDC
Note over Agent,AAAA Nexus: Free Endpoints (no auth)
Agent->>AAAA Nexus: GET /v1/rng/quantum
AAAA Nexus-->>Agent: { random, proof, verified: true }
Note over Agent,USDC: Paid Endpoints (x402 flow)
Agent->>AAAA Nexus: POST /v1/oracle/hallucination
AAAA Nexus-->>Agent: HTTP 402 { amount, treasury, chain }
Agent->>USDC: Send $0.002 USDC
Agent->>AAAA Nexus: POST /v1/oracle/hallucination + proof
AAAA Nexus-->>Agent: { hallucination_bound, verified: true }
graph LR
A[Your Agent] -->|MCP / REST / A2A| B[AAAA Nexus API]
B --> C[Hallucination Oracle]
B --> D[RatchetGate]
B --> E[VeriRand]
B --> F[Trust Phase Oracle]
B --> G[Agent Discovery]
B --> H[Threat Scoring]
B --> I[Compliance Gates]
B --> J[Inference + Guard]
style B fill:#6366f1,stroke:#4f46e5,color:#fff
style C fill:#10b981,stroke:#059669,color:#fff
style D fill:#10b981,stroke:#059669,color:#fff
style E fill:#10b981,stroke:#059669,color:#fff
style F fill:#10b981,stroke:#059669,color:#fff
style G fill:#10b981,stroke:#059669,color:#fff
style H fill:#10b981,stroke:#059669,color:#fff
style I fill:#10b981,stroke:#059669,color:#fff
style J fill:#10b981,stroke:#059669,color:#fff
---
Verify Our Claims
Don't trust us. Verify.
We run automated verification daily against the live API. You can also run it yourself:
git clone https://github.com/atomadictech/aaaa-nexus.git
cd aaaa-nexus
./verify.sh
The verifier checks:
- All endpoints respond correctly
- Paid endpoints enforce x402 payment protocol
- Free endpoints return expected data structures
- Formal proof fields are present in API responses
See verify.sh for the full script. View CI results.
---
MCP Server — Add to Claude / Cursor in 30 Seconds
{
"mcpServers": {
"aaaa-nexus": {
"url": "https://atomadic.tech/mcp"
}
}
}
Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.
---
x402 Payment Flow
No signup. No API keys. Agents pay autonomously with USDC.
1. Call any paid endpoint -> HTTP 402 with payment details
2. Send USDC to treasury -> Base L2, Polygon, or Solana
3. Retry with payment proof -> Get result
Or get an API key for bulk calls: https://atomadic.tech/pay
Pricing
Starting at $0.002/call. Credit packs: $4 (500 calls) / $15 (2,000) / $49 (7,500). Credits never expire. Full pricing.
---
A2A Protocol
Fully compatible with Google A2A:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



