MCP server

aaaa-nexus — Formally Verified AI Safety APIs

io.github.atomadictech/aaaa-nexus

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

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

Working at last checkAbout 3,477 tokens per request once connected44 tools

Website Source

https://aaaa-nexus.atomadictech.workers.dev/mcp

At a glance

Type: MCP server
Publisher: Not verified
Status: Working at last check
Tools: 44
Token cost: About 3,477 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http aaaa-nexus https://aaaa-nexus.atomadictech.workers.dev/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.aaaa-nexus]
url = "https://aaaa-nexus.atomadictech.workers.dev/mcp"

Gemini CLI

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

Cursor

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

VS Code

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

Antigravity

agy mcp add aaaa-nexus https://aaaa-nexus.atomadictech.workers.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"aaaa-nexus","server_url":"https://aaaa-nexus.atomadictech.workers.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"aaaa-nexus","server_url":"https://aaaa-nexus.atomadictech.workers.dev/mcp"}

Tools

aegis_mcp_proxy_execute ~82 tokens
NEXUS AEGIS MCP-Sentinel gateway for prompt-injection resistant tool execution
aegis_router_epistemic_bound ~84 tokens
NEXUS AEGIS reverse proxy that blocks high-entropy or low-confidence generations
agents_plan ~76 tokens
Rule-based goal decomposition into 3–5 deterministic execution steps.
authorize_action ~83 tokens
Pre-action authorization gateway — deterministic tool-call gating with cryptographic tokens
certify_codebase ~77 tokens
Countersign local Forge certificate with storefront attestation lane.
certify_output ~77 tokens
Output certification notary — tamper-evident seal on agent deliverables.
contract_verify ~80 tokens
Behavioral contract verifier — verify agent policy claims against formal bounds
docs_generate ~77 tokens
Deterministic documentation enrichment targets from local path analysis.
entitlement_attest ~83 tokens
Attest Ed25519-style entitlement token structure + signature for sovereign emit access.
federation_mint ~78 tokens
Agent identity federation — mint cross-platform portable identity tokens
forge_audit ~76 tokens
Compound Forge audit — recon + certify + wire in one deterministic pass.
forge_certify ~76 tokens
Polyglot 4-axis certify (docs/tests/layout/wire) with scored verdict.
forge_recon ~78 tokens
Polyglot repo recon — language/tier/source breakdown for monadic architectures.
forge_tier_infer ~77 tokens
Infer monadic tier placement for a file path from polyglot heuristics.
forge_wire ~75 tokens
Repo-wide upward-import wire scan — polyglot tier discipline check.
hallucination_oracle ~71 tokens
Get the LLM hallucination threshold constant
identity_verify ~66 tokens
Topological identity verification
intent_classify ~80 tokens
Keyword intent classifier for agent utterances — query/command/report/alert lanes.
keys_validate ~80 tokens
Validate X-API-Key entitlement tier (paid/extended/master) before gated tool calls.
lineage_record ~82 tokens
Decision lineage vault — structured decision trace capture with tamper-proof hash chain
lint_analyze ~74 tokens
Synthesize lint findings from supplied local analysis artifacts.
omega_emit_materialize ~83 tokens
Materialize deterministic contract sketch from intent — logic upstream of language.
omega_emit_polyglot ~82 tokens
Language-agnostic emit targets from frozen contract — Python/Rust/TS/JS/Go sketches.
omega_intent_nl ~80 tokens
Structured intent → agent-facing NL sketch (training signal, not human blueprint).
omega_intent_route ~84 tokens
Rank sovereign intent lanes (recon/emit/heal/govern/hive/synthesis) — deterministic router.
rag_augment ~78 tokens
Trusted RAG augment — retrieve-and-quote augmentation with provenance hashes.
ratchet_register ~78 tokens
Register a new 47-epoch RatchetGate session (MCP CVE-2025-6514 mitigation)
rng_quantum ~72 tokens
Quantum-seeded random bytes with HMAC-SHA256 entropy proof
spending_authorize ~80 tokens
Spending governance — validate agent chain spending within trust-decay bounds
sys_constants ~81 tokens
Sys constants snapshot — public tier counts, trust floor, and block dimension anchors.
sys_lint_gate ~74 tokens
Sys lint gate — structural policy lint over JSON agent plans.
sys_trust_gate ~79 tokens
Sys trust gate — PASS/FAIL hallucination and drift screen for agent payloads.
text_summarize ~77 tokens
Extractive text summarizer for bounded passages (JSON in, summary out).
threat_score ~75 tokens
Score a JSON payload for security threats using triality consensus
uep_aha_detect ~78 tokens
UEP AHA moment detector — novelty spike scoring for epiphany-style gates.
uep_autopoiesis_plan ~83 tokens
UEP autopoiesis plan — structured self-maintenance loop proposal with rollback hooks.
uep_context ~82 tokens
UEP context pack synthesis — merge recon snippets into a single agent-facing context object.
uep_preflight ~82 tokens
UEP phase-0 preflight gate — bounded task summary and friction estimate before execution.
uep_synthesis_guard ~82 tokens
UEP synthesis guard — block ungrounded expansions when evidence links are missing.
uep_trace_certify ~81 tokens
UEP trace certification — sign a decision trace checksum for audit vault handoff.
vanguard_continuous_redteam ~84 tokens
NEXUS VANGUARD continuous red teaming for DeFi contracts and transaction bundles.
vanguard_escrow_lock_and_verify ~85 tokens
NEXUS VANGUARD escrow lock-and-verify with contract validation and release gating.
vanguard_mev_route_intent ~81 tokens
NEXUS VANGUARD MEV route intent protection and shield bundle orchestration.
vanguard_wallet_govern_session ~84 tokens
NEXUS VANGUARD UCAN governance session issuance for structured wallet approval.

Browse

Related MCP servers

Web & domain tools
Read any public page as markdown, link previews, URL safety, page audits, domain availability and…
toolvend - utility APIs for agents
30-day x402 history, calendar, DNS, RDAP, LEI, URLs, scraping, text, VAT, QR. Pay-per-call USDC.
Agent Data Tools
15 data tools at $0.01 USDC/call on Base via x402. Free discovery; x402 wallet client required.
HumanMirror One
Agent routing, safety preflight, execution receipts, best execution and verified outcomes.
DevX Agent Hub
x402 pay-per-call agent tools: token safety/honeypot check, speech to text, TTS, translate, OCR, web
Quant Agent Shop
Search, filings, sanctions, company, domain, email, SEO and weather tools, paid per call over x402.
X402 Endpoints
x402 paid API tools for AI agents on Base: EU/global registries, crypto, wallet & agent trust.
Minia2a
minia2a.uk — hosted MCP over streamable HTTP: call 1,600+ x402 pay-per-call APIs, USDC on Base.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.atomadictech/aaaa-nexus.svg)](https://aptlynx.net/servers/io.github.atomadictech/aaaa-nexus)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents