AAAA Nexus MCP
- AAAA-Nexus/aaaa-nexus-mcp
AAAA-Nexus MCP is an MCP server that exposes 75+ formally verified AI safety APIs to agents with pay-per-call USDC x402 billing.
About
AAAA-Nexus MCP is a Model Context Protocol server that connects coding agents to Atomadic’s formally verified AI safety APIs. developers shipping agent features often lack time to design red-team suites, policy classifiers, and audit trails; this server packages those capabilities as callable tools over stdio so Claude Code, Cursor, or Codex can invoke checks during implementation and pre-launch review. Billing is pay-per-call through USDC x402, which suits developers who want usage-based cost instead of enterprise contracts. The catalog lists 75+ endpoints, signaling broad coverage beyond a single moderation call. Use it when you want agent workflows to consult external safety verification rather than trusting prompt rules alone. It is an integration layer, not a replacement for your own threat modeling or legal review.
- 75+ formally verified AI safety API endpoints exposed as MCP tools
- Pay-per-call billing via USDC x402 with no account signup
- Python stdio MCP package (`aaaa-nexus-mcp`) for local agent wiring
- Hosted safety APIs at atomadic.tech instead of self-hosted policy engines
AAAA Nexus MCP by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add aaaa-nexus-mcp -- python aaaa-nexus-mcp -m aaaa_nexus_mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | aaaa-nexus-mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Repository | AAAA-Nexus/aaaa-nexus-mcp ↗ |
What it does
Wire formally verified AI safety checks into Claude Code or Cursor agents without building your own guardrail stack.
Who is it for?
Best when you're shipping AI agents or copilots and need external safety APIs without signup-heavy enterprise platforms.
Skip if: Skip if you require fully on-prem safety with no micropayments or and only need simple static content filters in-app.
What you get
After you register the stdio server, your agent can call verified safety endpoints on demand and you pay only per invocation via x402.
- Agent-callable tools backed by 75+ safety API endpoints
- Usage-based safety checks without platform signup
- Documented stdio MCP entry in your agent config
By the numbers
- 75+ API endpoints
- Pay-per-call USDC x402 billing
- Package version 0.1.1
Recommended MCP Servers
1Claw VaultHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.2
1passwordMCP server for 1Password service accounts — tools and resources for vaults and credentials18
402sentinel McpAssess an x402 counterparty's risk BEFORE paying: allow/review/block, scored on-chain (Base).1
A2adependencyinspector McpRemote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready evi
A2a Governance Bridge McpA2A Governance Bridge MCP server.A2aidentitytoll McpRemote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.How it compares
MCP safety API bridge, not an agent skill or local lint rule pack.
FAQ
Who is AAAA Nexus MCP for?
It is for developers wiring Claude Code, Cursor, or similar agents to formally verified AI safety APIs at build and ship time.
When should I use AAAA Nexus MCP?
Use it when you are hardening agent features before launch and want pay-per-call access to 75+ safety endpoints instead of building verification in-house.
How do I add AAAA Nexus MCP to my agent?
Install the PyPI package `aaaa-nexus-mcp`, run it as a stdio MCP server with `python -m aaaa_nexus_mcp`, and add that command to your agent’s MCP config; fund USDC x402 calls per Atomadic docs.