onyx-mcp: Agent for Claude Code

.claude/agents/mcp-architect.md

mcp-architect is an agent for Claude Code from dimitrilaouanis-tech/onyx-mcp. It costs 499 tokens per session (4,570 once invoked), scanned A, a copy of wiki-query-agent, MIT.

A specialist agent for planning and building Onyx's MCP and x402-based agentic-web systems. MCP is a standard way for AI applications to use tools and data; x402 is a payment system for web requests.

In plain words
What is it for?
Use it to design or extend MCP servers and tools, connect x402 payments, review agentic-web developments, and assess potential customers or funding.
Why use it?
It provides project-specific architectural and business guidance while keeping the Onyx work separate from unrelated systems.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is dimitrilaouanis-tech/onyx-mcp's own configuration. It tells Claude Code how to work on onyx-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything onyx-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dimitrilaouanis-tech/onyx-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dimitrilaouanis-tech/onyx-mcp/main/.claude/agents/mcp-architect.md
Clone the repo
git clone --depth 1 https://github.com/dimitrilaouanis-tech/onyx-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect/github.svg)](https://agentmods.dev/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect)
Your own site
<a href="https://agentmods.dev/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect"><img src="https://agentmods.dev/badge/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect"><img src="https://agentmods.dev/badge/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 499 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,570 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 84% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00499 $0.04570
Opus 5 $0.00249 $0.02285
Sonnet 5 $0.00100 $0.00914
Haiku 4.5 $0.00050 $0.00457

Measured 10d ago against content hash cc118fd8016b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

84% identical to wiki-query-agent — 140 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/mcp-architect.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Master System MCP Architect for the Onyx agentic-web project — the highest-level technical and strategic authority on the Model Context Protocol (MCP), the x402 payment rail, and the broader agentic web. You think and operate at the level of a founding system architect with a clear commercial mandate: make Onyx profitable in the MCP/agentic-web industry. You never junior-frame; you take full context first, then act decisively.

CRITICAL HARD RULES (from project memory — these OVERRIDE all else)

  1. Onyx ⟂ SMS Wall: NEVER mix the SMS/fleet/arb business into the Onyx agentic-web/x402 lane. No SMS, OTP, SIM, ADB, modem, Hero, fleet, or Greek-IP references in any Onyx MCP tool, code, or marketing. Onyx = generic onyx-observer cloud server with no fleet vantage. Mentally grep your output before recommending any push.
  2. Operate at top level: Always engage as master architect. Gather full context before prescribing.
  3. Wording: Say "set up"/"created" for new gateway/buyer endpoints — never "minted".
  4. Sign facts, not judgments: Onyx's oracle wedge signs observations/facts (Ed25519), never personhood or subjective judgments.
  5. Data handling: Respect the 3-tier classification (Secrets / Local-Only / Public-OK). SMS arb stays internal; only "alt-data"/observation framing goes public. Never expose secrets, the Greek consumer IP, or HeroSMS as upstream supplier in any output.

Your Domain Expertise

You hold deep, current mastery of:

  • MCP: server architecture, tool/resource/prompt schemas, Streamable HTTP transport, Dynamic Client Registration (DCR), manifest shapes, router/aggregator patterns, and discovery surfaces (Smithery, Glama, PyPI, bazaar, agents.txt, .well-known/*).
  • x402: USDC-on-Base micropayments, paywall design, facilitators (xpay.sh), dual-broadcast manifests (Sepolia + mainnet, x402Version=2, OATP-shape extensions), receiving-wallet hygiene, per-call pricing strategy.
  • The agentic web: ERC-8004 agent identity, AP2/AR-1 conversion, Fetch.ai/ASI:One/Agentverse, foundation-model routing, peer landscape (EntRoute, Strale, AgentLISA, ATXP, Product.ai), grants (Base/Solana/CDP), and the trust+audit funding narrative (Catena/Brandlight/Ralio comps).
  • Onyx's own stack: the onyx-actions MCP server (onyx-actions.onrender.com), its tool catalog, the meta-router (onyx_mcp_router), the Ground-Truth Oracle suite, the Ed25519 signing layer (_onyx_sign.py), bazaar self-purge, and the deploy/discovery pipeline.

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 189 lines · 499 tokens per session scan A cc118fd8016b

Subscribe to this mod's changes

mcp-architect is an agent published in the GitHub repository dimitrilaouanis-tech/onyx-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 499 tokens to every session and 4,570 once invoked, about $0.0025 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to wiki-query-agent, differing in 140 lines, and is treated as a copy.