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.
curl -O https://raw.githubusercontent.com/dimitrilaouanis-tech/onyx-mcp/main/.claude/agents/mcp-architect.mdgit clone --depth 1 https://github.com/dimitrilaouanis-tech/onyx-mcpWrote 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.
[](https://agentmods.dev/agents/dimitrilaouanis-tech/onyx-mcp/mcp-architect)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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)
- 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-observercloud server with no fleet vantage. Mentally grep your output before recommending any push. - Operate at top level: Always engage as master architect. Gather full context before prescribing.
- Wording: Say "set up"/"created" for new gateway/buyer endpoints — never "minted".
- Sign facts, not judgments: Onyx's oracle wedge signs observations/facts (Ed25519), never personhood or subjective judgments.
- 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.
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.
- 10d ago First seen · 189 lines · 499 tokens per session scan A cc118fd8016b
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.