Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add roedyrustam/vibes-plug --skill mcp-server-architectgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/skills/roedyrustam/vibes-plug/mcp-server-architect)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/mcp-server-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/mcp-server-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/skills/roedyrustam/vibes-plug/mcp-server-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/mcp-server-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01366 |
| Opus 5 | $0.00034 | $0.00683 |
| Sonnet 5 | $0.00014 | $0.00273 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
mcp-server-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Architect (Modern AI Tools)
English
Orchestration & Integration
Connects and orchestrates with relevant domain skills: ai-llm-integration-expert for core LLM routing and RAG pipelines, and doku-mcp-server for payments integration examples. Ensure cohesive execution when spawning subagents.
Description
Ultimate guide for building modern AI Tools/Bots via Model Context Protocol (MCP). Enforces the use of FastMCP (Python) and @modelcontextprotocol/sdk (TypeScript). Mandates strict security guardrails and guidelines for stateful, real-time MCP servers.
Trigger Conditions
- Building an MCP server to expose tools, resources, or prompt templates to AI agents.
- Integrating APIs or Databases as MCP tools.
- Implementing stateful, real-time MCP servers (streaming, tailing logs, live dashboarding).
- Securing MCP servers exposing sensitive endpoints.
SDK Selection (Mandatory)
Use only the following official modern SDKs to build MCP servers:
- Python:
FastMCP(provides FastAPI-like developer experience for MCP). - TypeScript:
@modelcontextprotocol/sdk(standard JS/TS implementation).
Building Stateful, Real-Time MCP Servers
Modern agents demand real-time telemetry and stateful context.
- Streaming Data: Use MCP's streamable transports (like Streamable HTTP) or push-based resource updates to stream continuous data chunks to the client.
- Tailing Logs: Implement resources with dynamic URIs (e.g.,
logs://{service}/{tail}) and utilize resource subscriptions. When new logs append, emit resource update notifications to the client. - Live Dashboarding: Expose live metrics via resources. Use background workers to poll system state and push updates to the LLM UI or client agent via MCP notifications, keeping dashboard contexts fresh without manual polling.
Security Guardrails
Enforce these security mechanisms for any MCP server exposing sensitive APIs or Databases:
- OAuth Integration: Implement standard OAuth 2.0 / 2.1 authorization flows. Bind session tokens to the MCP transport layer. Never accept raw API keys over unencrypted channels.
- Strict Rate-Limiting: Apply token bucket or leaky bucket rate limiting per session/user. Prevent LLM looping from executing denial-of-service on upstream APIs.
- Row-Level Security (RLS): When querying databases directly, pass the authenticated user's identity to the database driver and enforce RLS at the database level. Never fetch all rows and filter in-memory.
- Input Validation: Use
zod(TS) orpydantic(Python) to strictly validate all tool arguments. Sanitize all LLM inputs to prevent prompt injection or SQL injection.
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.
- 7d ago First seen · 80 lines · 68 tokens per session scan A e7e05494f753
mcp-server-architect is a skill published in the GitHub repository roedyrustam/vibes-plug (50 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,366 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
component-identification-sizing
Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use…
evolutionary-modular-architecture
Guides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), flat-by-aggregate organization, an Anti-Corruption Layer for vendor independence, a transactional outbox for events, smart resilience (backoff with jitter, circuit breakers, idempotency), and a polished…
nestjs-modular-monolith
Specialist in designing and implementing scalable modular monolith architectures using NestJS with DDD, Clean Architecture, and CQRS patterns. Use when building modular monolith backends, designing bounded contexts, creating domain modules, implementing event-driven module communication, or when user mentions "modular…
rails-dev
Opinionated Rails conventions: rich models, concerns, CRUD-everything, state-as-records, minimal dependencies, Minitest with fixtures. Load this skill BEFORE any code-level thinking, not only before editing a file. It is required the moment a task touches Rails code in ANY way: designing or even just discussing a data…
modular-decomposition
Runs a sequenced monolith-to-modular pipeline that sizes and inventories components, finds shared domain duplication, addresses flattening and hierarchy issues, analyzes coupling, then groups components into candidate domain-aligned units, with optional embedded DDD strategic analysis for bounded contexts. Use when…