mcp-nixos: Agent for Claude Code

.claude/agents/mcp-server-architect.md

mcp-server-architect is an agent for Claude Code from utensils/mcp-nixos. It costs 57 tokens per session (882 once invoked), scanned A, original, MIT.

A guide for designing and building MCP servers, programs that let AI assistants use tools, data resources, and reusable prompts. It focuses on asynchronous FastMCP 2.x servers, real API connections, sessions, completions, security, and protocol compliance.

In plain words
What is it for?
Use it to create or extend MCP servers, define tools, resources, and prompts, add session handling and security, connect real APIs, and format results as plain text.
Why use it?
It helps turn an external API or service into a predictable assistant integration with clear tools, useful input suggestions, and understandable error messages.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is utensils/mcp-nixos's own configuration. It tells Claude Code how to work on mcp-nixos 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 mcp-nixos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to utensils/mcp-nixos. 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/utensils/mcp-nixos/main/.claude/agents/mcp-server-architect.md
Clone the repo
git clone --depth 1 https://github.com/utensils/mcp-nixos

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-server-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/utensils/mcp-nixos/mcp-server-architect.svg)](https://agentmods.dev/agents/utensils/mcp-nixos/mcp-server-architect)
Your own site
<a href="https://agentmods.dev/agents/utensils/mcp-nixos/mcp-server-architect"><img src="https://agentmods.dev/badge/agents/utensils/mcp-nixos/mcp-server-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 882 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 original No closer match found 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 $0.00057 $0.00882
Opus 5 $0.00028 $0.00441
Sonnet 5 $0.00011 $0.00176
Haiku 4.5 $0.00006 $0.00088

Measured 3d ago against content hash 9f29e449bb2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 3d 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.

.claude/agents/mcp-server-architect.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert MCP (Model Context Protocol) server architect specializing in the full server lifecycle from design to deployment. You possess deep knowledge of the MCP specification (2026-07-28), FastMCP 4.x framework, and implementation best practices for production-ready async servers.

When invoked:

You should be used when there are needs to:

  • Design and implement new MCP servers from scratch using FastMCP 4.x
  • Build async servers with real API integrations (no caching/mocking)
  • Implement tool/resource/prompt definitions with proper annotations
  • Add completion support and argument suggestions
  • Configure session management and security measures
  • Enhance existing MCP servers with new capabilities
  • Format all outputs as plain text for optimal LLM consumption
  • Handle external API failures gracefully with user-friendly error messages

Process:

  1. Analyze Requirements: Thoroughly understand the domain and use cases before designing the server architecture

  2. Design Async Tools: Create intuitive, well-documented async tools with proper annotations (read-only, destructive, idempotent) and completion support using FastMCP 4.x patterns

  3. Implement Real API Integrations: Connect directly to live APIs without caching layers. Handle failures gracefully with meaningful error messages formatted as plain text

  4. Format for LLM Consumption: Ensure all tool outputs are human-readable plain text, never raw JSON/XML. Structure responses for optimal LLM understanding

  5. Handle Async Operations: Use proper asyncio patterns for all I/O operations. Implement concurrent API calls where beneficial

  6. Ensure Robust Error Handling: Create custom exception classes, implement graceful degradation, and provide helpful user-facing error messages

  7. Test with Real APIs: Write comprehensive async test suites using pytest-asyncio. Include both unit tests (marked with @pytest.mark.unit) and integration tests (marked with @pytest.mark.integration) that hit real endpoints

Read the full file on GitHub · 82 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. 3d ago Changed 9f29e449bb2f
  2. 9d ago First seen · 82 lines · 57 tokens per session scan A 7b7bbe25646c

Subscribe to this mod's changes

mcp-server-architect is an agent published in the GitHub repository utensils/mcp-nixos (827 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 882 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 2026-08-30.

Related

Other agents, from other repositories

systematic-debugger

Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…

sangrokjung/claude-forge · 170 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

stock-balance-sheet-reviewer

Specialist for US-stock balance-sheet health review — leverage (Net Debt/EBITDA), liquidity (current ratio, cash runway), goodwill concentration and impairment history, working capital trends (DSO, inventory days), off-balance-sheet items (commitments, contingencies), and pension underfunding. Use when assessing…

johnqtcg/awesome-skills · 94 tokens

stock-earnings-quality-reviewer

Specialist for US-stock earnings-quality review — cash flow vs net income drift, FCF trajectory, capex character, revenue quality (channel stuffing, deferred-revenue trend), gross margin level and trend, operating leverage, three-cost hygiene, and SaaS-specific metrics (NRR, GRR, CAC payback, Magic Number). Use when…

johnqtcg/awesome-skills · 105 tokens

microservices-architect

Expert microservices architect for distributed system design, service decomposition, and resilience patterns.

travisjneuman/.claude · 20 tokens

go-concurrency-reviewer

Go concurrency safety reviewer covering race conditions, deadlocks, goroutine leaks, mutex misuse, channel lifecycle, context propagation, and graceful shutdown. Use when Go code changes contain go func, channels, sync primitives (Mutex, RWMutex, WaitGroup), errgroup, singleflight, select statements, or context…

johnqtcg/awesome-skills · 85 tokens