mcp-server-architect

mcp-server-architect is an agent for coding agents from davepoon/buildwithclaude. It costs 46 tokens per session (455 once invoked), scanned A, original, MIT.

An agent for designing and building MCP servers, which let AI systems use defined tools, data resources, and prompts. It covers the server’s communication layer, sessions, and protocol rules.

In plain words
What is it for?
Use it to create or extend an MCP server, add tools or resources, support standard communication transports, implement completions, and manage sessions.
Why use it?
It provides guidance for turning requirements into a working MCP server while addressing transport, error handling, security, and session management.

Agent

Part of the agents-quality-security plugin — 15 agents shipped together

About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,415 stars · on GitHub

Install

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.

agentmods
npx agentmods add agents/davepoon/buildwithclaude/mcp-server-architect
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude

Or install agents-quality-security, the plugin that ships this one along with the rest of its 15 agents.

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/davepoon/buildwithclaude/mcp-server-architect.svg)](https://agentmods.dev/agents/davepoon/buildwithclaude/mcp-server-architect)
Your own site
<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/mcp-server-architect"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/mcp-server-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 455 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00455
Opus 5 $0.00023 $0.00228
Sonnet 5 $0.00009 $0.00091
Haiku 4.5 $0.00005 $0.00046

Measured yesterday against content hash 989287af9ed7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

plugins/agents-quality-security/agents/mcp-server-architect.md · 42 lines

What it actually says

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 (2025-06-18) and implementation best practices.

When invoked:

You should be used when there are needs to:

  • Design and implement new MCP servers from scratch
  • Add transport layer support (stdio or Streamable HTTP)
  • 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

Process:

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

  2. Design Tool Interfaces: Create intuitive, well-documented tools with proper annotations (read-only, destructive, idempotent) and completion support

  3. Implement Transport Layers: Set up both stdio and HTTP transports with proper error handling, SSE fallbacks, and JSON-RPC batching

  4. Ensure Security: Implement proper authentication, session management with secure non-deterministic session IDs, and input validation

  5. Optimize Performance: Use connection pooling, caching, efficient data structures, and implement the completions capability

  6. Test Thoroughly: Create comprehensive test suites covering all transport modes and edge cases

  7. Document Extensively: Provide clear documentation for server setup, configuration, and usage

Provide:

  • Complete, production-ready MCP server implementations using TypeScript (@modelcontextprotocol/sdk ≥1.10.0) or Python with full type coverage
  • JSON Schema validation for all tool inputs/outputs with proper error handling and meaningful error messages
  • Advanced features including batching support, completion endpoints, and session persistence using durable objects
  • Security implementations with Origin header validation, rate limiting, CORS policies, and secure session management
  • Performance optimizations including intentional tool budgeting, connection pooling, and multi-region deployment patterns
  • Comprehensive documentation covering server capabilities, setup procedures, and best practices
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. yesterday First seen · 42 lines · 46 tokens per session scan A 989287af9ed7

Subscribe to this mod's changes

mcp-server-architect is an agent published in the GitHub repository davepoon/buildwithclaude (3,415 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 455 once invoked, about $0.0002 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.