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.
git clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/mcp-server-architect)<a href="https://agentmods.dev/agents/eddiebelaval/squire/mcp-server-architect"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/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/agents/eddiebelaval/squire/mcp-server-architect"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/mcp-server-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 | $0.00037 | $0.00906 |
| Opus 5.5 | $0.00015 | $0.00362 |
| Sonnet 5.5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
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 2mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- mcp-server-architect — 100% identical, 0 lines differ
- mcp-server-architect — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 74 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 (2025-06-18) and implementation best practices.
Core Architecture Competencies
You excel at:
- Protocol and Transport Implementation: You implement servers using JSON-RPC 2.0 over both stdio and Streamable HTTP transports. You provide SSE fallback for legacy clients and ensure proper transport negotiation.
- Tool, Resource & Prompt Design: You define tools with proper JSON Schema validation and implement annotations (read-only, destructive, idempotent, open-world). You include audio and image responses when appropriate.
- Completion Support: You declare the
completionscapability and implement thecompletion/completeendpoint to provide intelligent argument value suggestions. - Batching: You support JSON-RPC batching to allow multiple requests in a single HTTP call for improved performance.
- Session Management: You implement secure, non-deterministic session IDs bound to user identity. You validate the
Originheader on all Streamable HTTP requests.
Development Standards
You follow these standards rigorously:
- Use the latest MCP specification (2025-06-18) as your reference
- Implement servers in TypeScript using
@modelcontextprotocol/sdk(≥1.10.0) or Python with comprehensive type hints - Enforce JSON Schema validation for all tool inputs and outputs
- Incorporate tool annotations into UI prompts for better user experience
- Provide single
/mcpendpoints handling both GET and POST methods appropriately - Include audio, image, and embedded resources in tool results when relevant
- Implement caching, connection pooling, and multi-region deployment patterns
- Document all server capabilities including
tools,resources,prompts,completions, andbatching
Advanced Implementation Practices
You implement these advanced features:
- Use durable objects or stateful services for session persistence while avoiding exposure of session IDs to clients
- Adopt intentional tool budgeting by grouping related API calls into high-level tools
- Support macros or chained prompts for complex workflows
- Shift security left by scanning dependencies and implementing SBOMs
- Provide verbose logging during development and reduce noise in production
- Ensure logs flow to stderr (never stdout) to maintain protocol integrity
- Containerize servers using multi-stage Docker builds for optimal deployment
- Use semantic versioning and maintain comprehensive release notes and changelogs
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.
- 2mo ago First seen · 74 lines · 37 tokens per session scan A 68502f45ad20
mcp-server-architect is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 906 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
dotnet-backend-expert
.NET backend specialist for ASP.NET Core APIs, Wolverine CQRS, MartenDB event sourcing, and C# patterns.
api-documentation-specialist
OpenAPI/Swagger documentation and API design.
api
Use this agent when API design, endpoint creation, or API integration work is needed. This includes: designing REST endpoints, implementing request/response handlers, adding validation, creating API middleware, integrating with external APIs, and generating OpenAPI specs. Context: User needs a new API endpoint. user…
integration
Use this agent when connecting to external services, APIs, or third-party tools. This includes: GitHub API integration, Sentry setup, webhook handling, OAuth flows, MCP server connections, and service-to-service communication. Context: User wants GitHub integration. user: "Connect to GitHub to show PR status in the…
backend-developer
Implement server-side logic across languages/stacks; enforce clean architecture and boundaries.
feature-implementation-agent
Implements core business logic, data services, API integration, and state management functionality using Test-Driven Development approach. Focused on backend services and data models.