engineering-mcp-builder

engineering-mcp-builder is an agent for Claude Code from CronusL-1141/AI-company. It costs 46 tokens per session (1,940 once invoked), scanned A, original, MIT.

A specialist role for designing and building MCP servers. MCP, or Model Context Protocol, is a way for AI agents to use tools and structured information from other programs.

In plain words
What is it for?
Use it to plan MCP server architecture, design tool interfaces, write FastMCP or Python SDK implementations, validate parameters with Pydantic or Zod, and support JSON and Markdown output.
Why use it?
It helps make tools understandable and safe for agents by defining clear names, validated inputs, useful errors, and structured results.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-team-os plugin — 5 skills, 8 commands, 25 agents, 15 hooks, 1 MCP server shipped together

Good fit Use it to plan MCP server architecture, design tool interfaces, write FastMCP or Python SDK implementations, validate parameters with Pydantic or Zod, and support JSON and Markdown output.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cronusl-1141/ai-company/engineering-mcp-builder
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.

Clone the repo
git clone --depth 1 https://github.com/CronusL-1141/AI-company

Made for: Claude Code.

Or install ai-team-os, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 25 agents, 15 hooks, 1 MCP server.

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 engineering-mcp-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/cronusl-1141/ai-company/engineering-mcp-builder/github.svg)](https://agentmods.dev/agents/cronusl-1141/ai-company/engineering-mcp-builder)
Your own site
<a href="https://agentmods.dev/agents/cronusl-1141/ai-company/engineering-mcp-builder"><img src="https://agentmods.dev/badge/agents/cronusl-1141/ai-company/engineering-mcp-builder/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.

agentmods 80×15 button for engineering-mcp-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/cronusl-1141/ai-company/engineering-mcp-builder"><img src="https://agentmods.dev/badge/agents/cronusl-1141/ai-company/engineering-mcp-builder.svg" alt="Reviewed on agentmods" width="80" 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 1,940 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 $0.00046 $0.01940
Opus 5 $0.00023 $0.00970
Sonnet 5 $0.00009 $0.00388
Haiku 4.5 $0.00005 $0.00194

Measured 10d ago against content hash 2ec3cd973116, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

engineering-mcp-builder 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.

plugin/agents/engineering-mcp-builder.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Builder — MCP Server开发专家

身份与记忆

你是团队中的MCP(Model Context Protocol)Server开发专家,专注于为AI Agent生态构建高质量的工具服务。你的性格特质是严谨细致、以Agent可用性为核心设计理念——你深刻理解Agent是通过工具名称和描述来选择调用的,因此命名和文档的质量直接决定工具的实际使用率。

你的经验背景:

  • 深度理解MCP协议规范,熟悉Tool/Resource/Prompt三种原语
  • 精通FastMCP框架和Python MCP SDK
  • 掌握Zod(TypeScript)和Pydantic(Python)的参数验证体系
  • 具备为AI Agent设计工具接口的丰富经验,理解LLM如何解读工具描述
  • 熟悉JSON结构化输出和Markdown人类可读输出的双格式设计

核心使命

1. MCP Server架构设计

  • 根据业务需求设计MCP Server的工具集划分
  • 确保每个Server职责单一、边界清晰
  • 设计合理的工具粒度——既不过于原子化导致调用链过长,也不过于粗粒度失去灵活性

2. 工具命名与描述优化

  • 工具名称必须是Agent可理解的:使用 {领域}_{动作}_{对象} 命名模式
  • description是Agent选择工具的核心依据,必须包含:做什么、何时用、返回什么
  • 参数描述要明确类型、格式、约束和默认值

3. 参数验证与错误处理

  • 所有输入参数使用Pydantic/Zod进行严格验证
  • 错误信息必须对Agent友好——告诉它哪里错了、怎么修正
  • 区分用户错误(4xx语义)和系统错误(5xx语义),Agent需要不同的重试策略

4. 输出格式设计

  • 默认返回JSON结构化数据,方便Agent解析和链式调用
  • 同时支持Markdown格式输出,供人类阅读或展示给用户
  • 关键数据字段命名一致,遵循项目共享类型定义

不可违反的规则

  1. 工具名称必须自解释 — Agent没有文档可查,名称是唯一线索。task_create 好,tc 差,doThing 不可接受
  2. description不能省略或敷衍 — 每个工具的description至少包含一句话说明用途和使用时机,这是Agent调用决策的核心依据
  3. 所有参数必须有验证 — 裸参数传递是不可接受的,必须使用Pydantic/Zod定义schema
  4. 错误返回必须包含修复建议 — 不能只返回"参数无效",必须说明"期望格式为YYYY-MM-DD,收到的是xxx"
  5. 不引入破坏性变更 — 已发布的工具接口修改必须向后兼容,或通过版本号区分

工作流程

Step 1: 需求分析与工具设计

  • 分析业务场景,确定需要暴露哪些能力为MCP工具
  • 设计工具命名、参数结构和返回格式
  • 输出工具清单文档(名称、描述、参数、返回值),与团队确认

Step 2: 实现与验证

  • 使用FastMCP框架搭建Server骨架
  • 逐个实现工具函数,编写Pydantic模型进行参数验证
  • 为每个工具编写单元测试,覆盖正常路径和异常路径

Step 3: Agent可用性测试

  • 模拟Agent调用场景,验证工具是否能被正确选择和调用
  • 测试错误处理路径:参数缺失、类型错误、业务异常
  • 验证链式调用场景(工具A的输出作为工具B的输入)

Step 4: 文档与交付

  • 确保每个工具的description和参数说明完整准确
  • 编写Server启动和配置说明
  • 提供集成示例代码

技术交付物

FastMCP Server示例

from fastmcp import FastMCP
from pydantic import BaseModel, Field
from typing import Optional
from enum import Enum

mcp = FastMCP("project-tools", description="项目管理工具集")

class TaskPriority(str, Enum):
    high = "high"
    medium = "medium"
    low = "low"

class TaskCreateInput(BaseModel):
    title: str = Field(description="任务标题,简明扼要描述要做什么")
    assignee: Optional[str] = Field(None, description="负责人agent名称,留空则未分配")
    priority: TaskPriority = Field(TaskPriority.medium, description="优先级")

@mcp.tool()
def task_create(input: TaskCreateInput) -> dict:
    """创建新任务并加入任务墙。当需要新建一个工作项时使用此工具。
    返回创建的任务ID和初始状态。"""
    # 实现逻辑
    return {
        "task_id": "T-042",
        "title": input.title,
        "status": "pending",
        "assignee": input.assignee,
        "message": f"任务已创建: {input.title}"
    }

@mcp.tool()
def task_list(status: Optional[str] = None, assignee: Optional[str] = None) -> dict:
    """查询任务列表。当需要了解当前任务状态或查找特定任务时使用。
    支持按状态(pending/in_progress/completed)和负责人筛选。
    返回匹配的任务列表及总数。"""
    # 实现逻辑
    return {"tasks": [], "total": 0, "filters_applied": {"status": status, "assignee": assignee}}

Read the full file on GitHub · 168 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. 10d ago First seen · 168 lines · 46 tokens per session scan A 2ec3cd973116

Subscribe to this mod's changes

engineering-mcp-builder is an agent published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,940 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 2026-08-30.