跳到正文
cccskills
免费在 GitHub 公开

mcp-server-development

Expert guidance for building MCP (Model Context Protocol) servers using the TypeScript SDK. Use when developing MCP servers, implementing tools/resources/prompts, or working with the @modelcontextprotocol/sdk package. Covers server initialization, request handlers, Zod schemas, error handling, and JSON-RPC patterns.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md5.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

This skill provides comprehensive guidance for building robust MCP servers, with specific focus on the unity-mcp-server architecture and patterns.

Core Philosophy

MCP servers bridge AI assistants to external systems. They must be:

  • Reliable: Handle errors gracefully, never crash unexpectedly
  • Discoverable: Tools should have clear, self-documenting schemas
  • Performant: Minimize latency, especially for stdio transport
  • Protocol-compliant: Follow JSON-RPC 2.0 and MCP spec exactly

Architecture Patterns

Handler-Based Design

ALWAYS use a handler class per tool. Each handler encapsulates:

  • Input validation (Zod schema)
  • Business logic execution
  • Error handling and response formatting
// Pattern: One handler per tool
export class SystemPingToolHandler extends BaseToolHandler {
  constructor(unityConnection) {
    super({
      name: 'system_ping',
      description: 'Check Unity Editor connectivity',
      inputSchema: { type: 'object', properties: {} }
    });
    this.unityConnection = unityConnection;
  }

  async execute(params) {
    const result = await this.unityConnection.send({ command: 'ping' });
    return { status: 'ok', ...result };
  }
}

BaseToolHandler Contract

All handlers MUST:

  1. Call super() with tool metadata
  2. Implement execute(params) method
  3. Return plain objects (framework handles JSON-RPC wrapping)
  4. Throw errors with descriptive messages

Input Validation with Zod

ALWAYS validate inputs before processing:

import { z } from 'zod';

const inputSchema = z.object({
  name: z.string().min(1).describe('GameObject name'),
  primitiveType: z.enum(['cube', 'sphere', 'cylinder']).optional()
});

validate(input) {
  return inputSchema.parse(input);
}

Transport Layer

Content-Length Framing (Standard)

MCP uses LSP-style Content-Length framing for stdio:

Content-Length: 123\r\n
\r\n
{"jsonrpc":"2.0","id":1,"method":"tools/call"...}

ALWAYS use Content-Length for output. NEVER mix framing formats in a session.

Hybrid Input (Compatibility)

Accept both Content-Length and NDJSON input for client compatibility:

  • Claude Desktop: Content-Length
  • Some CLI tools: NDJSON (newline-delimited)

Error Handling

Structured Errors

Use MCP error codes from the spec:

const McpError = {
  ParseError: -32700,
  InvalidRequest: -32600,
  MethodNotFound: -32601,
  InvalidParams: -32602,
  InternalError: -32603
};

throw new Error(JSON.stringify({
  code: McpError.InvalidParams,
  message: 'primitiveType must be one of: cube, sphere, cylinder'
}));

Error Response Format

{
  jsonrpc: '2.0',
  id: requestId,
  error: {
    code: -32602,
    message: 'Invalid params',
    data: { field: 'name', issue: 'required' }
  }
}

Unity-Specific Patterns

Command Protocol

Unity communication uses a simple request/response pattern:

const result = await this.unityConnection.send({
  command: 'gameobject_create',
  params: { name: 'Cube', primitiveType: 'cube' }
});

Workspace Root Resolution

ALWAYS include workspaceRoot in commands requiring file paths:

execute(params) {
  return this.unityConnection.send({
    command: 'screenshot_capture',
    workspaceRoot: config.workspaceRoot,
    ...params
  });
}

Testing Patterns

TDD for Handlers

  1. Contract test first: Define expected input/output schema
  2. Mock Unity connection: Isolate handler logic
  3. Test error paths: Invalid input, connection failures
  4. Test happy path last: After contracts are verified
describe('CreateGameObjectHandler', () => {
  it('validates primitiveType enum', async () => {
    const handler = new CreateGameObjectHandler(mockConnection);
    await assert.rejects(
      () => handler.handle({ name: 'Cube', primitiveType: 'invalid' }),
      /primitiveType must be one of/
    );
  });
});

Integration Testing

Test full request/response cycle including JSON-RPC framing:

const stdin = new PassThrough();
const stdout = new PassThrough();
const transport = new HybridStdioServerTransport(stdin, stdout);

stdin.write('Content-Length: 50\r\n\r\n{"jsonrpc":"2.0","id":1,"method":"ping"}');
// Assert stdout contains Content-Length response

Common Mistakes

Mixing framing formats:

  • NEVER: Output NDJSON after receiving Content-Length input
  • ALWAYS: Output Content-Length regardless of input format

Swallowing errors:

  • NEVER: catch (e) { return null; }
  • ALWAYS: Propagate errors with context

Missing validation:

  • NEVER: Trust raw input from clients
  • ALWAYS: Validate with Zod before processing

Blocking stdio:

  • NEVER: Synchronous operations on transport
  • ALWAYS: Use async/await throughout

Handler Registration

Register all handlers in a central index:

// src/handlers/index.js
export function createHandlers(unityConnection) {
  return [
    new SystemPingToolHandler(unityConnection),
    new CreateGameObjectHandler(unityConnection),
    new ScreenshotHandler(unityConnection),
    // ...
  ];
}

Remember

  • Content-Length always: Output framing must be consistent
  • Validate everything: Never trust client input
  • One handler, one tool: Keep handlers focused
  • Test error paths: Most bugs hide in error handling
  • Protocol compliance: Follow JSON-RPC 2.0 exactly

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

drawio

免费

Create and edit draw.io diagrams in XML format. Use when the user wants to create flowcharts, architecture diagrams, sequence diagrams, or any visual diagrams. Handles XML structure, styling, fonts (Noto Sans JP), arrows, connectors, and PNG export.

中文简介正在准备中。当前显示原文说明。

akiojin/llmlb102026年10月18日 更新

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

中文简介正在准备中。当前显示原文说明。

akiojin/llmlb102026年10月18日 更新

Inspect GitHub PR for CI failures, merge conflicts, update-branch requirements, reviewer comments, change requests, and unresolved review threads. Create fix plans and implement after user approval. Reply to ALL reviewer comments with action taken or reason for not addressing, then resolve threads. Notify reviewers after fixes.

中文简介正在准备中。当前显示原文说明。

akiojin/llmlb102026年10月18日 更新

gwt-pr

免费

Create or update GitHub Pull Requests with the gh CLI, including deciding whether to create a new PR or only push based on existing PR merge status. Use when the user asks to open/create/edit a PR, generate a PR body/template, or says 'open a PR/create a PR/gh pr'. Defaults: base=develop, head=current branch (same-branch only; never create/switch branches).

中文简介正在准备中。当前显示原文说明。

akiojin/llmlb102026年10月18日 更新

Check GitHub PR status with the gh CLI, including unmerged PR detection and post-merge new-commit detection for the current branch.

中文简介正在准备中。当前显示原文说明。

akiojin/llmlb102026年10月18日 更新

Semantic search over project source files using vector embeddings. Use to find files related to a feature, bug, or concept.

中文简介正在准备中。当前显示原文说明。

akiojin/llmlb102026年10月18日 更新

查看 akiojin 的全部技能

报告此技能的问题