leanmcp-builder
Skill2.1k starsChanged 7 months agoMITView on GitHub
Build MCP servers using the Leanmcp SDK with decorator-based TypeScript. Use this skill when users ask for "leanmcp", "MCP with decorators", "MCP with authentication", "MCP with elicitation", "MCP with environment injection", or want a simpler, more elegant way to build MCP servers. Leanmcp provides automatic schema generation, dependency injection, authentication, and user input collection.
- Reads credentials
- Installs packages
- Sends data out
3 other projects use a version of this.
Trending
Quiet since April.thin dataabout the whole repository
Most recently taken up by
- Leanmcp/superview.shword for word, first seen Oct 13, 2026
- chatgptprojects/claude-codeword for word, first seen Oct 8, 2026
- Leanmcp/gateway-skillsword for word, first seen Oct 8, 2026
Who's talking about chatgptprojects/clear-code
- karthink/gptel-agent“The Claude Code source code has leaked, probably bringing a massive boost to open source projects such as …”GitHub · Mar 31, 2026 · 1 reactions
- ProSkillsMD/proskills“[SUBMISSION] clear-code”GitHub · Apr 20, 2026
The biggest 2 of 2 mentions linking to the repository that our crawl found. Each line is their own headline.
Other versions3 projects use a version of this.
Word for word · 3
- Leanmcp/superview.sh★ 2.1k100% same
- chatgptprojects/claude-code★ 2.1k100% same
- Leanmcp/gateway-skills★ 2.1k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- claude-code-devSkill
- analyze-exportsSkill
- code-explanationSkill
- fireworks-inferenceSkill
- godot-city-game-3dSkill
- ios-bootstrap-testflightSkill
- mcp-apps-builderSkill
- mcp-builderSkill
- posthog-adblock-bypassSkill
- publicity-distributionSkill
- research-observabilitySkill
- research-paper-integritySkill
- security-reproSkill
- tinker-training-inferenceSkill
- translate-explanationSkill
- vuln-reproSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 237
Add authentication to your service:
- Very specific: line 442
Add new services in mcp/servicename/index.ts
- Very specific: line 443
Use @Tool, @Resource, @Prompt decorators
- Very specific: line 444
Use @SchemaConstraint for input validation
- Very specific: line 445
Use @Optional() for optional fields
- Distinctive: line 447
Follow decorator patterns consistently
- Very specific: line 452
Use direct imports for components in @UIApp
- Distinctive: line 454
Add terminal/command instructions
- Distinctive: line 455
Remove existing working code
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Leanmcp Builder Skill
This skill guides you in building MCP servers using the Leanmcp SDK - a decorator-based TypeScript framework for elegant MCP development.
When to Use This Skill
- User asks for "leanmcp server"
- User wants "MCP with decorators"
- User needs "authenticated MCP server"
- User wants "simpler MCP development"
- User mentions "@leanmcp/core"
- User needs "user input collection" or "elicitation"
- User wants "environment injection" for multi-tenant secrets
Leanmcp vs Vanilla MCP
| Feature | Vanilla MCP | Leanmcp SDK |
| Tool definition | Manual schema | @Tool decorator with auto-schema |
| Input validation | Manual | Automatic with @SchemaConstraint |
| Service discovery | Manual registration | Auto-discovery from ./mcp directory |
| Authentication | DIY | @Authenticated decorator |
| User input | Not built-in | @Elicitation decorator |
| Secrets | DIY | @RequireEnv + getEnv() |
Core Packages
# Minimal setup
npm install @leanmcp/core
# With authentication
npm install @leanmcp/auth
# With user input forms
npm install @leanmcp/elicitation
# With user secrets
npm install @leanmcp/env-injection
# CLI (global or dev)
npm install -g @leanmcp/cliProject Structure
my-leanmcp-server/
├── main.ts # Entry point (minimal)
├── mcp/ # Auto-discovered services
│ ├── example/
│ │ └── index.ts # Exports ExampleService
│ └── myservice/
│ └── index.ts # Exports MyService
├── package.json
├── tsconfig.json
└── .envRequired package.json
{
"name": "my-leanmcp-server",
"version": "1.0.0",
"type": "module",
"scripts": {
"dev": "leanmcp dev",
"start": "leanmcp start",
"build": "leanmcp build"
},
"dependencies": {
"@leanmcp/core": "latest",
"dotenv": "^16.5.0"
},
"devDependencies": {
"@leanmcp/cli": "latest",
"@types/node": "^20.0.0",
"typescript": "^5.6.3"
}
}TypeScript Configuration
{
"compilerOptions": {
"experimentalDecorators": true,
"emitDecoratorMetadata": true,
"target": "ES2020",
"module": "ESNext",
"moduleResolution": "node",
"outDir": "./dist",
"strict": true,
"esModuleInterop": true
},
"include": ["**/*.ts"]
}Entry Point (main.ts)
import dotenv from 'dotenv';
import { createHTTPServer } from '@leanmcp/core';
dotenv.config();
// Services are automatically discovered from ./mcp directory
await createHTTPServer({
name: 'my-leanmcp-server',
version: '1.0.0',
port: 3001,
cors: true,
logging: true,
});@Tool Decorator
Marks a method as an MCP tool with automatic schema generation.
Basic Tool
import { Tool } from '@leanmcp/core';
export class MyService {
@Tool({ description: 'Echo a message back' })
async echo(args: { message: string }) {
return { echoed: args.message };
}
}Tool with Input Class (Recommended)
import { Tool, SchemaConstraint, Optional } from '@leanmcp/core';
class CalculateInput {
@SchemaConstraint({ description: 'First number', minimum: -1000000 })
a!: number;
@SchemaConstraint({ description: 'Second number', minimum: -1000000 })
b!: number;
@Optional()
@SchemaConstraint({
description: 'Operation to perform',
enum: ['add', 'subtract', 'multiply', 'divide'],
default: 'add'
})
operation?: string;
}
export class MathService {
@Tool({
description: 'Perform arithmetic operations',
inputClass: CalculateInput
})
async calculate(input: CalculateInput) {
const a = Number(input.a);
const b = Number(input.b);
switch (input.operation || 'add') {
case 'add': return { result: a + b };
case 'subtract': return { result: a - b };
case 'multiply': return { result: a * b };
case 'divide':
if (b === 0) throw new Error('Division by zero');
return { result: a / b };
default: throw new Error('Invalid operation');
}
}
}Tool Naming
Tool name is derived from the method name:
async calculate(...)-> tool name:calculateasync sendMessage(...)-> tool name:sendMessage
@Resource Decorator
import { Resource } from '@leanmcp/core';
export class InfoService {
@Resource({ description: 'Get server information' })
async serverInfo() {
return {
contents: [{
uri: 'server://info',
mimeType: 'application/json',
text: JSON.stringify({
name: 'my-server',
version: '1.0.0',
uptime: process.uptime()
})
}]
};
}
}@Prompt Decorator
import { Prompt } from '@leanmcp/core';
export class PromptService {
@Prompt({ description: 'Generate a greeting prompt' })
async greeting(args: { name?: string }) {
return {
messages: [{
role: 'user' as const,
content: {
type: 'text' as const,
text: `Hello ${args.name || 'there'}! Welcome to my server.`
}
}]
};
}
}@Authenticated Decorator
Add authentication to your service:
import { Tool } from '@leanmcp/core';
import { Authenticated, AuthProvider, authUser } from '@leanmcp/auth';
const authProvider = new AuthProvider('cognito', {
region: 'us-east-1',
userPoolId: 'us-east-1_XXXXXXXXX',
clientId: 'your-client-id'
});
await authProvider.init();
@Authenticated(authProvider)
export class SecureService {
@Tool({ description: 'Get user data' })
async getUserData() {
// authUser is automatically available
return {
userId: authUser.sub,
email: authUser.email
};
}
}Supported providers: AWS Cognito, Clerk, Auth0, Leanmcp
@Elicitation Decorator
Collect structured user input:
import { Tool } from '@leanmcp/core';
import { Elicitation } from '@leanmcp/elicitation';
export class ChannelService {
@Tool({ description: 'Create a new channel' })
@Elicitation({
title: 'Channel Details',
fields: [
{ name: 'channelName', label: 'Channel Name', type: 'text', required: true },
{ name: 'isPrivate', label: 'Private Channel', type: 'boolean', defaultValue: false },
{ name: 'topic', label: 'Topic', type: 'textarea' }
]
})
async createChannel(args: { channelName: string; isPrivate: boolean; topic?: string }) {
return { success: true, channel: args.channelName };
}
}Field types: text, textarea, number, boolean, select, multiselect, email, url, date
@RequireEnv Decorator
Inject user-specific secrets:
import { Tool } from '@leanmcp/core';
import { Authenticated } from '@leanmcp/auth';
import { RequireEnv, getEnv } from '@leanmcp/env-injection';
@Authenticated(authProvider, { projectId: 'my-project' })
export class SlackService {
@Tool({ description: 'Send Slack message' })
@RequireEnv(['SLACK_TOKEN', 'SLACK_CHANNEL'])
async sendMessage(args: { message: string }) {
const token = getEnv('SLACK_TOKEN')!;
const channel = getEnv('SLACK_CHANNEL')!;
await fetch('https://slack.com/api/chat.postMessage', {
method: 'POST',
headers: {
'Authorization': `Bearer ${token}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({ channel, text: args.message })
});
return { success: true };
}
}Complete Service Example
// mcp/products/index.ts
import { Tool, Resource, SchemaConstraint, Optional } from '@leanmcp/core';
class CreateProductInput {
@SchemaConstraint({ description: 'Product name', minLength: 1 })
name!: string;
@SchemaConstraint({ description: 'Price in dollars', minimum: 0 })
price!: number;
@Optional()
@SchemaConstraint({ description: 'Product description' })
description?: string;
}
class UpdateProductInput {
@SchemaConstraint({ description: 'Product ID' })
id!: string;
@Optional()
@SchemaConstraint({ description: 'Product name' })
name?: string;
@Optional()
@SchemaConstraint({ description: 'Price in dollars', minimum: 0 })
price?: number;
}
export class ProductsService {
private products: Map<string, any> = new Map();
@Tool({ description: 'Create a new product', inputClass: CreateProductInput })
async createProduct(input: CreateProductInput) {
const id = crypto.randomUUID();
const product = { id, ...input, createdAt: new Date().toISOString() };
this.products.set(id, product);
return { success: true, product };
}
@Tool({ description: 'List all products' })
async listProducts() {
return { products: Array.from(this.products.values()) };
}
@Tool({ description: 'Update a product', inputClass: UpdateProductInput })
async updateProduct(input: UpdateProductInput) {
const product = this.products.get(input.id);
if (!product) throw new Error('Product not found');
if (input.name) product.name = input.name;
if (input.price) product.price = input.price;
product.updatedAt = new Date().toISOString();
return { success: true, product };
}
@Tool({ description: 'Delete a product' })
async deleteProduct(args: { id: string }) {
if (!this.products.has(args.id)) throw new Error('Product not found');
this.products.delete(args.id);
return { success: true };
}
@Resource({ description: 'Get product statistics' })
async productStats() {
const products = Array.from(this.products.values());
return {
contents: [{
uri: 'products://stats',
mimeType: 'application/json',
text: JSON.stringify({
total: products.length,
totalValue: products.reduce((sum, p) => sum + p.price, 0)
})
}]
};
}
}Server Configuration Options
import { MCPServer, createHTTPServer } from '@leanmcp/core';
// Simple API (recommended)
await createHTTPServer({
name: 'my-server',
version: '1.0.0',
port: 3001,
cors: true,
logging: true
});
// Advanced: Factory pattern with manual registration
const serverFactory = async () => {
const server = new MCPServer({
name: 'my-server',
version: '1.0.0',
autoDiscover: false, // Disable auto-discovery
logging: true
});
server.registerService(new MyService());
return server.getServer();
};
await createHTTPServer(serverFactory, {
port: 3001,
cors: true
});Editing Guidelines
DO
- Add new services in
mcp/servicename/index.ts - Use
@Tool,@Resource,@Promptdecorators - Use
@SchemaConstraintfor input validation - Use
@Optional()for optional fields - Export service classes from index.ts
- Follow decorator patterns consistently
DON'T
- Wrap services in AppProvider (CLI handles this)
- Use direct imports for components in
@UIApp - Completely rewrite existing files
- Add terminal/command instructions
- Remove existing working code
Error Handling
@Tool({ description: 'Divide two numbers' })
async divide(input: { a: number; b: number }) {
if (input.b === 0) {
throw new Error('Division by zero is not allowed');
}
return { result: input.a / input.b };
}Errors are automatically caught and formatted as MCP error responses.
Best Practices
- Always provide descriptions - Helps LLMs understand tool purpose
- Use inputClass for complex inputs - Automatic schema generation
- Return structured data - Objects with clear field names
- Handle errors gracefully - Throw descriptive errors
- Keep tools focused - One tool = one clear action
- Organize by domain - One service per business domain
- Use schema constraints - Validate inputs with min/max/enum
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

