mcp-server-builder
Builds Model Context Protocol (MCP) servers for Claude with tools, resources, and prompts. Use when users request "create MCP server", "build Claude tool", "MCP integration", or "custom Claude tools".
What this skill does
# MCP Server Builder
Create Model Context Protocol servers to extend Claude's capabilities with custom tools and resources.
## Core Workflow
1. **Define purpose**: Identify what capabilities to add
2. **Choose transport**: stdio (local) or HTTP/SSE (remote)
3. **Design tools**: Define tool schemas and handlers
4. **Add resources**: Optional file/data access
5. **Create prompts**: Optional reusable prompts
6. **Test locally**: Verify with MCP inspector
7. **Deploy**: Configure for Claude Desktop or API
## MCP Architecture Overview
```
┌─────────────┐ MCP Protocol ┌─────────────┐
│ Claude │◄────────────────────►│ MCP Server │
│ (Host) │ JSON-RPC over stdio │ (Your App) │
└─────────────┘ └─────────────┘
│
▼
┌───────────┐
│ Tools │
│ Resources │
│ Prompts │
└───────────┘
```
## Project Setup
### TypeScript MCP Server
```bash
# Create project
mkdir my-mcp-server && cd my-mcp-server
npm init -y
# Install dependencies
npm install @modelcontextprotocol/sdk zod
# Dev dependencies
npm install -D typescript @types/node tsx
```
```json
// package.json
{
"name": "my-mcp-server",
"version": "1.0.0",
"type": "module",
"main": "dist/index.js",
"bin": {
"my-mcp-server": "./dist/index.js"
},
"scripts": {
"build": "tsc",
"dev": "tsx watch src/index.ts",
"start": "node dist/index.js"
}
}
```
```json
// tsconfig.json
{
"compilerOptions": {
"target": "ES2022",
"module": "NodeNext",
"moduleResolution": "NodeNext",
"outDir": "./dist",
"rootDir": "./src",
"strict": true,
"esModuleInterop": true,
"skipLibCheck": true,
"declaration": true
},
"include": ["src/**/*"]
}
```
## Basic Server Structure
```typescript
// src/index.ts
#!/usr/bin/env node
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
CallToolRequestSchema,
ListToolsRequestSchema,
ListResourcesRequestSchema,
ReadResourceRequestSchema,
ListPromptsRequestSchema,
GetPromptRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";
// Create server instance
const server = new Server(
{
name: "my-mcp-server",
version: "1.0.0",
},
{
capabilities: {
tools: {},
resources: {},
prompts: {},
},
}
);
// Define tools
const TOOLS = [
{
name: "get_weather",
description: "Get current weather for a location",
inputSchema: {
type: "object" as const,
properties: {
location: {
type: "string",
description: "City name or coordinates",
},
units: {
type: "string",
enum: ["celsius", "fahrenheit"],
default: "celsius",
},
},
required: ["location"],
},
},
{
name: "search_database",
description: "Search the internal database",
inputSchema: {
type: "object" as const,
properties: {
query: {
type: "string",
description: "Search query",
},
limit: {
type: "number",
default: 10,
},
},
required: ["query"],
},
},
];
// List tools handler
server.setRequestHandler(ListToolsRequestSchema, async () => {
return { tools: TOOLS };
});
// Call tool handler
server.setRequestHandler(CallToolRequestSchema, async (request) => {
const { name, arguments: args } = request.params;
switch (name) {
case "get_weather": {
const { location, units = "celsius" } = args as {
location: string;
units?: string;
};
// Implement your logic here
const weather = await fetchWeather(location, units);
return {
content: [
{
type: "text",
text: JSON.stringify(weather, null, 2),
},
],
};
}
case "search_database": {
const { query, limit = 10 } = args as { query: string; limit?: number };
const results = await searchDatabase(query, limit);
return {
content: [
{
type: "text",
text: JSON.stringify(results, null, 2),
},
],
};
}
default:
throw new Error(`Unknown tool: ${name}`);
}
});
// Start server
async function main() {
const transport = new StdioServerTransport();
await server.connect(transport);
console.error("MCP Server running on stdio");
}
main().catch(console.error);
// Helper functions (implement your logic)
async function fetchWeather(location: string, units: string) {
// Your implementation
return { location, temperature: 22, units, condition: "sunny" };
}
async function searchDatabase(query: string, limit: number) {
// Your implementation
return { query, results: [], total: 0 };
}
```
## Tools
### Tool Schema Definition
```typescript
// src/tools/index.ts
import { z } from "zod";
// Define input schemas with Zod for validation
export const GetWeatherSchema = z.object({
location: z.string().describe("City name or coordinates"),
units: z.enum(["celsius", "fahrenheit"]).default("celsius"),
});
export const SearchSchema = z.object({
query: z.string().min(1).describe("Search query"),
filters: z
.object({
category: z.string().optional(),
dateFrom: z.string().optional(),
dateTo: z.string().optional(),
})
.optional(),
limit: z.number().min(1).max(100).default(10),
});
// Convert Zod schema to JSON Schema for MCP
export function zodToJsonSchema(schema: z.ZodObject<any>) {
// Use zod-to-json-schema package in production
return schema;
}
```
### Tool Handler Pattern
```typescript
// src/tools/handlers.ts
import { z } from "zod";
type ToolHandler<T extends z.ZodSchema> = (
args: z.infer<T>
) => Promise<{ content: Array<{ type: string; text: string }> }>;
export function createToolHandler<T extends z.ZodSchema>(
schema: T,
handler: (args: z.infer<T>) => Promise<any>
): ToolHandler<T> {
return async (rawArgs) => {
// Validate input
const args = schema.parse(rawArgs);
// Execute handler
const result = await handler(args);
// Format response
return {
content: [
{
type: "text",
text: typeof result === "string" ? result : JSON.stringify(result, null, 2),
},
],
};
};
}
// Usage
export const handleGetWeather = createToolHandler(
GetWeatherSchema,
async ({ location, units }) => {
const response = await fetch(
`https://api.weather.com/v1/current?location=${location}&units=${units}`
);
return response.json();
}
);
```
## Resources
### Static Resources
```typescript
// src/resources/index.ts
const RESOURCES = [
{
uri: "config://app-settings",
name: "Application Settings",
description: "Current application configuration",
mimeType: "application/json",
},
{
uri: "file://docs/readme",
name: "Documentation",
description: "Project documentation",
mimeType: "text/markdown",
},
];
// List resources handler
server.setRequestHandler(ListResourcesRequestSchema, async () => {
return { resources: RESOURCES };
});
// Read resource handler
server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
const { uri } = request.params;
switch (uri) {
case "config://app-settings":
return {
contents: [
{
uri,
mimeType: "application/json",
text: JSON.stringify(getAppSettings(), null, 2),
},
],
};
case "file://docs/readme":
const content = await fs.readFile("./README.md", "utf-8");
return {
contents: [
{
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.