Mcp Server Builder logo

Mcp Server Builder

Organization
UitbreidenOS
mcp-server-builder

Build custom MCP servers: expose tools, resources, and prompts via stdio or HTTP/SSE transport — connect proprietary data to Claude Code

Overview

PublisherUitbreidenOS
RepositoryUitKit
Skill namemcp-server-builder
Stars
14
Forks
5
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by UitbreidenOS on GitHub. Read the source before you install it.

Installation

Install the Mcp Server Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/UitbreidenOS/UitKit/tree/main/plugins/uitkit-ai-engineering/skills/mcp-server-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/UitbreidenOS/UitKit.git /tmp/UitKit
mkdir -p .claude/skills
cp -r /tmp/UitKit/plugins/uitkit-ai-engineering/skills/mcp-server-builder .claude/skills/mcp-server-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcp Server Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mcp Server Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mcp Server Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MCP Server Builder Skill

When to activate

  • Building a custom MCP server to expose internal data or APIs to Claude Code
  • Wrapping a REST API as MCP tools so Claude can call it natively
  • Creating an MCP server for a database, file system, or proprietary service
  • Setting up MCP with stdio transport (local tools) or HTTP/SSE (remote servers)
  • Adding MCP resources (read-only data) or prompts (reusable templates) alongside tools

When NOT to use

  • When an existing MCP server already does what you need (check mcp.so first)
  • Simple Claude API integrations without tool exposure — use the Claude API skill
  • When you just need to USE an MCP server, not build one — see mcp/recommended-servers.md

Instructions

Installation

bash
npm install @modelcontextprotocol/sdk

Minimal MCP server (stdio)

typescript
// src/server.ts
import { Server } from '@modelcontextprotocol/sdk/server/index.js'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
import {
  CallToolRequestSchema,
  ListToolsRequestSchema,
} from '@modelcontextprotocol/sdk/types.js'

const server = new Server(
  { name: 'my-mcp-server', version: '1.0.0' },
  { capabilities: { tools: {} } }
)

// Define tools
server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [
    {
      name: 'get_user',
      description: 'Retrieve a user by their ID from the internal database',
      inputSchema: {
        type: 'object',
        properties: {
          userId: { type: 'string', description: 'The user UUID' },
        },
        required: ['userId'],
      },
    },
    {
      name: 'list_orders',
      description: 'List recent orders for a user',
      inputSchema: {
        type: 'object',
        properties: {
          userId: { type: 'string' },
          limit:  { type: 'number', default: 10 },
        },
        required: ['userId'],
      },
    },
  ],
}))

// Handle tool calls
server.setRequestHandler(CallToolRequestSchema, async (request) => {
  const { name, arguments: args } = request.params

  switch (name) {
    case 'get_user': {
      const user = await db.users.findById(args.userId)
      if (!user) return { content: [{ type: 'text', text: 'User not found' }], isError: true }
      return { content: [{ type: 'text', text: JSON.stringify(user, null, 2) }] }
    }

    case 'list_orders': {
      const orders = await db.orders.findByUser(args.userId, args.limit ?? 10)
      return { content: [{ type: 'text', text: JSON.stringify(orders, null, 2) }] }
    }

    default:
      throw new Error(`Unknown tool: ${name}`)
  }
})

// Start server
const transport = new StdioServerTransport()
await server.connect(transport)

Resources (read-only data Claude can access)

typescript
import { ListResourcesRequestSchema, ReadResourceRequestSchema } from '@modelcontextprotocol/sdk/types.js'

const server = new Server(
  { name: 'my-server', version: '1.0.0' },
  { capabilities: { resources: {}, tools: {} } }
)

// List available resources
server.setRequestHandler(ListResourcesRequestSchema, async () => ({
  resources: [
    {
      uri: 'db://schema',
      name: 'Database Schema',
      description: 'Current database schema for all tables',
      mimeType: 'text/plain',
    },
    {
      uri: 'config://app',
      name: 'Application Config',
      description: 'Current application configuration (non-sensitive)',
      mimeType: 'application/json',
    },
  ],
}))

// Read a specific resource
server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
  const { uri } = request.params

  if (uri === 'db://schema') {
    const schema = await getDbSchema()
    return { contents: [{ uri, mimeType: 'text/plain', text: schema }] }
  }

  if (uri === 'config://app') {
    return { contents: [{ uri, mimeType: 'application/json', text: JSON.stringify(safeConfig) }] }
  }

  throw new Error(`Unknown resource: ${uri}`)
})

Prompts (reusable templates)

typescript
import { ListPromptsRequestSchema, GetPromptRequestSchema } from '@modelcontextprotocol/sdk/types.js'

server.setRequestHandler(ListPromptsRequestSchema, async () => ({
  prompts: [
    {
      name: 'analyze_user',
      description: 'Analyze a user account for suspicious activity',
      arguments: [
        { name: 'userId', description: 'The user ID to analyze', required: true },
      ],
    },
  ],
}))

server.setRequestHandler(GetPromptRequestSchema, async (request) => {
  const { name, arguments: args } = request.params

  if (name === 'analyze_user') {
    const user = await db.users.findById(args?.userId)
    return {
      messages: [
        {
          role: 'user',
          content: {
            type: 'text',
            text: `Analyze this user for suspicious activity:\n\n${JSON.stringify(user, null, 2)}\n\nCheck for: unusual login times, high-value transactions, account age vs activity ratio.`,
          },
        },
      ],
    }
  }
  throw new Error(`Unknown prompt: ${name}`)
})

HTTP/SSE transport (remote server)

typescript
// src/http-server.ts — for servers that run remotely (not local stdio)
import { Server } from '@modelcontextprotocol/sdk/server/index.js'
import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js'
import express from 'express'

const app = express()
app.use(express.json())

const server = new Server({ name: 'remote-mcp', version: '1.0.0' }, { capabilities: { tools: {} } })
// ... add handlers ...

app.post('/mcp', async (req, res) => {
  const transport = new StreamableHTTPServerTransport({ sessionIdGenerator: () => crypto.randomUUID() })
  await server.connect(transport)
  await transport.handleRequest(req, res, req.body)
})

app.listen(3001, () => console.log('MCP server on :3001'))

Register in Claude Code settings

json
// ~/.claude/settings.json (global) or .claude/settings.json (project)
{
  "mcpServers": {
    "my-internal-api": {
      "command": "node",
      "args": ["./dist/server.js"],
      "env": {
        "DATABASE_URL": "${DATABASE_URL}",
        "API_KEY": "${INTERNAL_API_KEY}"
      }
    },
    "remote-server": {
      "url": "https://my-mcp-server.example.com/mcp",
      "headers": {
        "Authorization": "Bearer ${MCP_TOKEN}"
      }
    }
  }
}

Full example — wrapping a REST API

typescript
// server.ts — expose a company's internal API as MCP tools
import { Server } from '@modelcontextprotocol/sdk/server/index.js'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
import { CallToolRequestSchema, ListToolsRequestSchema } from '@modelcontextprotocol/sdk/types.js'

const API_BASE = process.env.INTERNAL_API_URL!
const API_KEY = process.env.INTERNAL_API_KEY!

const headers = { 'Authorization': `Bearer ${API_KEY}`, 'Content-Type': 'application/json' }

async function apiCall(path: string, options?: RequestInit) {
  const res = await fetch(`${API_BASE}${path}`, { ...options, headers })
  if (!res.ok) throw new Error(`API error ${res.status}: ${await res.text()}`)
  return res.json()
}

const server = new Server({ name: 'internal-api', version: '1.0.0' }, { capabilities: { tools: {} } })

server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [
    {
      name: 'search_customers',
      description: 'Search customers by name, email, or company',
      inputSchema: {
        type: 'object',
        properties: {
          query:  { type: 'string' },
          status: { type: 'string', enum: ['active', 'churned', 'trial'] },
          limit:  { type: 'number', default: 10 },
        },
        required: ['query'],
      },
    },
    {
      name: 'get_customer_usage',
      description: 'Get usage metrics for a customer',
      inputSchema: {
        type: 'object',
        properties: {
          customerId: { type: 'string' },
          period:     { type: 'string', enum: ['7d', '30d', '90d'], default: '30d' },
        },
        required: ['customerId'],
      },
    },
    {
      name: 'create_support_ticket',
      description: 'Create a support ticket for a customer',
      inputSchema: {
        type: 'object',
        properties: {
          customerId: { type: 'string' },
          subject:    { type: 'string' },
          body:       { type: 'string' },
          priority:   { type: 'string', enum: ['low', 'medium', 'high'] },
        },
        required: ['customerId', 'subject', 'body'],
      },
    },
  ],
}))

server.setRequestHandler(CallToolRequestSchema, async (request) => {
  const { name, arguments: args } = request.params

  try {
    switch (name) {
      case 'search_customers': {
        const data = await apiCall(`/customers/search?q=${args.query}&status=${args.status ?? ''}&limit=${args.limit ?? 10}`)
        return { content: [{ type: 'text', text: JSON.stringify(data, null, 2) }] }
      }
      case 'get_customer_usage': {
        const data = await apiCall(`/customers/${args.customerId}/usage?period=${args.period ?? '30d'}`)
        return { content: [{ type: 'text', text: JSON.stringify(data, null, 2) }] }
      }
      case 'create_support_ticket': {
        const data = await apiCall('/tickets', {
          method: 'POST',
          body: JSON.stringify({ customerId: args.customerId, subject: args.subject, body: args.body, priority: args.priority ?? 'medium' }),
        })
        return { content: [{ type: 'text', text: `Ticket created: ${data.ticketId}` }] }
      }
      default:
        throw new Error(`Unknown tool: ${name}`)
    }
  } catch (err) {
    return { content: [{ type: 'text', text: `Error: ${err.message}` }], isError: true }
  }
})

const transport = new StdioServerTransport()
await server.connect(transport)
json
// package.json
{
  "scripts": {
    "build": "tsc",
    "start": "node dist/server.js"
  },
  "bin": {
    "internal-api-mcp": "./dist/server.js"
  }
}

Example

User: Build an MCP server that wraps our Linear project management API — Claude should be able to list issues, create issues, and update issue status.

Expected output:

  • src/server.ts — 3 tools: list_issues, create_issue, update_issue_status
  • Each tool calls the Linear GraphQL API with Bearer token from env
  • Error handling returns isError: true with descriptive message
  • settings.json snippet to register as linear MCP server with LINEAR_API_KEY env var

Frequently asked questions

What does the Mcp Server Builder AI skill do?

Build custom MCP servers: expose tools, resources, and prompts via stdio or HTTP/SSE transport — connect proprietary data to Claude Code

Why use Mcp Server Builder on TypingMind?

Because you install it once and use it with any model. Mcp Server Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mcp Server Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/UitbreidenOS/UitKit/tree/main/plugins/uitkit-ai-engineering/skills/mcp-server-builder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mcp Server Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mcp Server Builder?

As many as you like. As long as a model supports skills, you can use Mcp Server Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mcp Server Builder AI skill free?

It is published on GitHub by UitbreidenOS. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇