MCP server builder

Guides the agent through building an MCP server for an external API in TypeScript or Python: tool design, schemas, pagination, errors, testing and an evaluation run with Claude. Use when wrapping an API or service as MCP tools.

AI models & APIsPack: Anthropic skills252 linesmcp-builder
Author
Source
anthropics/skills/skills/mcp-builder @ e4bb5d9
License
Apache-2.0 · Copyright 2026 Anthropic, PBC.

About this skill

What it does

The skill walks the agent through building an MCP server for an external API in four phases: planning, implementation, testing and evaluation. When in doubt, it prefers broad API coverage over a few workflow tools. The default stack is TypeScript on SDK v2 (@modelcontextprotocol/server), Streamable HTTP for remote servers and stdio for local ones; Python goes through FastMCP.

The rules are concrete: tool names like service_action_resource, Zod or Pydantic input schemas, outputSchema with structuredContent, Markdown and JSON responses, pagination with has_more, a 25,000-character cap met by returning fewer items, errors that tell the model what to try next, and annotations such as readOnlyHint. Testing means npm run build, a self-check script and the MCP Inspector.

reference/ holds a best-practice sheet, guides for TypeScript v2, TypeScript v1 (existing projects only) and Python, and an evaluation guide. The last phase is ten read-only questions with one verifiable answer each, in an XML file. scripts/evaluation.py has Claude answer them through your server's tools and reports accuracy, tool calls and the model's feedback on each tool; connections.py is its stdio, SSE and HTTP client, example_evaluation.xml a sample. The script needs the packages in scripts/requirements.txt (anthropic, mcp) and ANTHROPIC_API_KEY.

When to use it, and when not

Use it to build an MCP server around an API or service, or to bring an existing one up to these conventions and measure it.

Skip it when you only connect an existing MCP server to your app.

How to run it

The install command below puts the whole folder in place. The agent picks the skill up when an MCP server is being built; to call it yourself:

  • Claude Code: /mcp-builder, or ask for the skill by name.
  • Codex: $mcp-builder.
  • Cursor: type / in the Agent chat and pick mcp-builder.

Example: /mcp-builder Build a TypeScript MCP server for our billing API: search invoices, read one, refund a payment. Add the evaluation file.

The script's default model, claude-3-7-sonnet-20250219, is listed as retired in Claude API reference for agents; pass a current one with -m.

How it differs from similar skills

ChatGPT Apps SDK also builds an MCP server, but for an app inside ChatGPT, with a widget UI and Apps SDK metadata. This skill builds a plain server for any MCP client and adds the evaluation run. CLI creator from API docs turns API docs into a command-line tool instead of a server. Cloudflare Agents SDK can also serve MCP, with createMcpHandler on Cloudflare Workers, but as one part of an agent with state, scheduling and RPC.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/mcp-builder/SKILL.md https://anymodel.org/en/skills/anthropic/mcp-builder/SKILL.md -o ~/.claude/skills/mcp-builder/LICENSE.txt https://anymodel.org/en/skills/anthropic/mcp-builder/LICENSE.txt -o ~/.claude/skills/mcp-builder/reference/evaluation.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/evaluation.md -o ~/.claude/skills/mcp-builder/reference/mcp_best_practices.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/mcp_best_practices.md -o ~/.claude/skills/mcp-builder/reference/node_mcp_server.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/node_mcp_server.md -o ~/.claude/skills/mcp-builder/reference/node_mcp_server_v2.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/node_mcp_server_v2.md -o ~/.claude/skills/mcp-builder/reference/python_mcp_server.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/python_mcp_server.md -o ~/.claude/skills/mcp-builder/scripts/connections.py https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/connections.py -o ~/.claude/skills/mcp-builder/scripts/evaluation.py https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/evaluation.py -o ~/.claude/skills/mcp-builder/scripts/example_evaluation.xml https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/example_evaluation.xml -o ~/.claude/skills/mcp-builder/scripts/requirements.txt https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/requirements.txt
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/mcp-builder/SKILL.md https://anymodel.org/en/skills/anthropic/mcp-builder/SKILL.md -o ~/.agents/skills/mcp-builder/LICENSE.txt https://anymodel.org/en/skills/anthropic/mcp-builder/LICENSE.txt -o ~/.agents/skills/mcp-builder/reference/evaluation.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/evaluation.md -o ~/.agents/skills/mcp-builder/reference/mcp_best_practices.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/mcp_best_practices.md -o ~/.agents/skills/mcp-builder/reference/node_mcp_server.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/node_mcp_server.md -o ~/.agents/skills/mcp-builder/reference/node_mcp_server_v2.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/node_mcp_server_v2.md -o ~/.agents/skills/mcp-builder/reference/python_mcp_server.md https://anymodel.org/en/skills/anthropic/mcp-builder/reference/python_mcp_server.md -o ~/.agents/skills/mcp-builder/scripts/connections.py https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/connections.py -o ~/.agents/skills/mcp-builder/scripts/evaluation.py https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/evaluation.py -o ~/.agents/skills/mcp-builder/scripts/example_evaluation.xml https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/example_evaluation.xml -o ~/.agents/skills/mcp-builder/scripts/requirements.txt https://anymodel.org/en/skills/anthropic/mcp-builder/scripts/requirements.txt
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE.txt','reference/evaluation.md','reference/mcp_best_practices.md','reference/node_mcp_server.md','reference/node_mcp_server_v2.md','reference/python_mcp_server.md','scripts/connections.py','scripts/evaluation.py','scripts/example_evaluation.xml','scripts/requirements.txt') { $p = Join-Path "$HOME\.claude\skills\mcp-builder" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/anthropic/mcp-builder/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE.txt','reference/evaluation.md','reference/mcp_best_practices.md','reference/node_mcp_server.md','reference/node_mcp_server_v2.md','reference/python_mcp_server.md','scripts/connections.py','scripts/evaluation.py','scripts/example_evaluation.xml','scripts/requirements.txt') { $p = Join-Path "$HOME\.agents\skills\mcp-builder" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/anthropic/mcp-builder/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/anthropic/mcp-builder/SKILL.md

SKILL.md

Raw

MCP Server Development Guide

Overview

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.


Process

🚀 High-Level Workflow

Creating a high-quality MCP server involves four main phases:

Phase 1: Deep Research and Planning

1.1 Understand Modern MCP Design

API Coverage vs. Workflow Tools: Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.

Tool Naming and Discoverability: Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., github_create_issue, github_list_repos) and action-oriented naming.

Context Management: Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently.

Actionable Error Messages: Error messages should guide agents toward solutions with specific suggestions and next steps.

1.2 Study MCP Protocol Documentation

Navigate the MCP specification:

Start with the sitemap to find relevant pages: https://modelcontextprotocol.io/sitemap.xml

Then fetch specific pages with .md suffix for markdown format (e.g., https://modelcontextprotocol.io/specification/draft.md).

Key pages to review:

  • Specification overview and architecture
  • Transport mechanisms (streamable HTTP, stdio)
  • Tool, resource, and prompt definitions
1.3 Study Framework Documentation

Recommended stack:

  • Language: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools)
  • Transport: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers.

Load framework documentation:

For TypeScript (recommended):

The TypeScript SDK has two major versions. Pick one before writing code:

  • v2 (@modelcontextprotocol/server): the current stable release. Use it for new servers.
  • v1 (@modelcontextprotocol/sdk): receives bug and security fixes only. Use it only when the project's package.json already depends on @modelcontextprotocol/sdk, or migrate that project with npx @modelcontextprotocol/codemod@latest v1-to-v2 .

If the project already uses v1, tell the user once, in a sentence or two, that v2 (@modelcontextprotocol/server) is the current stable release, that v1 receives only bug and security fixes, and that npx @modelcontextprotocol/codemod@latest v1-to-v2 . migrates the project. Then continue with v1 unless the user asks to migrate.

Don't mix the two in one project: v1 code samples (imports from @modelcontextprotocol/sdk/...) don't apply to v2.

  • TypeScript SDK (v2): Use WebFetch to load https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md; the full docs index is https://ts.sdk.modelcontextprotocol.io/v2/llms.txt
  • ⚡ TypeScript Guide (v2) - TypeScript patterns and examples
  • For v1 projects only: https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/v1.x/README.md and the TypeScript Guide (v1)

For Python:

  • Python SDK: Use WebFetch to load https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md
  • 🐍 Python Guide - Python patterns and examples
1.4 Plan Your Implementation

Understand the API: Review the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed.

Tool Selection: Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.


Phase 2: Implementation

2.1 Set Up Project Structure

See language-specific guides for project setup:

2.2 Implement Core Infrastructure

Create shared utilities:

  • API client with authentication
  • Error handling helpers
  • Response formatting (JSON/Markdown)
  • Pagination support
2.3 Implement Tools

For each tool:

Input Schema:

  • Use Zod (TypeScript) or Pydantic (Python)
  • Include constraints and clear descriptions
  • Add examples in field descriptions

Output Schema:

  • Define outputSchema where possible for structured data
  • Use structuredContent in tool responses (TypeScript SDK feature)
  • Helps clients understand and process tool outputs

Tool Description:

  • Concise summary of functionality
  • Parameter descriptions
  • Return type schema

Implementation:

  • Async/await for I/O operations
  • Proper error handling with actionable messages
  • Support pagination where applicable
  • Return both text content and structured data when using modern SDKs

Annotations:

  • readOnlyHint: true/false
  • destructiveHint: true/false
  • idempotentHint: true/false
  • openWorldHint: true/false

Phase 3: Review and Test

3.1 Code Quality

Review for:

  • No duplicated code (DRY principle)
  • Consistent error handling
  • Full type coverage
  • Clear tool descriptions
3.2 Build and Test

TypeScript:

  • Run npm run build to verify compilation
  • v2 projects: run the self-check script from the v2 guide against the built server
  • Test with MCP Inspector: npx @modelcontextprotocol/inspector

Python:

  • Verify syntax: python -m py_compile your_server.py
  • Test with MCP Inspector

See language-specific guides for detailed testing approaches and quality checklists.


Phase 4: Create Evaluations

After implementing your MCP server, create comprehensive evaluations to test its effectiveness.

Load ✅ Evaluation Guide for complete evaluation guidelines.

4.1 Understand Evaluation Purpose

Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions.

4.2 Create 10 Evaluation Questions

To create effective evaluations, follow the process outlined in the evaluation guide:

  1. Tool Inspection: List available tools and understand their capabilities
  2. Content Exploration: Use READ-ONLY operations to explore available data
  3. Question Generation: Create 10 complex, realistic questions
  4. Answer Verification: Solve each question yourself to verify answers
4.3 Evaluation Requirements

Ensure each question is:

  • Independent: Not dependent on other questions
  • Read-only: Only non-destructive operations required
  • Complex: Requiring multiple tool calls and deep exploration
  • Realistic: Based on real use cases humans would care about
  • Verifiable: Single, clear answer that can be verified by string comparison
  • Stable: Answer won't change over time
4.4 Output Format

Create an XML file with this structure:

<evaluation>
  <qa_pair>
    <question>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?</question>
    <answer>3</answer>
  </qa_pair>
<!-- More qa_pairs... -->
</evaluation>

Reference Files

📚 Documentation Library

Load these resources as needed during development:

Core MCP Documentation (Load First)

  • MCP Protocol: Start with sitemap at https://modelcontextprotocol.io/sitemap.xml, then fetch specific pages with .md suffix
  • 📋 MCP Best Practices - Universal MCP guidelines including:
    • Server and tool naming conventions
    • Response format guidelines (JSON vs Markdown)
    • Pagination best practices
    • Transport selection (streamable HTTP vs stdio)
    • Security and error handling standards

SDK Documentation (Load During Phase 1/2)

  • Python SDK: Fetch from https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md
  • TypeScript SDK (v2): Fetch from https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md; full docs index at https://ts.sdk.modelcontextprotocol.io/v2/llms.txt
  • TypeScript SDK (v1, existing v1 projects only): Fetch from https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/v1.x/README.md

Language-Specific Implementation Guides (Load During Phase 2)

  • 🐍 Python Implementation Guide - Complete Python/FastMCP guide with:

    • Server initialization patterns
    • Pydantic model examples
    • Tool registration with @mcp.tool
    • Complete working examples
    • Quality checklist
  • ⚡ TypeScript Implementation Guide (SDK v2) - Complete TypeScript guide for @modelcontextprotocol/server with:

    • Project setup and the server factory
    • Tool design: Zod 4 schemas, output formats, pagination, errors
    • A complete example serving stdio and Streamable HTTP, plus bearer auth
    • Resources, prompts, and notifications
    • A self-check script to verify the built server
    • Links to SDK examples for advanced features
    • A v1 → v2 translation table, migration steps, and a quality checklist
  • ⚡ TypeScript Implementation Guide (SDK v1) - The equivalent guide for existing @modelcontextprotocol/sdk projects

Evaluation Guide (Load During Phase 4)

  • ✅ Evaluation Guide - Complete evaluation creation guide with:
    • Question creation guidelines
    • Answer verification strategies
    • XML format specifications
    • Example questions and answers
    • Running an evaluation with the provided scripts

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Anthropic skills

Skill creator with evals

Drafts or revises an agent skill, tests it with subagents against a baseline, shows results and benchmarks on a review page and tunes the description for triggering. Use when a new or edited skill has to be measured, not just written.

Distinctive frontend design

Gives new UI a visual direction drawn from its subject: a short plan of colours, type and layout, checked against the brief and against common AI-generated looks before any code. Use when a page or product screen should not look templated.

Web app testing with Playwright scripts

Tests a local web app with Python Playwright scripts: a helper starts and stops the servers, the agent inspects the rendered page, then clicks, fills, takes screenshots and reads console logs. Use when checking a frontend change or reproducing a UI bug.

PDF files: read, fill, create

Extracts text and tables, merges, splits, encrypts and OCRs PDFs with pypdf, pdfplumber, reportlab and qpdf, and fills forms through bundled scripts that check fields and boxes. Use when a task reads, fills or produces a PDF file.

Word documents (.docx)

Creates Word files with docx-js, edits existing ones as unpacked XML, adds tracked changes and comments through bundled scripts, then validates and renders the result. Use when the deliverable or input is a .docx or .dotx file.

Excel spreadsheets (.xlsx)

Builds and edits Excel workbooks with openpyxl, keeps real formulas, recalculates them in LibreOffice with a JSON error report and follows financial-model conventions. Use when the deliverable is a spreadsheet file such as .xlsx, .xlsm or .csv.

PowerPoint decks (.pptx)

Creates themed decks with pptxgenjs, edits templates as unpacked XML with scripts for slide text, thumbnails, duplication and validation, and checks every slide as an image. Use when a task creates, edits or reads a .pptx or .potx file.

Claude API reference for agents

Anthropic's reference for code that calls Claude: SDKs in seven languages and cURL, current models and prices, tool use, caching, Managed Agents, plus migration, cost and eval procedures. Use when writing or changing code that uses the Claude API.

Algorithmic art with p5.js

Creates generative art in p5.js: a short manifesto for the piece, then a seeded algorithm in one HTML page with sliders, seed navigation and PNG download. Use when asked for flow fields, particle systems or other art made with code.

Document co-authoring workflow

Guides the user through writing a document in three stages: context gathering with numbered questions, section-by-section drafting with brainstormed options, and a test on a subagent that sees only the text. Use when drafting a spec, proposal or decision doc.