Menu
Use this skill when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style, summarize documents into decks, add AI voice narration, and export pages/audio. Use for any "make slides", "create a deck", or "slides from this document" request.
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.
Use the Hugging Face Hub CLI (`hf`) to download, upload, and manage models, datasets, and Spaces.
Plan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.
Manage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patterns
Generate AI images, videos, and music/audio from agents using the RunAPI CLI.
| name | mcp-builder-ms |
| description | Use this skill when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). |
| risk | unknown |
| source | community |
| date_added | 2026-02-27 |
Use this skill when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
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.
Microsoft provides extensive MCP infrastructure for Azure and Foundry services. Understanding this ecosystem helps you decide whether to build custom servers or leverage existing ones.
| Type | Transport | Use Case | Example |
|---|---|---|---|
| Local | stdio | Desktop apps, single-user, local dev | Azure MCP Server via NPM/Docker |
| Remote | Streamable HTTP | Cloud services, multi-tenant, Agent Service | https://mcp.ai.azure.com (Foundry) |
Before building a custom server, check if Microsoft already provides one:
| Server | Type | Description |
|---|---|---|
| Azure MCP | Local | 48+ Azure services (Storage, KeyVault, Cosmos, SQL, etc.) |
| Foundry MCP | Remote | https://mcp.ai.azure.com - Models, deployments, evals, agents |
| Fabric MCP | Local | Microsoft Fabric APIs, OneLake, item definitions |
| Playwright MCP | Local | Browser automation and testing |
| GitHub MCP | Remote | https://api.githubcopilot.com/mcp |
Full ecosystem: See 🔷 Microsoft MCP Patterns for complete server catalog and patterns.
| Scenario | Recommendation |
|---|---|
| Azure service integration | Use Azure MCP Server (48 services covered) |
| AI Foundry agents/evals | Use Foundry MCP remote server |
| Custom internal APIs | Build custom server (this guide) |
| Third-party SaaS integration | Build custom server (this guide) |
| Extending Azure MCP | Follow Microsoft MCP Patterns |
Creating a high-quality MCP server involves four main phases:
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.
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:
Language Selection:
| Language | Best For | SDK |
|---|---|---|
| TypeScript (recommended) | General MCP servers, broad compatibility | @modelcontextprotocol/sdk |
| Python | Data/ML pipelines, FastAPI integration | mcp (FastMCP) |
| C#/.NET | Azure/Microsoft ecosystem, enterprise | Microsoft.Mcp.Core |
Transport Selection:
| Transport | Use Case | Characteristics |
|---|---|---|
| Streamable HTTP | Remote servers, multi-tenant, Agent Service | Stateless, scalable, requires auth |
| stdio | Local servers, desktop apps | Simple, single-user, no network |
Load framework documentation:
For TypeScript (recommended):
https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.mdFor Python:
https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.mdFor C#/.NET (Microsoft ecosystem):
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.
See language-specific guides for project setup:
Create shared utilities:
For each tool:
Input Schema:
Output Schema:
outputSchema where possible for structured datastructuredContent in tool responses (TypeScript SDK feature)Tool Description:
Implementation:
Annotations:
readOnlyHint: true/falsedestructiveHint: true/falseidempotentHint: true/falseopenWorldHint: true/falseReview for:
TypeScript:
npm run build to verify compilationnpx @modelcontextprotocol/inspectorPython:
python -m py_compile your_server.pySee language-specific guides for detailed testing approaches and quality checklists.
After implementing your MCP server, create comprehensive evaluations to test its effectiveness.
Load ✅ Evaluation Guide for complete evaluation guidelines.
Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions.
To create effective evaluations, follow the process outlined in the evaluation guide:
Ensure each question is:
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>
Load these resources as needed during development:
https://modelcontextprotocol.io/sitemap.xml, then fetch specific pages with .md suffixhttps://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.mdhttps://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md🐍 Python Implementation Guide - Complete Python/FastMCP guide with:
@mcp.tool⚡ TypeScript Implementation Guide - Complete TypeScript guide with:
server.registerTool🔷 Microsoft MCP Patterns - Complete C#/.NET guide with:
{Resource}{Operation}Command).AsRequired() / .AsOptional()