MCP Server Not Showing in Claude Desktop? Here’s What I Did

2026-05-30 · Source: Towards AI - Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

This article details the process of connecting a local "Math MCP Server" to Claude Desktop on Windows, serving as the third installment in an MCP series. The server, previously built using FastMCP, is demonstrated with two fundamental mathematical tools: "square" and "square_root". These tools are implemented in Python, utilizing "@mcp.tool()" decorators to define their functionality, including calculating the square of a float and its square root, with specific error handling for negative numbers in the square root function. The core procedure outlined focuses on registering this custom local MCP server to enable its specialized tools within the Claude Desktop application.

Key takeaway

For AI Engineers or developers aiming to extend Claude Desktop's functionality, you should consider integrating local custom tools via an MCP server. This approach allows you to define specialized functions, such as mathematical operations or data processing, directly accessible within Claude Desktop. By registering your local server, you can significantly enhance the AI's capabilities with domain-specific or proprietary logic, moving beyond its default toolset.

Key insights

Connecting local custom tools via an MCP server extends Claude Desktop's capabilities.

Principles

• Define custom tools using "@mcp.tool()" decorators.
• Implement error handling for tool robustness.
• Register local MCP servers for desktop integration.

Method

The article outlines registering a local MCP server, containing custom Python tools like "square" and "square_root", with Claude Desktop on Windows.

In practice

• Develop custom functions for specific tasks.
• Integrate local services with AI desktop applications.

Topics

• MCP Server
• Claude Desktop
• FastMCP
• Custom Tools
• Tool Integration
• Windows Development

Best for: AI Engineer, Software Engineer

Related on AIssential

• How I Use Bifrost MCP Gateway and Code Mode to Give Claude Code Safer MCP Access with Lower Token Cost — Bifrost's MCP Gateway and Code Mode enhance Claude Code's tool use with governance, cost reduction, and scalable orchestration.
• The AWS API MCP Server connector for Claude: What It Is and How to Set It Up. — Natural language processing can significantly reduce friction in cloud resource management.
• I Built Claude OS — A System That Turns Claude into an Execution Engine — Claude OS centralizes Claude's vast ecosystem components, enabling advanced execution beyond basic chatbot interactions.
• Why was MCP created? — MCP standardizes AI-tool communication, reducing M×N integration complexity to M+N implementations.
• HPC Coding Agent - Part 3: MCP Tool for Profiling — An AI agent can autonomously profile and optimize GPU-accelerated HPC applications using a custom MCP server for tool integration.
• Build a Claude Cowork-Like Browser Agent Using Playwright MCP and Claude Desktop — Playwright MCP transforms Claude Desktop into an agent capable of structured, free web automation using accessibility snapshots.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Towards AI - Medium.