---
title: "10 Months into AI Agents : Which Are Used Most?"
description: "Analysis of 200 Model Context Protocol tools shows developers prioritize infrastructure \u0026 search over entertainment. 54% of MCP usage focuses on code generation, debugging \u0026 terminal access - revealing AI adoption patterns."
categories: ["AI","Developer Tools","Technology Adoption"]
keywords: ["Model Context Protocol","AI agents","Claude AI","code generation tools","developer tools","AI adoption","infrastructure tools","information retrieval"]
ai_summary: "Analysis reveals developers favor infrastructure tools in AI agent usage, highlighting trends in AI adoption and tool efficiency."
date: 2025-09-09
lastmod: 2026-07-28
canonical_url: https://www.tomtunguz.com/mcp-server-activity/
author: "Tomasz Tunguz"
---

{{< email_image src="maojocd3r4sfvdbu28vj" alt="MCP Usage Shows Clear Infrastructure Focus" width="540" height="304" >}}
When [Anthropic introduced the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol), they promised to simplify using agents.

MCP enables an AI to understand which tools rest at its disposal : web search, file editing, & email drafting for example.

Ten months later, we analyzed 200 MCP tools to understand which categories developers actually use.

Three usage patterns have emerged from the data :

Development infrastructure tools dominate with 54% of all sessions despite being just half the available servers. Terminal access, code generation, & infrastructure access are the most popular.

While coding, engineers benefit from the ability to push to GitHub, run code in a terminal, & spin up databases. These tools streamline workflows & reduce context switching.

Information retrieval captures 28% of sessions with fewer tools, showing high efficiency. Web search, knowledge bases, & document retrieval are key players. These systems are likely used more in production, on behalf on users, than during development.

Everything else including entertainment, personal management, content creation, splits the remaining 18%. Movie recommenders, task managers, & Formula 1 schedules fill specific niches.

MCP adoption is still early. Not all AIs support MCP. Of those that do, Claude, Claude Code, Cursor top the list (alliteration in AI). Developer focused products & early technical adopters are the majority of users.

But as consumer use of AI tools grows & MCP support broadens, we should expect to see a much greater diversity of tool use.