# Tiny Agents: an MCP-powered agent in 50 lines of code

DevFeed: [Tiny Agents: an MCP-powered agent in 50 lines of code](<https://devfeed.tech/articles/tiny-agents-an-mcp-powered-agent-in-50-lines-of-code-7514.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/tiny-agents>)

Author: Julien Chaumond

Published: 2025-04-25T00:00:00Z

Content type: tutorial

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Model Context Protocol (MCP)](<https://devfeed.tech/topics/model-context-protocol-mcp.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Playwright](<https://devfeed.tech/topics/playwright.md>), [Filesystems](<https://devfeed.tech/topics/filesystems.md>), [Chromium](<https://devfeed.tech/topics/chromium.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [browser](<https://devfeed.tech/tags/browser.md>), [chromium](<https://devfeed.tech/tags/chromium.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [hub](<https://devfeed.tech/tags/hub.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

## AI overview

This tutorial explains how MCP exposes tools to LLMs and shows how to build a simple TypeScript agent around an MCP client in about 50 lines of code. The example connects to local filesystem and Playwright MCP servers, enabling file operations and sandboxed Chromium browsing, with configurable model and provider settings.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.