OSS Python client for creating MCP capable agents in 6 lines of code
Hello HN, Pietro here! I've been really excited to see the recent buzz around MCP and all the cool things people are building with it. Though, the fact that you can use it only through desktop apps really seemed wrong and prevented me for trying most examples, so I wrote a simple client, then I wrapped into some class, and I ended up creating a python package that abstracts some of the async uglyness. You need: * one of those MCPconfig JSONs * 6 lines of code and you can have an agent use the MCP tools from python. The structure is simple: an MCP client creates and manages the connection and…
What it does
In the maker’s words, at launch
Hello HN, Pietro here! I've been really excited to see the recent buzz around MCP and all the cool things people are building with it. Though, the fact that you can use it only through desktop apps really seemed wrong and prevented me for trying most examples, so I wrote a simple client, then I wrapped into some class, and I ended up creating a python package that abstracts some of the async uglyness. You need: * one of those MCPconfig JSONs * 6 lines of code and you can have an agent use the MCP tools from python. The structure is simple: an MCP client creates and manages the connection and instantiation (if needed) of the server and extracts the available tools. The MCPAgent reads the tools from the client, converts them into callable objects, gives access to them to an LLM, manages tool calls and responses. It's very early-stage, and I'm sharing it here for feedback and contributions. If you're playing with MCP or building agents around it, I hope this makes your life easier. Repo: https://github.com/pietrozullo/mcp-use Pipy: pip install mcp-use (https://pypi.org/project/mcp-use/) Happy to answer questions or walk through examples! Props: Name is clearly inspired by browser_use an insane project by a friend of mine, following him closely I think I got brainwashed into naming everything mcp related _use. Thanks!
Does the same job
all alternatives →
- PPPractical Python Projects book release2021 · practicalpython.yasoob.me · ▲88
Hi everyone! I just released the Practical Python Projects book! (https://practicalpython.yasoob.me) I am happy to announce the first version as a release candidate. I have poured a lot of love into writing this book and would love to hear what you guys think. (A limited 100% off and discount coupons at the end) This is not a pure beginner book. The book does assume some background Python knowledge. You need to know the basics like methods, functions, classes, and such. If I use something that is not typically covered in beginner Python books, I will explain it before I use it.…
- FAFastMCP – A Pythonic way to build Model Context Protocol servers2024 · github.com · ▲6
Hi HN -- Since Anthropic announced the Model Context Protocol (MCP) last week [1], I've been excited about giving Claude new capabilities through my custom servers. But while MCP is powerful, implementing the protocol correctly requires a lot of low-level boilerplate code. I found myself wanting something like FastAPI - a high-level framework that would let me focus on building features, not servers. After some hacking, I'm sharing FastMCP: a Pythonic framework for building MCP servers. FastMCP uses decorators to transform normal functions into MCP tools, resources, templates, and prompts,…
- MMMCP Mesh – one endpoint for all your MCP servers (OSS self-hosted)Dec 2025 · github.com · ▲8
Hey HN! I’m Gui from deco (decocms.com). We’ve been using this tool internally as the foundation for a few customer AI platforms, and today we’re open-sourcing it as MCP Mesh. MCP is quickly becoming the standard for agentic systems, but… once you go past a couple servers it turns into the same problems for every team: - M×N config sprawl (every client wired to every server, each with its own JSON + ports + retries) - Token + tool bloat (dumping tool definitions into every prompt doesn’t scale) - Credentials + blast radius (tokens scattered across clients, hard to audit, hard to revoke) - No…
- PAPrefab – A generative UI framework for PythonApr 2026 · prefab.prefect.io · ▲5
Hi HN, I'm the author of FastMCP, the most popular Python framework for building MCP servers. I've been really excited about MCP Apps for a while. I think letting a server ship a fully interactive UI directly into the conversation is one of the most compelling additions to the protocol. I wanted to make this a first-class experience in FastMCP, but I kept getting stuck on what it actually means for a Python framework to integrate with a frontend feature. The JavaScript ecosystem has extraordinary tooling for this. I didn't want to build a worse version of it just to stay in Python. What…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
