For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and prompts.

mcp-agent provides a higher level interface to build apps with MCP. It handles the connection management of MCP servers so you don’t have to. It also implements the Building Effective Agents patterns:
- Augmented LLM (an LLM with access to one or more MCP servers)
- Router, Orchestrator-Worker, Evaluator-Optimizer, and more
- Swarm

The key design principles are composability and reusability – every pattern is an AugmentedLLM itself, so you can chain them into more complex workflows.

Some background: I worked on LSP [5] and language servers at Microsoft, and saw firsthand how standards and protocols can revolutionize developer workflows. Before LSP every IDE had its own esoteric ways of providing language services. LSP changed all that, and arguably made every language server better, since they can focus on improving a single implementation for all clients.

I think AI development is in a similar pre-LSP space right now. There are tons of frameworks [6], every model provider has its own way of handling messages, tool calls, streaming, etc. I really think we need a protocol to standardize these patterns.

Pretty soon every service is going to expose an MCP interface, and mcp-agent is about letting developers orchestrate these services into applications (i.e. build “MCP apps”). This can cover any use of an AI model that needs to interact with the world around it:
- RAG pipelines and Q&A chatbots
- Process automation via AI workflows/async tasks
- Multi-agent orchestration, with human in the loop

The repo contains examples [7] to build RAG agents, streamlit apps and more. There’s a lot left to build, like streaming support, server auth and tighter integration with MCP clients.

But I wanted to share early in the hopes that you can guide me:
- If you find this useful, please let me know. If it’s useful to you, I will dedicate all my time to improving it.
- I really welcome contributions. If you want to collaborate, please reach out on github to help take this forward.

I want to help standardize AI development, so developers a few years from now can look back with horror at the pre-MCP days.

[1] - https://github.com/lastmile-ai/mcp-agent

[2] - https://modelcontextprotocol.io/introduction

[3] - https://www.anthropic.com/research/building-effective-agents

[4] - https://github.com/openai/swarm

[5] - https://microsoft.github.io/language-server-protocol/

[6] - https://xkcd.com/927/ (I understand the irony)

[7] - https://github.com/lastmile-ai/mcp-agent/tree/main/examples

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, handling all the protocol and server complexity so you can focus and iterate quickly.

This is a young project that didn't exist 24 hours ago, but it's ready for some kicking so I'd welcome any thoughts!

[1] HN Link: https://news.ycombinator.com/item?id=42237424

I've tried it on cases like:
- Visualize my networking setup
- Prepare a thorough analysis of my AWS costs and give insights how to cut it
- Find S3 buckets without encryption enabled and their total size

And it works surprisingly well. Let me know what do you think!

I also launched https://archos.ai/chat today, which leverages a distributed systems architecture to enable advanced capabilities within Archos AI Chat