Alternatives
Products that do what FastAPI-MCP to expose FastAPI endpoints as MCP tools does
I built FastAPI-MCP as an open-source library, and recently had to completely refactor it, abandoning FastMCP wrappers in favor of the low-level MCP SDK. The new version gives more control over which endpoints are exposed, supports complex request bodies, and allows flexible routing options. I wrote about the technical journey and lessons learned here: https://medium.com/@miki_45906/advanced-mcps-in-python-how-t... Looking for feedback and contributors who are interested in MCPs!
- 1OS
I built a zero-configuration tool for automatically exposing FastAPI endpoints as Model Context Protocol (MCP) tools, open to collabs and contributions!
2025 · github.com
- 2
- 3
- 4FA
2025 · github.com
- 5FF
A few months ago, I benchmarked FastAPI on an i9 MacBook Pro. I couldn't believe my eyes. A primary REST endpoint to `sum` two integers took 6 milliseconds to evaluate. It is okay if you are targeting a server in another city, but it should be less when your client and server apps are running on the same machine. FastAPI would have bottleneck-ed the inference of our lightweight UForm neural networks recently trending on HN under the title "Beating OpenAI CLIP with 100x less data and compute". (Thank you all for the kind words!) So I wrote another library. It has been a while since I have…
2023 · github.com
- 6
- 7
- 8
- 9FA
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,…
2024 · github.com
- 10MO
Every MCP server injects its full tool schemas into context on every turn — 30 tools costs ~3,600 tokens/turn whether the model uses them or not. Over 25 turns with 120 tools, that's 362,000 tokens just for schemas. mcp2cli turns any MCP server or OpenAPI spec into a CLI at runtime. The LLM discovers tools on demand: mcp2cli --mcp https://mcp.example.com/sse --list # ~16 tokens/tool mcp2cli --mcp https://mcp.example.com/sse create-task --help # ~120 tokens, once mcp2cli --mcp https://mcp.example.com/sse create-task --title "Fix bug" No…
Mar 2026 · github.com
- 11PT
I built Polymcp, a framework that allows you to transform any Python function into an MCP (Model Context Protocol) tool ready to be used by AI agents. No rewriting, no complex integrations. Examples Simple function: from polymcp.polymcp_toolkit import expose_tools_http def add(a: int, b: int) -> int: """Add two numbers""" return a + b app = expose_tools_http([add], title="Math Tools") Run with: uvicorn server_mcp:app --reload Now add is exposed via MCP and can be called directly by AI agents. API function: import requests from polymcp.polymcp_toolkit import expose_tools_http def…
Jan 2026
- 12WM
2025 · npmjs.com
- 13CD
Hey folks, I've been building AI agents that need to talk to various APIs, and I got tired of writing custom integrations for every service. So I built the MCP-OpenAPI Server to solve this problem! It's a simple bridge that lets AI agents discover and use our existing OpenAPI endpoints through the Model Context Protocol. No need to write custom code for each service - just point it at the OpenAPI specs, choose which endpoints to expose, and you're good to go. What makes this different from other MCP servers is that it uses SSE transport instead of stdio, making it work well for multi-tenant…
2025 · github.com
- 14MG
Hey HN, Sagiv from liblab is here. We've been deep in the world of API tooling for years at liblab, primarily focusing on generating SDKs and documentation from OpenAPI specs. Recently, we kept running into a recurring frustration: connecting AI tools to existing APIs is way more complex than it should be. You start with a simple goal – let an LLM talk to your API – and suddenly you're neck-deep in spinning up infrastructure, wrestling with authentication, and writing a ton of custom glue code just to translate natural language into structured API calls. Then you have to maintain it all. To…
2025 · mcp.liblab.com
- 15PA
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…
Apr 2026 · prefab.prefect.io
- 16MF
Hey everyone, I've wanted an easy way to control which mcp server tools are available to clients. So for example, I might want a gmail server to only expose the read tool (but not send, delete etc). I figured if I create a cli for spawning mcp servers, I could intercept the stdin, stdout, stderr etc and modify what the clients see when they are making calls to list tools, resources, and prompts. Well it worked! In the initial version you can easily add a server to claude with a safe list of tools: npx -y mcpgod add @modelcontextprotocol/server-everything --client claude --tools=echo,add…
2025 · github.com
- 17OP
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…
2025 · github.com
- 18
An ultra-fast, single-binary MCP server written in Rust as a lightweight alternative to Node.js/Python. - StamManif/mcp-stama
24d ago · github.com
- 19TA
Hi HN! We built Zalor. It turns an OpenAPI spec into an MCP server, so you can make your APIs callable by Claude or ChatGPT without writing any code. Here's a list of specs you can try: https://github.com/ZalorAI/test-data/tree/main/openapi, but feel free to use your own. For background, MCP is a protocol that standardizes how you connect tools to AI assistants. We're both engineers at large software companies, and when we worked on MCP integrations we saw how long setup took and how often the spec was changing. So we built a platform to handle the MCP…
Dec 2025 · mcp.zalor.ai
- 20
- 21OZ
Hey HN! We've developed a way to turn API specifications, like OpenAPI 3.0, into Zapier Triggers and Actions for you to automate parts of an app, with the added benefit of SDK generators. Documenting endpoints sucks. What sucks more is a clunky interface to let nontechnical use your app or outdated/nonexistent SDKs for technical people to set and forget. This project originated from my cofounder and I having to make Zapier.com and Make.com apps frequently while not getting what we wanted out of https://openapi-generator.tech/docs/generators/zapier/. Our…
2024 · portway.ai
- 22
- 23MT
Recently I was trying to use an MCP server to pull data from a service, but hit a limitation: the MCP didn't expose the data I needed, even though the service's REST API supported it. So I wrote a quick CLI wrapper around the API. Worked great, except Claude Code had no structured way to know what my CLI does or how to call it. For `gh` or `curl` the model can learn from the extensive training data, but for a tool I just wrote, it was stabbing in the dark. MCP solves this discovery problem, but it does it by rebuilding tool interaction from scratch: server processes, JSON-RPC transport,…
Feb 2026 · github.com
- 24AL
Most of the MCP servers that I’ve seen are tools implemented in standalone projects. To onboard more tools (especially agents and multi-agent workflows) to MCP, I’ve been thinking it’s important to allow AI engineers to continue to prototype in their existing agent frameworks and deploy with minimal conversion when ready. We created the automcp library, which you can add as a dependency to existing projects (CrewAI, LangGraph, Llama Index, OpenAI Agents SDK, Pydantic AI, mcp-agent currently supported but more coming soon). You just need to run a CLI command to create a run_mcp.py file, make…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →