PolyMCP – Expose Python functions as MCP tools
Zero-decorator function wrapping into MCP tools solves real integration friction.
A simple python decorator, to build UI forms out of your everyday python functions
Drop @ui_enabled on a function and you get an instant Flask-backed web form with inputs inferred from type hints, a sidebar for global variables, and a searchable collapsible JSON result viewer. It's a deliberate tiny alternative to Streamlit/Gradio — no React or npm, just vanilla HTML/JS with grouping and theming; excellent for converting one-off scripts into a control panel, but expect limited auth, validation, and scaling features.
Backend developers, SREs, data engineers and anyone who writes automation scripts and wants a quick web UI
It’s a minimalist library that maps your Python functions to a clean web dashboard instantly.
The Essentials:
- One Decorator: Add @ui_enabled to any function to generate a UI form. - No Frontend Bloat: Built with vanilla HTML/JS and Flask. No React, no NPM, no complex build steps. - Smart Inputs: It uses type hints to build forms (supporting strings, numbers, lists, and nested JSON). - Global State: A dedicated sidebar to view and update global variables (like API keys) on the fly. - Rich Output: Function results are displayed in a searchable, collapsible JSON viewer.
It’s essentially "Swagger UI" for your internal scripts. Perfect for when you need a control panel but don't want to spend an hour building one.
Zero-decorator function wrapping into MCP tools solves real integration friction.
Formal verification via Python decorator—Lean proofs generated by LLMs on the fly.
Spring-style config injection for Python when pydantic-settings already handles this.
MCP agent orchestration framework, but MCP itself is still early and fractured.
Temporal alternative with function decorators instead of workflow DSLs.
Unified MCP toolkit shipping in Python and TypeScript, but MCP server scaffolding is already crowded.