# mcpygen

> MCP tooling infrastructure

mcpygen generates typed Python APIs from MCP server tool schemas. Tool calls made through
the generated APIs are executed on a local tool server that manages stdio MCP servers and
connects to remote streamable HTTP or SSE servers, with optional approval workflows via
WebSocket-based approval channels.


## User Guide

- [Overview](https://gradion-ai.github.io/mcpygen/index.md): Project overview and capabilities
- [Installation](https://gradion-ai.github.io/mcpygen/installation/index.md): Installation and setup instructions
- [Quickstart](https://gradion-ai.github.io/mcpygen/quickstart/index.md): Getting started guide
- [API generation](https://gradion-ai.github.io/mcpygen/apigen/index.md): Generating typed Python APIs from MCP server schemas
- [Tool server](https://gradion-ai.github.io/mcpygen/toolserver/index.md): ToolServer
- [Approval](https://gradion-ai.github.io/mcpygen/approval/index.md): Approval workflow
- [CLI](https://gradion-ai.github.io/mcpygen/cli/index.md): CLI reference

## API Reference

- [API generation](https://gradion-ai.github.io/mcpygen/api/apigen/index.md): API generation
- [ToolServer](https://gradion-ai.github.io/mcpygen/api/toolserver/index.md): ToolServer
- [ToolRunner](https://gradion-ai.github.io/mcpygen/api/toolrunner/index.md): ToolRunner
- [Approval](https://gradion-ai.github.io/mcpygen/api/approval/index.md): Approval workflow