Metadata-Version: 2.4
Name: cloudrun-mcp
Version: 0.1.1
Summary: Async MCP SSE client for Google Cloud Run with ID-token auth
Project-URL: Homepage, https://pypi.org/project/cloudrun-mcp/
Project-URL: Source, https://github.com/<your-org>/cloudrun-mcp
Author: Raghava Chellu
License: MIT
License-File: LICENSE
Requires-Python: >=3.10
Requires-Dist: httpx>=0.27.0
Description-Content-Type: text/markdown

# cloudrun-mcp

Async MCP (Model Context Protocol) client for Google Cloud Run.

## Features
- Cloud Run / GKE Workload Identity support
- Automatic ID-token authentication
- Async Server-Sent Events (SSE)
- Agentic-AI friendly streaming API

## Install
```bash
pip install cloudrun-mcp

## Usage

import asyncio
from cloudrun_mcp import MCPClient

async def main():
    client = MCPClient(
        base_url="https://your-mcp-server.run.app"
    )

    async for event in client.events():
        print(event)

asyncio.run(main())

## Requirements

- Python 3.10+
- Running on GCP (Cloud Run, GKE, GCE) with metadata server access


---

## Publish to PyPI (exact commands)

```bash
# 1. Create virtual env
python3 -m venv .venv
source .venv/bin/activate

# 2. Install tools
pip install --upgrade build twine

# 3. Build
python -m build

# 4. Upload (TestPyPI first – recommended)
twine upload --repository testpypi dist/*

# 5. Production PyPI
twine upload dist/*

