Metadata-Version: 2.4
Name: helladmin-server
Version: 0.1.0a5
Summary: HellAdmin MCP proxy server — policy enforcement gateway for AI agents (alpha)
Project-URL: Homepage, https://helladmin.dev
Project-URL: Documentation, https://helladmin.dev/tutorials/deployment/12-docker/
Project-URL: Repository, https://github.com/reimmerse-one/helladmin
Project-URL: Issues, https://github.com/reimmerse-one/helladmin/issues
Project-URL: Changelog, https://github.com/reimmerse-one/helladmin/blob/main/CHANGELOG.md
Author: Arseniy Kustov
License-Expression: Apache-2.0
Keywords: agent-security,ai-agent,firewall,gateway,helladmin,llm-security,mcp,policy-enforcement,proxy,security
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: System Administrators
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Security
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: aiohttp>=3.9
Requires-Dist: fastapi>=0.115
Requires-Dist: helladmin-trust>=0.1.0a5
Requires-Dist: httpx>=0.27
Requires-Dist: psutil>=5.9
Requires-Dist: pydantic>=2.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: uvicorn[standard]>=0.34
Requires-Dist: websockets>=14.0
Provides-Extra: dev
Requires-Dist: httpx>=0.27; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.25; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.8; extra == 'dev'
Provides-Extra: llm
Requires-Dist: openai>=1.0; extra == 'llm'
Provides-Extra: mcp
Requires-Dist: mcp>=1.0; extra == 'mcp'
Description-Content-Type: text/markdown

# HellAdmin Server

![status: alpha](https://img.shields.io/badge/status-alpha-black) ![platform: linux](https://img.shields.io/badge/platform-linux-blue) ![license: Apache 2.0](https://img.shields.io/badge/license-Apache%202.0-blue)

MCP proxy server + kernel-level enforcement engine for AI agent infrastructure.

Contains:
- **Landlock enforcer** — unprivileged kernel file/network sandboxing (no root)
- **seccomp-bpf** — syscall filtering (ptrace, mount, unshare blocked)
- **MCP proxy** — reverse proxy for MCP servers with argument validation
- **ArgumentValidator** — blocks command injection, path traversal
- **EgressGuard** — blocks SSRF to cloud metadata endpoints
- **Policy compiler** — one YAML config to seccomp + AppArmor + nftables + Landlock rules
- **Activity source detection** — classify events by SSH session, container, process

## Quick start

```bash
pip install helladmin

# Sandbox a process
helladmin run -- python3 agent.py

# MCP proxy
helladmin proxy add --name my-server --cmd python3 server.py --access public
helladmin proxy serve --port 8443

# Dashboard
helladmin dashboard --port 8888
```

## Requirements

Linux (kernel 5.13+), Python 3.11+.

## License

Apache-2.0
