Metadata-Version: 2.4
Name: proliant-mcp
Version: 0.15.2
Summary: MCP server for HPE compute: read-only tools for ProLiant iLO (Redfish), HPE Compute Ops Management (GreenLake) and HPE OneView / Synergy
Keywords: mcp,hpe,proliant,ilo,redfish,oneview,synergy,compute-ops-management,greenlake,fastmcp,ai-agent
Author: hjma29
License-Expression: MIT
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: System Administrators
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: System :: Systems Administration
Requires-Dist: fastmcp>=4.2.0
Requires-Dist: httpx>=0.27
Requires-Python: >=3.12
Project-URL: Homepage, https://github.com/hjma29/proliant-mcp
Project-URL: Repository, https://github.com/hjma29/proliant-mcp
Project-URL: Changelog, https://github.com/hjma29/proliant-mcp/blob/main/CHANGELOG.md
Project-URL: Issues, https://github.com/hjma29/proliant-mcp/issues
Description-Content-Type: text/markdown

# proliant-mcp

Ask your AI assistant about your HPE servers. **proliant-mcp** is an [MCP](https://modelcontextprotocol.io) server that gives AI assistants (GitHub Copilot, Claude, Codex, opencode, ...) read-only access to **HPE iLO**, **HPE Compute Ops Management** (GreenLake) and **HPE OneView**.

Ask things like *"which servers in Compute Ops Management are critical and why"*, *"show a table of each server's storage controller and GPU"* or *"any active OneView alerts on the Synergy frame"*.

## Install

### Option 1: ask your AI agent

Paste this into your AI agent (GitHub Copilot, Claude, Codex, opencode, ...):

> Install the proliant-mcp MCP server for me. Follow the instructions at https://raw.githubusercontent.com/hjma29/proliant-mcp/main/AGENTS.md (install uv first if it is missing), then tell me when to restart you.

### Option 2: manual

**Step 1.** Install [uv](https://docs.astral.sh/uv/) (no admin rights, no git needed).

Windows (PowerShell):

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

macOS:

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

**Step 2.** Add this to your AI client's MCP configuration and restart the client (VS Code Copilot: *MCP: Open User Configuration*; Claude Desktop: *Settings > Developer > Edit Config*, with `mcpServers` in place of `servers`):

```json
{"servers": {"proliant": {"type": "stdio", "command": "uvx", "args": ["proliant-mcp@latest"]}}}
```

If the client cannot find `uvx`, put its full path in `command`: `C:\Users\<you>\.local\bin\uvx.exe` on Windows, `/Users/<you>/.local/bin/uvx` on macOS.

## Connect your servers

Just ask your assistant, and it guides you in the chat:

- *"Sign in to HPE GreenLake"* for Compute Ops Management. If your chat cannot show pop-ups, it gives you a link to a page on your own computer to type your email.
- *"Add my iLO"* or *"add my OneView"*, or *"import my servers from a file"* (`.ini` or `.csv`).

Passwords are typed on a page on your own computer, never in the chat.

## Update

`proliant-mcp@latest` picks up new releases whenever your AI client restarts the server. To stay on one version, use `proliant-mcp@X.Y.Z`. To check what you run: `uvx proliant-mcp@latest --check --connect`.

## More

[Tools](https://github.com/hjma29/proliant-mcp/blob/main/docs/tools.md) | [Configuration](https://github.com/hjma29/proliant-mcp/blob/main/docs/configuration.md) (inventory file, environment variables, API client) | [Advanced](https://github.com/hjma29/proliant-mcp/blob/main/docs/advanced.md) (pinning, testing, skills, security) | [Changelog](https://github.com/hjma29/proliant-mcp/blob/main/CHANGELOG.md)

Read-only. Credentials stay on your computer and are never sent to the AI model. MIT licensed; not an official HPE product.

<!-- mcp-name: io.github.hjma29/proliant-mcp -->
