How do I use proliant-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@proliant-mcp List my ProLiant servers and their iLO versions" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

proliant-mcp

by hjma29

Overview Schema Source Related Servers Discussions Admin

Python

Remote

proliant-mcp

An MCP server for HPE ProLiant servers, built with FastMCP. It lets AI assistants and agents (GitHub Copilot, Claude, Google ADK, ...) read server inventory and health straight from each server's iLO through the Redfish API.

Tested against iLO 6 (ProLiant DL380 Gen11) and iLO 7 (ProLiant Compute DL325 / DL345 Gen12). iLO 5 (Gen10) uses the same Redfish paths.

Status: v0.1, iLO, read-only. HPE Compute Ops Management (COM) and OneView are next; see Roadmap.

Tools

Tool	What it returns
`list_servers`	Configured server names and iLO hosts (never credentials)
`get_server_summary`	Model, product ID, serial, power and POST state, health, UID, BIOS and iLO version, CPU/memory totals
`get_fleet_summary`	`get_server_summary` for all servers in parallel; failures are per server
`get_ilo_info`	iLO model and firmware version/date, license, COM connection status, iLO IP/MAC/DHCP/DNS
`get_health`	Overall and per-subsystem health, fan and power-supply redundancy
`get_firmware_inventory`	Every firmware component and version
`get_processors`	CPUs and GPUs
`get_memory`	Total, populated/empty slots, each DIMM
`get_storage`	Controllers, drives, RAID volumes
`get_network_adapters`	NICs, ports, MACs, link, LLDP neighbor (switch and port)
`get_event_log`	Newest IML (hardware) or IEL (iLO) entries, filter by severity
`redfish_get`	Raw read-only GET of any `/redfish/v1/...` resource

Every tool is annotated readOnlyHint. Nothing in this version changes a server.

Related MCP server: Redfish MCP Server

Install

Requires Python 3.12+ and uv.

git clone https://github.com/hjma29/proliant-mcp.git
cd proliant-mcp
uv sync

Configure your iLOs

Credentials are read from your machine only, never from this repository.

Option A: inventory file (several servers). Copy examples/inventory.example.ini to ~/.config/proliant-mcp/inventory.ini, fill in hosts and passwords, then chmod 600 it. Or point PROLIANT_MCP_CONFIG at any path. An existing proliant-cli inventory at ~/.config/proliant-cli/inventory.ini is picked up automatically.

Option B: one server from environment variables.

export ILO_HOST=192.0.2.10 ILO_USERNAME=Administrator ILO_PASSWORD='...'
export ILO_NAME=my-server        # optional, default "default"

iLO uses a self-signed certificate by default, so TLS verification is off unless you set verify_ssl = true (ini) or ILO_VERIFY_SSL=1. A read-only iLO account (Login privilege only) is enough for every tool.

Test it

1. Unit tests (no hardware)

uv run pytest

Runs the tools against a fake iLO (httpx.MockTransport) through a real MCP client.

2. From the terminal

uv run fastmcp list src/proliant_mcp/server.py                     # tools and schemas
uv run fastmcp call src/proliant_mcp/server.py list_servers
uv run fastmcp call src/proliant_mcp/server.py get_ilo_info server=dl380-gen11

3. MCP Inspector (web UI)

npx @modelcontextprotocol/inspector uv run --directory "$PWD" proliant-mcp

Open the printed URL, click Connect, then Tools to call each tool by hand.

4. VS Code / GitHub Copilot

Open this folder in VS Code. .vscode/mcp.json registers the server as proliant; start it from the MCP view (or the code lens in that file), switch Copilot Chat to Agent mode, and ask:

"List my ProLiant servers and their iLO versions"
"Which servers have a GPU?"
"Any critical IML events on dl380-gen11?"
"Which switch port is each NIC on dl345-gen12 connected to?"

To use it from any workspace, add the same entry to your user MCP config with an absolute path in --directory.

Claude Desktop / Claude Code / other clients use the same command: uv run --directory /path/to/proliant-mcp proliant-mcp.

5. Over HTTP

uv run proliant-mcp --http --host 127.0.0.1 --port 8000   # endpoint: http://127.0.0.1:8000/mcp

The HTTP endpoint has no authentication. Keep it on localhost or a trusted management network.

Google ADK

examples/adk_agent/agent.py is a Google ADK agent that starts this server over stdio with McpToolset:

export GOOGLE_API_KEY=...            # or Vertex AI env vars
uv run --with "google-adk[mcp]" adk web examples   # pick "adk_agent"

Set ADK_MODEL to choose a different Gemini model. To use the HTTP mode instead, swap StdioConnectionParams for StreamableHTTPConnectionParams(url="http://127.0.0.1:8000/mcp").

Skills

skills/proliant-ilo/SKILL.md is an agent skill that tells an assistant which tool to use for which question, plus workflows (fleet firmware audit, health triage, finding a server's switch port). Copy it into your agent's skills folder (for example ~/.copilot/skills/ or .github/skills/).

Roadmap

iLO (now): read-only inventory and health.
iLO actions: power, UID, one-time boot, opt-in and gated as destructive.
HPE Compute Ops Management (GreenLake): fleet inventory, firmware baselines and jobs.
HPE OneView / Synergy.
Skills for deploying and managing ProLiant servers (OS deployment, firmware updates, BIOS baselines).

Security

No credentials are stored in this repository; .gitignore blocks *.ini (except the example) and .env files.
Tools never return passwords; redfish_get refuses session and account resources.
Each tool call opens and closes its own Redfish session.

License

MIT. Not an official HPE product.

Available Tools

12 tools

get_event_logGet Event LogB

Read-onlyIdempotent

Newest entries from the IML or iLO event log, optionally filtered by severity.

Inputs: server (required), log, limit, severity. Returns: result

get_firmware_inventoryGet Firmware InventoryC

Read-onlyIdempotent

All firmware components and versions (iLO, BIOS/System ROM, NICs, storage controllers, drives, CPLD, ...).

Inputs: server (required). Returns: result

get_fleet_summaryGet Fleet SummaryA

Read-onlyIdempotent

get_server_summary for every configured server at once. Unreachable servers are returned with an error field instead of failing the whole call.

Inputs: no named parameters. Returns: result

get_healthGet HealthA

Read-onlyIdempotent

Overall and per-subsystem health (processors, memory, storage, network, fans, power supplies, temperatures) plus fan / power-supply redundancy.

Inputs: server (required). Returns: object

get_ilo_infoGet Ilo InfoB

Read-onlyIdempotent

iLO details: model (iLO 5/6/7), firmware version and date, license, Compute Ops Management connection status, and the iLO's own network (hostname, IP, MAC, DHCP).

Inputs: server (required). Returns: object

get_memoryGet MemoryA

Read-onlyIdempotent

Memory: total GiB, populated/empty slot counts, and each DIMM (slot, size, type, speed, vendor, HPE part number, health).

Inputs: server (required). Returns: object

get_network_adaptersGet Network AdaptersB

Read-onlyIdempotent

Host network adapters: model, part number, slot, firmware, and ports (MAC, link, speed, LLDP neighbor switch/port when available).

Inputs: server (required). Returns: result

get_processorsGet ProcessorsB

Read-onlyIdempotent

CPUs (socket, model, cores, threads, speed) and GPUs that iLO reports.

Inputs: server (required). Returns: object

get_server_summaryGet Server SummaryB

Read-onlyIdempotent

Server identity and state: model, product ID, serial, power and POST state, health, UID light, BIOS and iLO versions, CPU count/model and total memory.

Inputs: server (required). Returns: object

get_storageGet StorageB

Read-onlyIdempotent

Storage subsystems: controllers (model, firmware), physical drives (model, media, capacity, serial, firmware, bay) and logical volumes / RAID.

Inputs: server (required). Returns: result

list_serversList ServersA

Read-onlyIdempotent

List the configured ProLiant servers (name and iLO host). Credentials are never returned.

Inputs: no named parameters. Returns: object

redfish_getRedfish GetA

Read-onlyIdempotent

Raw read-only GET of any iLO Redfish resource, for data the other tools don't cover.

Inputs: path (required), server (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored 2026-11-15 05:25 across 12 tools

Disambiguation4/5

Each tool targets a distinct resource or granularity, but get_server_summary overlaps meaningfully with get_health, get_processors, get_memory, and get_firmware_inventory, since it reports power/health state, CPU count, total memory, and BIOS/iLO versions. get_fleet_summary is clearly framed as a bulk variant of get_server_summary, and redfish_get is explicitly positioned as the escape hatch for uncovered data.

Naming Consistency4/5

Eleven of the twelve tools follow a clean verb_noun pattern (list_servers, get_ilo_info, get_firmware_inventory, get_event_log, etc.). The lone deviation is redfish_get, which inverts the order to noun_verb, though it remains readable.

Tool Count5/5

Twelve tools is well within the ideal range and each is scoped to a distinct slice of iLO data (firmware, memory, storage, network, health, events). Nothing feels padded or missing in terms of breadth.

Completeness4/5

Read-only inventory and health coverage is thorough, including a raw Redfish escape hatch for anything not modeled. However, there are no write/action operations (power control, UID light toggle, log clearing) even though power/UID state is reported, and redfish_get is GET-only so agents have no remediation path.

Maintenance

ActivityMaintained

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

OneIQ
com.oneiq
Infrastructure context for any AI: VMware, Nutanix, Kubernetes and cloud. Read-only, off production.
Virtualization Cloud Platforms
1
https://mcp.oneiq.com
OpservoA
com.getopservo
Read-only server insight: why a Linux server or K8s cluster is slow, failing or changed.
Developer Tools Monitoring Observability
91
https://api.getopservo.com/mcp
mcpB
com.googleapis.compute
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Cloud Platforms Networking & Infrastructure OS Automation
292
https://compute.googleapis.com/mcp
mcp
com.vibgrate
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Security Monitoring
2
https://mcp.vibgrate.com

Related MCP Servers

HPE OneView MCP Server
Cloud Platforms Virtualization OS Automation
Quazmoz
F
license
Not graded
quality
Not graded
maintenance
Enables AI agents to manage HPE OneView infrastructure through the REST API, including server hardware operations, power control, profile management, and network/storage configuration.
Updated a year ago (2025-11-15 13:09 UTC)
-
Redfish MCP Server
Monitoring OS Automation Virtualization
carlosedp
F
license
C
quality
D
maintenance
Enables AI agents and LLMs to control and monitor Redfish-enabled hardware through power operations, system inventory, event logs, health monitoring, sensor readings, and user account management.
Updated a year ago (2025-08-15 16:25 UTC)
15
1
-
Redfish MCP Server
Networking & Infrastructure Cloud Platforms
nokia-steward
A
license
A
quality
B
maintenance
Enables AI agents to manage infrastructure through natural language queries to Redfish API endpoints, supporting listing endpoints and retrieving resource data.
Updated 2 days ago (2026-11-13 19:58 UTC)
3
20
BSD 3-Clause
mcp-redfish
Monitoring Networking & Infrastructure
fredriksknese
F
license
A
quality
C
maintenance
Enables AI assistants to monitor and control server hardware (power, thermal, storage, firmware, event logs) via Redfish BMC API on Dell iDRAC, HPE iLO, Lenovo XCC, Supermicro BMC, and others.
Updated 6 months ago (2026-05-29 03:29 UTC)
17
4
-

proliant-mcp

Tools

Install

Configure your iLOs

Test it

1. Unit tests (no hardware)

2. From the terminal

3. MCP Inspector (web UI)

4. VS Code / GitHub Copilot

5. Over HTTP

Google ADK

Skills

Roadmap

Security

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

HPE OneView MCP Server

Redfish MCP Server

Redfish MCP Server

mcp-redfish