OME MCP Server

OME MCP Server

Enables AI agents to manage Dell PowerEdge servers via Dell OpenManage Enterprise (OME) REST API, providing tools for device inventory, power control, firmware updates, alert management, and compliance baselines.

Category
访问服务器

README

OME MCP v5 — Dell OpenManage Enterprise MCP Server

Version 5.2 | Changelog

A Model Context Protocol (MCP) server that exposes Dell OpenManage Enterprise (OME) management capabilities to AI agents via a Streaming HTTP transport. No direct iDRAC connections are made — all data flows through OME's REST API.


Features

Tool Description
ome_list_devices List all managed devices with OData filter + pagination
ome_get_device Full detail for one device by ID
ome_get_device_inventory Hardware inventory (CPU/RAM/NIC/HDD/PSU)
ome_get_device_subsystem_health Per-subsystem health status
ome_get_device_network_adapters NIC/port details
ome_device_power_action PowerOn/Off/Restart/Cycle via OME
ome_list_groups List device groups
ome_get_group_devices Devices in a specific group
ome_list_alerts Alerts with severity/status filter
ome_acknowledge_alerts Acknowledge one or more alerts
ome_list_jobs List jobs with filter
ome_get_job Job detail and status
ome_run_job_now Trigger an existing job immediately
ome_get_job_execution_history Job run history
ome_list_discovery_jobs Discovery configuration groups
ome_create_discovery_job Create & start a discovery scan
ome_list_firmware_catalogs Firmware update catalogs
ome_list_firmware_baselines Firmware compliance baselines
ome_get_firmware_baseline_compliance Per-component compliance report
ome_list_templates Configuration/deployment templates
ome_get_template Template details
ome_list_config_baselines Configuration compliance baselines
ome_get_config_baseline_compliance Per-device config compliance
ome_get_system_info OME version, license, health
ome_list_active_sessions Active OME API sessions
ome_get_audit_logs OME audit trail
ome_get_warranty_info Device warranty records
ome_refresh_device_inventory Trigger OME inventory refresh

Architecture

AI Agent / MCP Client
        │
        │  HTTP POST /mcp  (Streaming HTTP transport)
        ▼
┌─────────────────────┐
│   ome_mcp_v5        │   Docker container (Ubuntu/Python 3.11)
│   FastMCP server    │
│   port 8000         │
└────────┬────────────┘
         │  HTTPS REST API calls
         ▼
┌─────────────────────┐
│  OME Appliance      │   https://192.168.1.145/api
│  (192.168.1.145)    │
└────────┬────────────┘
         │  OME manages iDRAC internally
         ▼
   Dell PowerEdge Servers

No connections are made directly to iDRAC — OME handles that internally.


Prerequisites

  • Docker Engine 24+ and Docker Compose v2 on an Ubuntu host
  • Network access from the host to https://192.168.1.145 (OME appliance)
  • OME admin credentials

Quick Start

1. Clone / copy project files

mkdir -p /opt/ome_mcp_v5
cd /opt/ome_mcp_v5
# Place all project files here

2. Configure credentials

cp .env.example .env
nano .env          # Set OME_USER, OME_PASSWORD

Never commit .env to version control.

3. Build the image

./service_control.sh build

4. Start the server

./service_control.sh start

The MCP endpoint will be available at http://<host>:8000/mcp.

5. Check status

./service_control.sh status
./service_control.sh logs 50

TLS / SSL Toggle

Scenario Setting in .env
Lab / self-signed cert OME_VERIFY_SSL=false
Production (trusted CA) OME_VERIFY_SSL=true
Production (custom CA bundle) OME_VERIFY_SSL=/path/to/ca-bundle.crt

No rebuild is required — just change the env var and restart.


Auto-start with systemd (optional)

# Install systemd unit (auto-updates WorkingDirectory to current path)
sudo ./service_control.sh install-systemd

# Start now
sudo systemctl start ome_mcp_v5

# View logs
sudo journalctl -u ome_mcp_v5 -f

To remove the systemd unit:

sudo ./service_control.sh uninstall-systemd

Connecting an MCP Client

Point any MCP-compatible client at:

http://<host_ip>:8000/mcp

Example with mcp CLI:

mcp call --url http://192.168.1.200:8000/mcp ome_list_devices '{"top":10}'

Example with Python SDK:

from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession

async with streamablehttp_client("http://192.168.1.200:8000/mcp") as (r, w, _):
    async with ClientSession(r, w) as session:
        await session.initialize()
        result = await session.call_tool("ome_list_devices", {"top": 5})
        print(result.content)

Pagination

All list tools accept top (page size, default 50) and skip (offset) parameters. Use the returned next_skip value to fetch subsequent pages:

{"top": 25, "skip": 0}   // first page
{"top": 25, "skip": 25}  // second page

OData Filtering

Pass standard OData $filter expressions via the filter parameter:

"Model eq 'PowerEdge R640'"
"Severity eq 'Critical'"
"LastRunStatus/Name eq 'Failed'"
"StatusType eq 'New'"

Security Notes

  • Credentials are stored in .env (owner-read-only, not version-controlled).
  • The server runs as a non-root user (mcpuser, UID 1000) inside the container.
  • Credentials are never logged.
  • For production, set OME_VERIFY_SSL=true and use a valid TLS certificate on OME.
  • The MCP endpoint itself is plain HTTP on port 8000; place a reverse proxy (nginx/caddy) with TLS in front of it if external exposure is required.

Troubleshooting

Container won't start:

./service_control.sh logs

Authentication errors:

  • Verify OME_USER / OME_PASSWORD in .env
  • Confirm OME is reachable: curl -k https://192.168.1.145/api/SessionService/Sessions

SSL errors:

  • Set OME_VERIFY_SSL=false for self-signed certs
  • Restart after changing: ./service_control.sh restart

Tools return empty results:

  • Devices may not be discovered yet — use ome_create_discovery_job
  • Check OME permissions for the API account

Adding New Tools

  1. Add a Pydantic Input model in ome_mcp_v5_server.py
  2. Add a function decorated with @mcp.tool(name="ome_your_tool")
  3. Call _ome_get / _ome_post as appropriate
  4. Rebuild: ./service_control.sh rebuild && ./service_control.sh restart

License

MIT License — see LICENSE file.


Changelog

v5.2.0 — 2026-04-09

Fixed: ome_remediate_firmware_baseline completely rewritten

The tool was non-functional in v5.0/v5.1 due to three root-cause bugs:

  1. Wrong endpoint — Code used UpdateService/Actions/UpdateService.UpdateFirmware, which does not exist in OME 4.6+ (UpdateService.Actions is null). Fixed: now POSTs directly to JobService/Jobs.

  2. Wrong Targets structure — Old payload used {"Id": id, "Type": {...}}, missing the required Data field. Fixed: {"Id": id, "Data": "<component_sources>", "TargetType": {"Id": 1000, "Name": "DEVICE"}} where Data is a semicolon-joined string of component SourceName values for non-compliant components.

  3. Incomplete Params — Old params list was missing required keys. Fixed: full validated param set is repositoryId, catalogId, complianceReportId, operationName, rebootType, signVerify, complianceUpdate, stagingValue.

New execution flow:

  1. GET UpdateService/Baselines({id}) → extract RepositoryId, CatalogId
  2. GET UpdateService/Baselines({id})/DeviceComplianceReports → per-device, collect SourceName for components where UpdateAction != UNKNOWN and ComplianceStatus not in {OK, UNKNOWN}
  3. POST JobService/Jobs with operationName=INSTALL_FIRMWARE, rebootType=2 (graceful) or 3 (stage-only)

Returns an early error if no non-compliant components are found, preventing empty job creation.

Validated by live test: full firmware update of a PowerEdge R6515 (13 components including BIOS, PERC RAID, HDDs, NICs, SSDs) against Dell online catalog baseline.


v5.0.0 — initial release

  • 28 read/write OME tools via Streaming HTTP MCP transport
  • Docker container with non-root user, systemd unit, health check
  • OData filtering and pagination on all list tools

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选