System Monitor MCP

System Monitor MCP 是一个基于 Model Context Protocol (MCP) 的系统监控服务，可以提供系统资源信息，包括 CPU、内存、磁盘、网络和进程等。

版本更新 (v1.1.3)

🐛 修复了内存信息获取功能中的 cached 和 buffers 属性错误
✅ 优化了内存监控的兼容性，支持不同操作系统
🔧 改进了错误处理机制
📊 所有功能已通过完整测试验证

功能特点

实时监控系统资源使用情况
提供 CPU 详细信息，包括使用率、频率等
提供内存详细信息，包括物理内存和交换内存
提供磁盘详细信息，包括分区和 I/O 统计
提供网络详细信息，包括接口和流量统计
提供进程详细信息，包括 CPU 使用率、内存使用率等
支持资源监控，定期返回资源数据

安装

pip install system-monitor-mcp

使用方法

作为 MCP 服务器

在 AI 助手配置中添加以下 MCP 服务器配置：

{
  "mcpServers": {
    "system-monitor-mcp": {
      "timeout": 60,
      "type": "stdio",
      "command": "python",
      "args": [
        "-m",
        "system_monitor_mcp"
      ]
    }
  }
}

可用工具

get_system_info: 获取系统基本信息，包括 CPU、内存、操作系统等
get_cpu_info: 获取 CPU 详细信息，包括使用率、频率等
get_memory_info: 获取内存详细信息，包括物理内存和交换内存
get_disk_info: 获取磁盘详细信息，包括分区和 I/O 统计
get_network_info: 获取网络详细信息，包括接口和流量统计
get_processes_info: 获取进程详细信息，包括 CPU 使用率、内存使用率等
monitor_resource: 监控系统资源使用情况，定期返回资源数据

示例

获取系统信息

# 使用 MCP 工具获取系统信息
result = await use_mcp_tool(
    server_name="system-monitor-mcp",
    tool_name="get_system_info",
    arguments={}
)
print(result)

监控 CPU 使用率

# 监控 CPU 使用率，每 2 秒采集一次，持续 30 秒
result = await use_mcp_tool(
    server_name="system-monitor-mcp",
    tool_name="monitor_resource",
    arguments={
        "resource_type": "cpu",
        "interval": 2,
        "duration": 30
    }
)
print(result)

依赖

Python >= 3.8
psutil >= 5.9.0
mcp >= 1.0.0
pydantic >= 2.0.0

更新日志

v1.1.3 (2024-12-19)

修复内存信息获取功能的兼容性问题
优化了 Windows 系统下的内存监控
改进了错误处理和异常捕获
完善了测试覆盖率

v1.1.2

基础功能实现
支持系统、CPU、内存、磁盘、网络、进程监控

许可证

MIT

Metadata

Release files for system-monitor-mcp 1.1.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for system-monitor-mcp 1.1.4
File	Size	Uploaded	Provenance
system_monitor_mcp-1.1.4.tar.gz	11.1 kB	Aug 13, 2025	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for system-monitor-mcp 1.1.4
File	Interpreter	ABI	Platform	Reset
system_monitor_mcp-1.1.4-py3-none-any.whl 11.7 kB Aug 13, 2025 Without provenance	Python 3	none	any	Details

Total release size: 22.8 kB

Release files / system_monitor_mcp-1.1.4.tar.gz

Download URL	system_monitor_mcp-1.1.4.tar.gz
Size	11.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`61ef828cb21b92e52494f9482f66c533861e668f836f709724c35f90e9e77fa1`
BLAKE2b-256 checksum How to use checksums	`d8d102da9fb58b050263437da79e49c5684e7a3f228f3fc347f4ef607d46a48b`
Upload date	Aug 13, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.8.6`

Release files / system_monitor_mcp-1.1.4-py3-none-any.whl

Download URL	system_monitor_mcp-1.1.4-py3-none-any.whl
Size	11.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`1825ce740d8473920d3de93152e40802ca2dd34f8a18cee156858a8a841345db`
BLAKE2b-256 checksum How to use checksums	`9c8d18e43837d3c054456a293df335cb2d3beb2d7d7b55004d23dac83780e796`
Upload date	Aug 13, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.8.6`

Security for system-monitor-mcp 1.1.4

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.