MCPgee
MCPgee
MCPgeeMCPgee

Cosmotop

v1.0.0•Monitoring & Observability•stable

Multiplatform system monitoring tool using Cosmopolitan Libc

cosmopolitan-libccppcross-platformmcp-serversystem-monitoring
Share:
67
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Cosmotop?

Cosmotop is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to multiplatform system monitoring tool using cosmopolitan libc

Multiplatform system monitoring tool using Cosmopolitan Libc

This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Multiplatform system monitoring tool using Cosmopolitan Libc

Use Cases

Monitor system performance across platforms.
Track CPU, memory, and resource usage.
Get cross-platform system insights using Cosmopolitan Libc.
bjia56

Maintainer

LicenseApache-2.0
Languagec++
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx cosmotop

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Cosmotop

Cosmotop is a multiplatform system monitoring tool built with Cosmopolitan Libc that runs natively on Linux, macOS, Windows, and BSD without recompilation. When launched with the --mcp flag it exposes an MCP server over STDIO, giving AI assistants real-time access to CPU, memory, disk, network, GPU, and container metrics from the host machine. Developers and operators use it to let Claude query live system health without leaving the chat interface.

Prerequisites

  • A supported OS: Linux 2.6.18+, macOS 13+, or Windows 10+
  • The cosmotop binary downloaded from GitHub releases (or installed via Homebrew on macOS/Linux)
  • An MCP-compatible client such as Claude Desktop or Claude Code
  • Optional: Docker/Podman running if you want container metrics (set DOCKER_HOST if using a non-default socket)
1

Download or install cosmotop

On macOS or Linux install via Homebrew. On other platforms download the pre-built binary directly from the GitHub releases page — the Cosmopolitan build is a single portable executable.

brew tap bjia56/tap
brew install cosmotop
2

Verify the binary works

Run cosmotop normally once to confirm it starts and auto-generates its config at ~/.config/cosmotop/cosmotop.conf.

cosmotop --version
3

Test MCP server mode

Launch cosmotop in MCP mode to confirm STDIO transport starts correctly. It will output a JSON initialization message and then wait for requests.

cosmotop --mcp
4

Configure your MCP client

Add cosmotop to your Claude Desktop or Claude Code MCP configuration so it starts automatically whenever the client launches.

5

Verify available tools in your client

After restarting your MCP client, ask Claude to list system info or query CPU usage. Cosmotop exposes tools: get_system_info, get_cpu_info, get_memory_info, get_disk_info, get_network_info, get_gpu_info, get_npu_info, get_container_info, and get_process_info.

Cosmotop Examples

Client configuration

Add this block to claude_desktop_config.json (or your Claude Code MCP config) to register cosmotop as an MCP server.

{
  "mcpServers": {
    "cosmotop": {
      "command": "cosmotop",
      "args": ["--mcp"]
    }
  }
}

Prompts to try

Once connected, use these prompts with Claude to query live system data.

- "What is the current CPU usage on this machine?"
- "How much memory is free right now, and what processes are using the most?"
- "Show me disk usage for all mounted drives."
- "Are there any running Docker containers and what resources are they consuming?"
- "Give me a full system health summary including CPU, memory, and network."

Troubleshooting Cosmotop

cosmotop --mcp exits immediately with no output

Ensure you are using a release build that includes MCP support (check the changelog on GitHub releases). Older builds may not include the --mcp flag.

get_container_info returns empty or an error about Docker

Set the DOCKER_HOST environment variable to your socket path (e.g. DOCKER_HOST=unix:///var/run/docker.sock cosmotop --mcp) or ensure your user has permission to read the Docker socket.

GPU or NPU tools not appearing in the tool list

These tools are only registered when cosmotop detects compatible hardware at startup. Confirm your GPU drivers are installed and the device is visible to the OS.

Frequently Asked Questions about Cosmotop

What is Cosmotop?

Cosmotop is a Model Context Protocol (MCP) server that multiplatform system monitoring tool using cosmopolitan libc It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Cosmotop?

Follow the installation instructions on the Cosmotop GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Cosmotop?

Cosmotop works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Cosmotop free to use?

Yes, Cosmotop is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Cosmotop Alternatives — Similar Monitoring & Observability Servers

Looking for alternatives to Cosmotop? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.

Netdata

★ 78.9k

Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.

Kubeshark

★ 11.9k

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

Mission Control

★ 4.9k

Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.

Grafana

★ 3.0k

This MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.

Sentrux

★ 2.4k

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

OpenInference

★ 986

OpenTelemetry Instrumentation for AI Observability

Browse More Monitoring & Observability MCP Servers

Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Monitoring & ObservabilityBrowse All Servers

Quick Config Preview

{ "mcpServers": { "cosmotop": { "command": "npx", "args": ["-y", "cosmotop"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Cosmotop?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides