Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for system metrics and process data
MCP System Monitor exposes live system information through a Model Context Protocol interface. It packages separate tools for CPU, memory, disk, network, host, and process data so an agent can inspect the machine during a session.
Builders who want an MCP-compatible agent to query live system metrics from the machine they are working on.
You can ask your agent for real-time CPU, memory, disk, network, host, and process details without leaving the chat.
What it does
CPU info tool
Provides CPU usage, core count, and per-core data through `get_cpu_info`.
Memory info tool
Returns virtual memory and swap usage through `get_memory_info`.
Disk info tool
Reports disk usage, partitions, and I/O stats through `get_disk_info`.
Network info tool
Shows interfaces, connections, and traffic stats through `get_network_info`.
Host info tool
Reports system details, uptime, boot time, and users through `get_host_info`.
Process info tool
Lists processes and can return detailed data for a PID through `get_process_info`.
How to get it
- 1Run
git clone https://github.com/seekrays/mcp-monitor.git cd mcp-monitor make build
- 2Run the compiled binary
./mcp-monitor
README
MCP System Monitor
A system monitoring tool that exposes system metrics via the Model Context Protocol (MCP). This tool allows LLMs to retrieve real-time system information through an MCP-compatible interface.

Features
This tool provides the following monitoring capabilities:
- CPU Information: Usage percentage, core count, and detailed CPU info
- Memory Information: Virtual and swap memory usage
- Disk Information: Disk usage, partitions, and I/O statistics
- Network Information: Network interfaces, connections, and traffic statistics
- Host Information: System details, uptime, boot time, and users
- Process Information: Process listing, sorting, and detailed per-process statistics
Available Tools
1. CPU Information
Tool: get_cpu_info
Description: Get CPU information and usage
Parameters:
- per_cpu (boolean, default: false): Whether to return data for each core
2. Memory Information
Tool: get_memory_info
Description: Get system memory usage information
Parameters: None
3. Disk Information
Tool: get_disk_info
Description: Get disk usage information
Parameters:
- path (string, default: "/"): Specify the disk path to query
- all_partitions (boolean, default: false): Whether to return information for all partitions
4. Network Information
Tool: get_network_info
Description: Get network interface and traffic information
Parameters:
- interface (string, optional): Specify the network interface name to query
5. Host Information
Tool: get_host_info
Description: Get host system information
Parameters: None
6. Process Information
Tool: get_process_info
Description: Get process information
Parameters:
- pid (number, optional): Process ID to get detailed information for a specific process
- limit (number, default: 10): Limit the number of processes returned
- sort_by (string, default: "cpu"): Sort field (cpu, memory, pid, name)
Installation
git clone https://github.com/seekrays/mcp-monitor.git
cd mcp-monitor
make build
Usage
Run the compiled binary:
./mcp-monitor
The server starts in stdio mode, ready to communicate with an MCP-compatible LLM client.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Files in the repo
- .github
- cpu
- disk
- doc
- host
- memory
- network
- process
- .gitignore
- .goreleaser.yml
- Dockerfile
- Dockerfile.goreleaser
- go.mod
- go.sum
- LICENSE
- main.go
- Makefile
- README.md
- utils.go
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.