Metadata-Version: 2.5
Name: mcp-local-telemetry
Version: 0.1.1
Summary: A lightweight MCP server that feeds local system telemetry to AI agents.
Project-URL: Homepage, https://github.com/Jamie643/mcp-local-telemetry
Project-URL: Issues, https://github.com/Jamie643/mcp-local-telemetry/issues
Author: Jamie643
License: MIT
License-File: LICENSE
Keywords: ai-agents,mcp,model-context-protocol,psutil,telemetry
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Requires-Dist: psutil<7,>=5.9
Provides-Extra: dev
Requires-Dist: mypy>=1.11; extra == 'dev'
Requires-Dist: pytest-cov>=5.0; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.6; extra == 'dev'
Requires-Dist: types-psutil>=5.9; extra == 'dev'
Description-Content-Type: text/markdown

# mcp-local-telemetry
[![CI](https://github.com/Jamie643/mcp-local-telemetry/actions/workflows/ci.yml/badge.svg)](https://github.com/Jamie643/mcp-local-telemetry/actions/workflows/ci.yml)
A lightweight [Model Context Protocol](https://modelcontextprotocol.io) server that
exposes local system telemetry (CPU, RAM, Disk, top processes) to MCP-aware AI
agents — Claude Code, Cursor, ChatGPT Desktop, and any other MCP client.

Written as a single-file, dependency-light Python script. Ships in under 200
lines and speaks JSON-RPC 2.0 over stdio.

## Why

AI coding agents are increasingly asked to reason about the machine they are
running on — *"is it safe to run this build?", "what's eating CPU right now?"*.
This server gives them a structured, protocol-standard way to ask.

## Tools

| Tool | Description |
| --- | --- |
| `get_system_metrics` | CPU %, memory %, disk %, load average, boot time. |
| `get_top_processes` | Top-N processes by CPU usage. |

## Install

```bash
git clone https://github.com/Jamie643/mcp-local-telemetry.git
cd mcp-local-telemetry
python -m venv .venv && source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install -e .
