What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the GPU Server MCP server?
MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
How to install GPU Server
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"mcp-gpu-server": {
"command": "uvx",
"args": [
"mcp-gpu-server"
]
}
}
}Related MCP servers

Colter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.
View repository →Navigate and query OpenAPI specs with fuzzy search, pagination, and API testing
View repository →
Embedded / IoT Mentor
Embedded/IoT mentor: picks the board and toolchain, estimates cost and battery life.

LibreNMS MCP
MCP server for LibreNMS network monitoring—query devices, ports, alerts, and manage infrastructure
No-key MCP server for steel equilibrium, TTT/CCT kinetics, phase-boundary and measured-data tools.
View repository →
Metabase
Search, explore, query, and visualize data in Metabase through AI agents.

