How to choose
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 io.github.om-tajne/pkgdiet MCP server?
Put your node_modules on a diet - find unused dependencies, analyze health, and reduce size
How to install io.github.om-tajne/pkgdiet
Copy-paste configuration for popular MCP clients.
transport: stdio
Config generated by PluginBench — verify against the source before use.~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
"mcpServers": {
"pkgdiet": {
"command": "npx",
"args": [
"-y",
"pkgdiet"
]
}
}
}Related MCP servers
RO

ROOT MCP Server
Stale
ROOT-based MCP server exposing root_python and root_cpp tools (stdio transport).
1
View repository →Python
BSD-2-Clause
GR

Compile any codebase into a walkable graph and serve it over MCP. No model decides an edge.
View repository →Single MCP hub: discover, add, audit, and govern MCP servers across every AI client.
1
View repository →TypeScript
MIT
MCP server for Tinify image optimization — one tool, max optimization
2
View repository →TypeScript
MIT
x402-gated weather and FX exchange rate data endpoints for AI agents.
HU

hush
Active
Team secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.
1
View repository →TypeScript
MIT

