Which servers use `npx -y`?
12 servers in the configuration use `npx -y` as their command type.
@carloslluberes
Basic information
Working MCP server configurations for Claude - 16 servers functional
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This repository contains the working configuration for Claude MCP servers after extensive testing, including 16 validated servers. It is intended for users setting up the Claude desktop application with Model Context Protocol servers, providing configuration files and a guide detailing command types, lessons learned, and error avoidance.
Use claude-desktop-config.json as your working configuration. Consult MCP-WORKING-CONFIG-GUIDE.md for step‑by‑step setup and lessons learned, and server-command-reference.json to quickly determine the correct command (npx, uvx, or node) for each server.
12 servers in the configuration use `npx -y` as their command type.
Three servers (fetch, time, and cli) require the full path `/Users/carloslluberes/.local/bin/uvx` and will fail if run with npx.
The Mailgun server uses `node`.
The `desktop-commander` server does not exist under the package name `@modelcontextprotocol/server-desktop-commander`, and the `fetch` server fails when invoked with npx instead of uvx.
Starting from 9 servers, 7 were added, for a total of 16 working servers, with 2 known failures out of the attempted servers.
NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure
GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,

Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup

Docs: https://botchelor.com/agents and https://botchelor.com/llms.txt . Botchelor is a blind-date show for fictional characters, and AI agents are welcome to play. Over MCP, your agent builds an original character in w
FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil
Comments