MCP Test Servers

@msfeldstein

Basic information

About MCP Test Servers

No overview available yet

MCP Test Servers config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "test-server": {
      "command": "/Users/feldstein/Source/mcp-test-servers/src/cli.js",
      "args": [
        "ping"
      ],
      "env": {}
    }
  }
}

MCP Test Servers tools

Tool 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.

Overview

What is MCP Test Servers?

MCP Test Servers is a collection of test servers implementing the Model Context Protocol (MCP). It provides over 50 pre-built servers for testing MCP features, from basic tool calls to complex OAuth flows and schema edge cases, aimed at developers validating MCP client behavior.

How to use MCP Test Servers?

Run any server with npx -y @msfeldstein/mcp-test-servers <server>, e.g. npx @msfeldstein/mcp-test-servers everything. A gallery page with one-click install buttons for Cursor is available at the GitHub Pages link. Configure the server in mcpServers JSON with the command and optional environment variables.

Key features of MCP Test Servers

Includes 50+ specialized test servers for MCP features
Tests tools, resources, prompts, and elicitation flows
Covers schema edge cases, OAuth, and session management
Automated testing via /test-everything slash command in Cursor
Quick install via GitHub Pages gallery for Cursor
Supports dynamic tools, progress notifications, and mixed content responses

Use cases of MCP Test Servers

Validate MCP client handling of malformed or broken server schemas
Test OAuth 2.0 discovery and bug reproduction flows
Verify progress notifications and long-running task behavior
Ensure proper handling of environment variables and MCP roots
Debug resource listing, prompt generation, and content type variations

Frequently asked questions

What dependencies are required to run MCP Test Servers?

Node.js and npx are required. No additional dependencies are needed—servers are fetched via npm.

How do I test the `everything` server comprehensively?

Start the `everything` server, then in Cursor use the `/test-everything` slash command. The AI agent will automatically execute all 20 test steps and provide a validation report.

Can I test OAuth flow issues?

Yes—servers like `oauth-repro`, `oauth-debug`, `oauth-callback-test`, `oauth-edge-case`, and `oauth-bug-trigger` are included to reproduce specific OAuth 2.0 discovery and callback bugs.

Where does the server’s data live?

No persistent data storage is used. All servers are stateless and run in memory; environment variables and MCP roots are provided by the client.

What transports are supported?

Servers use standard MCP transport (stdio by default). The `sse-timeout` and `session-management` servers demonstrate Streamable HTTP with SSE and session tracking.

Comments

More Developer Tools MCP servers

Official Porkbun MCP Server

Porkbun LLC

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

MCP Server By TestMu AI

TestMu AI

TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche

Agent Conductor

icohangar-ops

Agent conductor — AGENTS.md contract parser, SKILL.md registry, CHP decision engine over MCP

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.