Demo (Everything) MCP server

Test protocol features and tools for client compatibility.
Back to servers
Provider
Anthropic
Release date
Nov 19, 2024
Language
TypeScript
Package
Stats
31.0K downloads
43.7K stars

The MCP Everything server is a comprehensive test server for developers building MCP clients. It implements various MCP protocol features including prompts, tools, resources, and sampling to showcase the full range of MCP capabilities rather than serving as a production server.

Installation Options

Installing with NPX

You can quickly run the MCP Everything server using NPX:

npx -y @modelcontextprotocol/server-everything

Installing with Claude Desktop

To integrate with Claude Desktop, add the following to your claude_desktop_config.json file:

{
  "mcpServers": {
    "everything": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-everything"
      ]
    }
  }
}

Installing in VS Code

Manual Installation

Add the following configuration to your VS Code User Settings (JSON) file:

  1. Press Ctrl + Shift + P and type Preferences: Open User Settings (JSON)
  2. Add this configuration:
{
  "mcp": {
    "servers": {
      "everything": {
        "command": "npx",
        "args": ["-y", "@modelcontextprotocol/server-everything"]
      }
    }
  }
}

Alternatively, you can add it to .vscode/mcp.json in your workspace (without the mcp key).

Running with HTTP Transport Options

To run with Streamable HTTP Transport:

cd src/everything
npm install
npm run start:streamableHttp

To run with HTTP+SSE Transport (deprecated):

cd src/everything
npm install
npm run start:sse

Using the MCP Everything Server

Available Tools

The server provides the following tools:

Echo Tool

  • Echoes back the input message
  • Input parameter: message (string)

Add Tool

  • Adds two numbers together
  • Input parameters:
    • a (number)
    • b (number)

Long Running Operation

  • Demonstrates progress notifications
  • Input parameters:
    • duration (number, default: 10) - duration in seconds
    • steps (number, default: 5) - number of progress steps

Sample LLM

  • Demonstrates LLM sampling capability
  • Input parameters:
    • prompt (string) - the prompt to send to the LLM
    • maxTokens (number, default: 100) - maximum tokens to generate

Get Tiny Image

  • Returns a small test image
  • No input parameters required

Print Environment Variables

  • Prints all environment variables
  • No input parameters required

Annotated Message

  • Demonstrates content annotations with metadata
  • Input parameters:
    • messageType (enum: "error" | "success" | "debug")
    • includeImage (boolean, default: false)

Get Resource Reference

  • Returns a reference to a resource
  • Input parameter: resourceId (number, 1-100)

Working with Resources

The server provides 100 test resources:

  • Even-numbered resources (2, 4, 6...) are plaintext format with URI pattern: test://static/resource/{even_number}
  • Odd-numbered resources (1, 3, 5...) are binary blob format with URI pattern: test://static/resource/{odd_number}

Resources support:

  • Pagination (10 items per page)
  • Subscription to updates
  • Resource templates
  • Auto-updates every 5 seconds for subscribed resources

Using Prompts

The server offers three demo prompts:

Simple Prompt

  • Basic prompt without arguments
  • Returns a single message exchange

Complex Prompt

  • Demonstrates argument handling
  • Required parameter: temperature (number)
  • Optional parameter: style (string)
  • Returns a multi-turn conversation with images

Resource Prompt

  • Shows how to embed resource references
  • Required parameter: resourceId (number, 1-100)
  • Returns a multi-turn conversation with an embedded resource reference

Logging

The server sends random-leveled log messages every 15 seconds in the format:

{
  "method": "notifications/message",
  "params": {
    "level": "info",
    "data": "Info-level message"
  }
}

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later