This MCP server is designed to exercise all features of the Model Context Protocol (MCP), serving as a test platform for MCP client developers. It implements a variety of tools, resources, prompts, and other MCP capabilities to demonstrate how they work in practice.
You can easily integrate this test server with Claude Desktop by adding it to your configuration file:
claude_desktop_config.json
file{
"mcpServers": {
"everything": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-everything"
]
}
}
}
This configuration instructs Claude Desktop to run the server using NPX, which will automatically download and execute the package.
The server provides several tools that demonstrate different MCP capabilities:
echo: Returns the input message
// Input
{ "message": "Hello world" }
// Output: "Hello world"
add: Adds two numbers together
// Input
{ "a": 5, "b": 7 }
// Output: "12"
longRunningOperation: Demonstrates progress notifications
// Input
{ "duration": 15, "steps": 5 }
// Output includes progress notifications during execution
sampleLLM: Shows LLM sampling capability
// Input
{
"prompt": "Write a short poem about AI",
"maxTokens": 100
}
// Output: Generated LLM response
getTinyImage: Returns a small test image
// No input required
// Output: Base64 encoded PNG image
printEnv: Useful for debugging server configuration
// No input required
// Output: JSON string of all environment variables
annotatedMessage: Demonstrates content annotations with metadata
// Input
{
"messageType": "error",
"includeImage": true
}
// Output: Content with various annotations
getResourceReference: Returns a referenceable resource
// Input
{ "resourceId": 42 }
// Output: Resource reference with usage instructions
The server provides 100 test resources that can be accessed and manipulated:
test://static/resource/42
test://static/resource/43
Resources support:
The server offers several prompt templates to test client capabilities:
Basic prompt with no arguments:
// Call simple_prompt
// Returns a single message exchange
Advanced prompt with required and optional arguments:
// Call complex_prompt
{
"temperature": 0.7,
"style": "concise"
}
// Returns multi-turn conversation including images
Demonstrates embedding resource references:
// Call resource_prompt
{
"resourceId": 42
}
// Returns conversation with embedded resource reference
The server automatically sends random-level log messages every 15 seconds for testing notification handling:
{
"method": "notifications/message",
"params": {
"level": "info",
"data": "Info-level message"
}
}
These logs can be useful for testing how your client handles different notification types and priority levels.
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.
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"
]
}
}
}
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.
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.