Create MCP Prompts

Creating MCP Prompts

MCP prompts are implemented using scripts written in QPR ProcessAnalyzer expression language. A script will be added as the MCP prompt when the MCP prompt option is selected in the Script Properties. Only system administrator users can enable the MCP prompt option. Also, only system administrators can modify scripts that are MCP prompts, because any changes to the MCP interface is restricted to system administrators for security reasons.

To enable a script as an MCP Prompt:

1. Log in to QPR ProcessAnalyzer as a System Administrator.
2. Open or create the script.
3. For the script to be used as an MCP prompt, give it a name. This name is then used as the MCP tool name. It is important to ensure that every script intended for MCP use has a non-empty, valid name, as clients may fail to discover tools with invalid names. The maximum length of the name is 50 characters.
4. Open the properties of the script.
5. Switch to the MCP tab and select the MCP tool option.
6. Switch to the Description tab and provide a description. The description is added to the context of the client.

MCP Prompt Settings

The prompt description is a concise metadata field that gives an AI agent instructions on how to achieve complex tasks. When a prompt is called, the associated script is executed and the result is returned as a prompt message.

Every script can define its own prompt configuration as JSON. Supported values are same as https://modelcontextprotocol.io/specification/2025-11-25/server/prompts#prompt, except for the name which is always generated automatically and can't be overridden. Defining the prompt configuration will override any default configurations generated for scripts automatically by QPR ProcessAnalyzer. For example, specifying the value for "title" here will override the default functionality of using script's name as title of the tool.

In addition to the name of the prompt, MCP prompts provide the following information to the MCP client:

• title: Title of the prompt. Uses the script's title by default.
• description: Description of the prompt. Uses the script's description by default.
• arguments: Following arguments are available to indicate about the MCP prompt:
  • 'name (required, string): The argument name.
  • description (optional, string): A human-readable description of the argument.
  • required (optional, boolean): Whether the argument must be provided.
• icons: Same as icons for MCP tools.
• meta: Metadata about the prompt.

Example: a full MCP prompt configuration:

{
  "title": "Text Summarizer",
  "description": "Generates a concise summary of the provided text",
  "arguments": [
    {
      "name": "text",
      "description": "The text content to summarize",
      "required": true
    },
    {
      "name": "maxLength",
      "description": "Maximum length of the summary in characters",
      "required": false
    }
  ],
  "icons": [
    {
      "src": "https://example.com/icons/summarize.svg",
      "mimeType": "image/svg+xml",
      "sizes": ["any"],
      "theme": "light"
    }
  ],
  "meta": {
    "category": "text-processing"
  }
}