Partition Tools Declaration

The Pricefx MCP Server can detect tools declared in a partition and make them available to its clients. A partition tool is essentially a Groovy function that can be invoked with parameters.

Configuration

The MCP Server reads tool declarations from the Advanced Configuration Options on the partition. For a tool to be detected and used by the MCP Server, it must be described by a JSON object that meets the following requirements:

• The option name must be prefixed with MCP_tool_, for example MCP_tool_models_list. Try to use the same value in the JSON name field.

• The JSON must follow the MCP tool structure:

  JSON

  {
    "name": "models_list", // Tool's name
    "title": "Models: List", // Tool's readable name
    "description": "Lists models filtered by model class", // What the tool does
    "formulaName": "MCP_Commons", // Groovy logic containing the code
    "elementName": "Models", // Element containing the function
    "functionName": "list", // Function to call
    "inputSchema": { // Parameters of the function
      "properties": {
        "modelClassUN": {
          "type": "string",
          "description": "Model class unique name"
        }
      }
    },
    "outputSchema": { // Description of the expected result from the call
      "properties": {
        "models": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "Model metadata objects"
        }
      }
    }
  }
  

Input and Output Schema Type Definitions

The formats used to define property types in inputSchema and outputSchema are currently limited to the following subset of JSON Schema:

"type": "string"

"type": "integer"

"type": "number"

"type": "boolean"

"type": "object"

"type": "string",
"format": "date"

"type": "string",
"format": "date-time"

"type": "array",
"items": {
  [T Format]
}

"type": "object",
"additionalProperties": {
  [T Format]
}

Examples

"type": "array",
"items": {
  "type": "number"
}

"type": "array",
"items": {
  "type": "string",
  "format": "date"
}

"type": "object",
"additionalProperties": {
  "type": "boolean"
}

"type": "object",
"additionalProperties": {
  "type": "string",
  "format": "date-time"
}

"type": "object",
"additionalProperties": {
  "type": "object",
  "additionalProperties": {
    "type": "integer"
  }
}