MCP Tool Examples - Revision history

Ollvihe: /* Model filters */

2026-04-24T13:27:50Z

Model filters

← Older revision		Revision as of 13:27, 24 April 2026
Line 168:		Line 168:

	== Model filters ==		== Model filters ==
	Returns all public [[Filtering_in_QPR_ProcessAnalyzer#Saving_filters\|filters]] stored to a model. The ~~case ID is provided as an MCP~~ parameter~~, so~~ the ~~following '''Input''' configuration is needed~~:		Returns all public [[Filtering_in_QPR_ProcessAnalyzer#Saving_filters\|filters]] stored to a model.

			The modelId input parameter defines the model from where to get the filters:
	<syntaxhighlight lang="json" line>		<syntaxhighlight lang="json" line>
	{		{
Line 182:		Line 184:
	</syntaxhighlight>		</syntaxhighlight>

	~~Optionally, output~~ schema ~~can~~ be defined:		Output schema will be defined as follows:
	<syntaxhighlight lang="json" line>		<syntaxhighlight lang="json" line>

	{		{
	"type": "object",		"type": "object",
Line 189:		Line 192:
	"filters": {		"filters": {
	"type": "array",		"type": "array",
	"description": "~~Array~~ of filters",		"description": "List of defined filters in the given model (as parameter).",
	"items": {		"items": {
	"type": "object",		"type": "object",
Line 195:		Line 198:
	"Filter name": {		"Filter name": {
	"type": "string",		"type": "string",
	"description": "~~Name~~ of the filter"		"description": "Human-readable name of the filter."
	},		},
	"Filter ID": {		"Filter ID": {
	"type": "integer",		"type": "integer",
	"description": "Id of the filter"		"description": "Unique identifier of the filter."
	},		},
	"Privacy mode": {		"Privacy mode": {
Line 207:		Line 210:
	"Private"		"Private"
	],		],
	"description": "~~Privacy mode~~ of the filter"		"description": "Visibility and access level of the filter."
	},		},
	"Filter description": {		"Filter description": {
	"type": "string",		"type": "string",
	"description": "~~Free~~ text description of the filter"		"description": "Optional free-text description explaining the purpose and intended use of the filter."
	},		},
	"Filter rules": {		"Filter rules": {
	"type": "string",		"type": "string",
	"description": "Filter ~~rules~~ in ~~json~~ format. ~~Rules describe the precise criateria what~~ the ~~filter is filtering~~."		"description": "Filter definition expressed in JSON format. The rules specify the exact criteria used to include or exclude data."
	}		}
	}		}

Ollvihe: /* Model filters */

2026-04-24T13:24:44Z

Model filters

@@ Line 177: / Line 177: @@
        "type": "integer",
        "description": "Model ID (identifier)"
+     }
+   }
@@ Line 218: / Line 260: @@
 }).Collect();
-return result.ToCsv();
+return #{
 </syntaxhighlight>

Ollvihe: /* Case details */

2026-04-24T13:11:12Z

Case details

← Older revision		Revision as of 13:11, 24 April 2026
Line 166:		Line 166:
	* The script uses the ''CaseId'' variable containing the provided CaseId parameter value (which is generated by the calling agent).		* The script uses the ''CaseId'' variable containing the provided CaseId parameter value (which is generated by the calling agent).
	* The model ID is hardcoded, but the model ID can also be provided as an MCP parameter.		* The model ID is hardcoded, but the model ID can also be provided as an MCP parameter.

			== Model filters ==
			Returns all public [[Filtering_in_QPR_ProcessAnalyzer#Saving_filters\|filters]] stored to a model. The case ID is provided as an MCP parameter, so the following '''Input''' configuration is needed:
			<syntaxhighlight lang="json" line>
			{
			"type": "object",
			"additionalProperties": false,
			"properties": {
			"modelId": {
			"type": "integer",
			"description": "Model ID (identifier)"
			}
			}
			}
			</syntaxhighlight>

			The MCP tool script that returns list of filters in the given model ID:
			<syntaxhighlight lang="typescript" line>
			let result = Query(#{
			"Dimensions": null,
			"Values": [
			#{
			"Name": "Filter name",
			"Expression": "Name"
			},
			#{
			"Name": "Filter ID",
			"Expression": "Id"
			},
			#{
			"Name": "Privacy mode",
			"Expression": "switch (PublishMode) { case \"Public\": return \"Public\"; case \"Private\": return \"Private\"; case \"ModelDefault\": return \"Default Public\"; }"
			},
			#{
			"Name": "Filter description",
			"Expression": "Description"
			},
			#{
			"Name": "Filter rules",
			"Expression": "Rules == null ? null : ToJson(Rules)"
			}
			],
			"Ordering": [
			#{
			"Name": "Filter ID",
			"Direction": "Ascending"
			}
			],
			"Root": `ModelById(${modelId}).Filters`,
			"ContextType": "generic"
			}).Collect();

			return result.ToCsv();
			</syntaxhighlight>

Ollvihe: /* Case details */

2026-04-24T09:35:56Z

Case details

← Older revision		Revision as of 09:35, 24 April 2026
Line 87:		Line 87:
	}		}
	</syntaxhighlight>		</syntaxhighlight>
			The above schema means that there is one input parameter named ''CaseId'' containing a textual value (which cannot be null or an empty string). In addition, no other parameters are accepted ("additionalProperties": false).

	The tool script that returns details of a case ID including all case attribute values:		The tool script that returns details of a case ID including all case attribute values:

Ollvihe: /* Case details */

2026-04-24T09:34:06Z

Case details

← Older revision		Revision as of 09:34, 24 April 2026
Line 163:		Line 163:

	Notes:		Notes:
	~~- Note that the~~ script ~~has~~ the ''CaseId'' variable containing the provided CaseId parameter.		* The script uses the ''CaseId'' variable containing the provided CaseId parameter value (which is generated by the calling agent).
	- The model ID is hardcoded ~~in this example~~, but the model ID can also be provided as an MCP parameter.		* The model ID is hardcoded, but the model ID can also be provided as an MCP parameter.

Ollvihe: /* Case details */

2026-04-24T09:32:52Z

Case details

← Older revision		Revision as of 09:32, 24 April 2026
Line 88:		Line 88:
	</syntaxhighlight>		</syntaxhighlight>

	The tool script:		The tool script that returns details of a case ID including all case attribute values:
	<syntaxhighlight lang="typescript" line>		<syntaxhighlight lang="typescript" line>
	let ~~result~~ = ~~Query(#{~~		let modelId = 1;
	~~"Dimensions": null,~~		let dataQuery = [
	~~"Values":~~ [
	#{		#{
	"Name": "Start time",		"Name": "Start time",
Line 125:		Line 124:
	"Expression": "AggregateFrom(Events, #{\"Function\":\"Array\",\"Ordering\":[TimeStamp, EventType]}, EventType, null)"		"Expression": "AggregateFrom(Events, #{\"Function\":\"Array\",\"Ordering\":[TimeStamp, EventType]}, EventType, null)"
	}		}
	],		];

			let caseAttributes = ModelById(modelId).CasesDatatable.Columns.Name.{
			let caseAttributeName = _;
			dataQuery = Concat(dataQuery, #{
			"Name": caseAttributeName,
			"Expression": `Column(${ToJson(caseAttributeName)})`
			});
			};

			let result = Query(#{
			"Dimensions": null,
			"Values": dataQuery,
	"MaximumRowCount": 1,		"MaximumRowCount": 1,
	"Root": "Cases",		"Root": "Cases",
Line 137:		Line 148:
	"Attribute": "Case Name",		"Attribute": "Case Name",
	"StringifiedValues": [		"StringifiedValues": [
	"0" + ~~CaseId~~		"0" + orderID
	]		]
	}		}
Line 144:		Line 155:
	]		]
	},		},
	"ModelId": 1,		"ModelId": modelId,
	"ContextType": "model",		"ContextType": "model",
	"ProcessingMethod": "dataframe"		"ProcessingMethod": "dataframe"
	}).Collect();		}).Collect();

	return result.ToCsv();		return result.ToCsv();
	</syntaxhighlight>		</syntaxhighlight>

Ollvihe: /* Case details */

2026-04-24T09:17:45Z

Case details

← Older revision		Revision as of 09:17, 24 April 2026
Line 73:		Line 73:

	== Case details ==		== Case details ==
	Returns ~~the specified~~ details of a ~~specified~~ case. The case ID is provided as parameter, so the following ~~input~~ configuration is needed:		Returns details of a specific case. The case ID is provided as an MCP parameter, so the following '''Input''' configuration is needed:
	<syntaxhighlight lang="json" line>		<syntaxhighlight lang="json" line>
	{		{
Line 116:		Line 116:
	"Name": "Event types count",		"Name": "Event types count",
	"Expression": "Coalesce(AggregateFrom(Events, \"CountDistinct\", EventType, null), 0)"		"Expression": "Coalesce(AggregateFrom(Events, \"CountDistinct\", EventType, null), 0)"
	},
	#{
	~~"Name": "Customer Group",~~
	~~"Expression": "Column(\"Customer Group\")"~~
	},
	#{
	~~"Name": "Supplier",~~
	~~"Expression": "Column(\"Supplier\")"~~
	},
	#{
	~~"Name": "Product Group",~~
	~~"Expression": "Column(\"Product Group\")"~~
	},
	#{
	~~"Name": "Account Manager",~~
	~~"Expression": "Column(\"Account Manager\")"~~
	},		},
	#{		#{
Line 168:		Line 152:
	</syntaxhighlight>		</syntaxhighlight>

	Note that the script has the ''CaseId'' variable containing the provided CaseId parameter.		Notes:
			- Note that the script has the ''CaseId'' variable containing the provided CaseId parameter.
	The model ID is hardcoded in this example, but the model ID can also be provided as an MCP parameter.		- The model ID is hardcoded in this example, but the model ID can also be provided as an MCP parameter.

Ollvihe at 09:15, 24 April 2026

2026-04-24T09:15:17Z

← Older revision		Revision as of 09:15, 24 April 2026
Line 71:		Line 71:
	return result.ToCsv();		return result.ToCsv();
	</syntaxhighlight>		</syntaxhighlight>

			== Case details ==
			Returns the specified details of a specified case. The case ID is provided as parameter, so the following input configuration is needed:
			<syntaxhighlight lang="json" line>
			{
			"type": "object",
			"additionalProperties": false,
			"properties": {
			"CaseId": {
			"type": "string",
			"minLength": 1,
			"description": "Unique identifier of the case (i.e, Case ID). Cases may be orders, deliveries, invoices depending on the model name."
			}
			}
			}
			</syntaxhighlight>

			The tool script:
			<syntaxhighlight lang="typescript" line>
			let result = Query(#{
			"Dimensions": null,
			"Values": [
			#{
			"Name": "Start time",
			"Expression": "AggregateFrom(Events, \"Min\", TimeStamp, null)"
			},
			#{
			"Name": "End time",
			"Expression": "AggregateFrom(Events, \"Max\", TimeStamp, null)"
			},
			#{
			"Name": "Duration in hours",
			"Expression": "DurationBetweenDates(\"hour\", AggregateFrom(Events, \"Min\", TimeStamp, null), AggregateFrom(Events, \"Max\", TimeStamp, null), null)"
			},
			#{
			"Name": "Latest event",
			"Expression": "AggregateFrom(Events.WithRowNumberColumn(\"RowNumber\", [TimeStamp, EventType], [CaseId], [false, false]).Where(Column(\"RowNumber\") == 1), \"Any\", EventType, null)"
			},
			#{
			"Name": "Event count",
			"Expression": "Coalesce(AggregateFrom(Events, \"Count\", null, null), 0)"
			},
			#{
			"Name": "Event types count",
			"Expression": "Coalesce(AggregateFrom(Events, \"CountDistinct\", EventType, null), 0)"
			},
			#{
			"Name": "Customer Group",
			"Expression": "Column(\"Customer Group\")"
			},
			#{
			"Name": "Supplier",
			"Expression": "Column(\"Supplier\")"
			},
			#{
			"Name": "Product Group",
			"Expression": "Column(\"Product Group\")"
			},
			#{
			"Name": "Account Manager",
			"Expression": "Column(\"Account Manager\")"
			},
			#{
			"Name": "Repeating event types",
			"Expression": "Coalesce(AggregateFrom(Events, \"Count\", null, null), 0) - Coalesce(AggregateFrom(Events, \"CountDistinct\", EventType, null), 0)"
			},
			#{
			"Name": "Variation path",
			"Expression": "AggregateFrom(Events, #{\"Function\":\"Array\",\"Ordering\":[TimeStamp, EventType]}, EventType, null)"
			}
			],
			"MaximumRowCount": 1,
			"Root": "Cases",
			"Filter": #{
			"Items": [
			#{
			"Type": "IncludeCases",
			"Items": [
			#{
			"Type": "CaseAttributeValue",
			"Attribute": "Case Name",
			"StringifiedValues": [
			"0" + CaseId
			]
			}
			]
			}
			]
			},
			"ModelId": 1,
			"ContextType": "model",
			"ProcessingMethod": "dataframe"
			}).Collect();

			return result.ToCsv();
			</syntaxhighlight>

			Note that the script has the ''CaseId'' variable containing the provided CaseId parameter.

			The model ID is hardcoded in this example, but the model ID can also be provided as an MCP parameter.

Ollvihe at 00:40, 17 April 2026

2026-04-17T00:40:02Z

← Older revision		Revision as of 00:40, 17 April 2026
Line 1:		Line 1:
	This page contains example scripts ~~that can be used~~ as MCP tools.		This page contains example scripts intended for use as MCP tools. When developing MCP tool scripts, make sure they return a string value, as this is required for the MCP client's LLM to interpret the output correctly.

	~~Make sure to create the~~ MCP tool scripts ~~in a way that~~ they return a string value.

	== List of Models ==		== List of Models ==

Ollvihe: /* Average case cost in specific model */

2026-04-17T00:37:35Z

Average case cost in specific model

← Older revision		Revision as of 00:37, 17 April 2026
Line 55:		Line 55:

	== Average case cost in specific model ==		== Average case cost in specific model ==
	Returns an average case Cost attribute value of all cases in a model with ID 1.		Returns the average of the case Cost attribute value of all cases in the model with ID 1.
	<syntaxhighlight lang="typescript" line>		<syntaxhighlight lang="typescript" line>
	let result = Query(#{		let result = Query(#{