Create MCP Tools - Revision history

TeeHiet: TK-64701

2026-05-27T11:32:44Z

TK-64701

← Older revision		Revision as of 11:32, 27 May 2026
Line 1:		Line 1:
	== Creating MCP Tools ==		== Creating MCP Tools ==
	MCP tools are implemented using [[Managing_Scripts\|scripts]] written in QPR ProcessAnalyzer expression language. A script will be added as the MCP tool when the '''MCP tool''' option is selected in the [[Managing_Scripts#Script_Properties\|Script Properties]]. Only system administrator users can enable the MCP tool ~~checkbox~~. Also, scripts that are MCP tools, ~~only system administrators can modify them~~ because any changes to the MCP interface is restricted to system administrators for security reasons.		MCP tools are implemented using [[Managing_Scripts\|scripts]] written in QPR ProcessAnalyzer expression language. A script will be added as the MCP tool when the '''MCP tool''' option is selected in the [[Managing_Scripts#Script_Properties\|Script Properties]]. Only system administrator users can enable the MCP tool option. Also, only system administrators can modify scripts that are MCP tools, because any changes to the MCP interface is restricted to system administrators for security reasons.

	To enable a script as an MCP Tool:		To enable a script as an MCP Tool:

TeeHiet: TK-64701

2026-05-27T11:30:17Z

TK-64701

← Older revision		Revision as of 11:30, 27 May 2026
Line 1:		Line 1:
	== Creating MCP Tools ==		== Creating MCP Tools ==
	MCP tools are implemented using [[Managing_Scripts\|scripts]] written in QPR ProcessAnalyzer expression language. A script will be added as the MCP tool when the '''MCP tool''' ~~checkbox~~ is ~~enabled~~ in the [[Managing_Scripts#Script_Properties\|Script Properties]]. Only system administrator users can enable the MCP tool checkbox. Also, scripts that are MCP tools, only system administrators can modify them because any changes to the MCP interface is restricted to system administrators for security reasons.		MCP tools are implemented using [[Managing_Scripts\|scripts]] written in QPR ProcessAnalyzer expression language. A script will be added as the MCP tool when the '''MCP tool''' option is selected in the [[Managing_Scripts#Script_Properties\|Script Properties]]. Only system administrator users can enable the MCP tool checkbox. Also, scripts that are MCP tools, only system administrators can modify them because any changes to the MCP interface is restricted to system administrators for security reasons.

	To enable a script as an MCP Tool:		To enable a script as an MCP Tool:
Line 7:		Line 7:
	# For the script to be used as an MCP tool, 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.		# For the script to be used as an MCP tool, 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.
	# Open the properties of the script.		# Open the properties of the script.
	# Switch to the '''MCP''' tab and select the '''MCP tool''' ~~checkbox~~.		# Switch to the '''MCP''' tab and select the '''MCP tool''' option.
	# Switch to the '''Description''' tab and provide a description. The description is added to the context of the client.		# Switch to the '''Description''' tab and provide a description. The description is added to the context of the client.

TeeHiet: TK-64701

2026-05-27T11:20:50Z

TK-64701

@@ Line 126: / Line 126: @@
          "readOnlyHint": false
+     }
+}
 </syntaxhighlight>

TeeHiet: TK-64701

2026-05-27T10:51:35Z

TK-64701

← Older revision		Revision as of 10:51, 27 May 2026
Line 71:		Line 71:

	=== Structured Tool Output ===		=== Structured Tool Output ===
	Structured tool output is described using a JSON schema following the [https://modelcontextprotocol.io/specification/2025-11-25/basic#json-schema-usage Model Context Protocol's JSON Schema]. By default, scripts don't enforce any schema and the result is considered to be just text.		Structured tool output is described using a JSON schema following the [https://modelcontextprotocol.io/specification/2025-11-25/basic#json-schema-usage Model Context Protocol's JSON Schema]. By default, scripts don't enforce any schema and the result is considered to be just text. Due to the limitations of MCP protocol, if defined, the top-level object type should be "object".

	Example: The following example configures the script's return value to contain an object having the "models" property with information about each model:<syntaxhighlight lang="json">		Example: The following example configures the script's return value to contain an object having the "models" property with information about each model:<syntaxhighlight lang="json">

Ollvihe: /* MCP Tool Settings */

2026-05-18T21:54:41Z

MCP Tool Settings

← Older revision		Revision as of 21:54, 18 May 2026
Line 19:		Line 19:
	It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively. During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:		It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively. During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:
	* Every character in every description costs tokens – across all tools, not just the one ultimately selected.		* Every character in every description costs tokens – across all tools, not just the one ultimately selected.
	* Long descriptions risk truncation – some implementations silently cut off descriptions beyond ~~1,024–2,048~~ characters, potentially hiding critical information.		* Long descriptions risk truncation – some implementations silently cut off descriptions beyond 1000–2000 characters, potentially hiding critical information.
	* Agents perform better with clear, concise signals – verbose descriptions introduce noise that can confuse tool selection.		* Agents perform better with clear, concise signals – verbose descriptions introduce noise that can confuse tool selection.

Ollvihe: /* MCP Tool Description */

2026-05-18T21:54:26Z

MCP Tool Description

← Older revision		Revision as of 21:54, 18 May 2026
Line 14:		Line 14:
	=== MCP Tool Description ===		=== MCP Tool Description ===
	The tool description is a concise metadata field that tells an AI agent what a tool does and when it should be used. It serves as the primary signal during the agent's planning and routing phase, where the agent decides which tool (if any) to call in response to a user's request. The tool description answers two questions for the agent:		The tool description is a concise metadata field that tells an AI agent what a tool does and when it should be used. It serves as the primary signal during the agent's planning and routing phase, where the agent decides which tool (if any) to call in response to a user's request. The tool description answers two questions for the agent:
	* What does this tool do? — A brief explanation of the tool's capability.		* What does this tool do? – A brief explanation of the tool's capability.
	* When should the agent use it? — The conditions, scenarios, or trigger signals that indicate this tool is the right choice.		* When should the agent use it? – The conditions, scenarios, or trigger signals that indicate this tool is the right choice.

	It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively. During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:		It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively. During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:
	* Every character in every description costs tokens — across all tools, not just the one ultimately selected.		* Every character in every description costs tokens – across all tools, not just the one ultimately selected.
	* Long descriptions risk truncation — some implementations silently cut off descriptions beyond 1,024–2,048 characters, potentially hiding critical information.		* Long descriptions risk truncation – some implementations silently cut off descriptions beyond 1,024–2,048 characters, potentially hiding critical information.
	* Agents perform better with clear, concise signals — verbose descriptions introduce noise that can confuse tool selection.		* Agents perform better with clear, concise signals – verbose descriptions introduce noise that can confuse tool selection.

	=== Input Parameters ===		=== Input Parameters ===

Ollvihe: /* MCP Tool Description */

2026-05-18T21:53:26Z

MCP Tool Description

← Older revision		Revision as of 21:53, 18 May 2026
Line 13:		Line 13:

	=== MCP Tool Description ===		=== MCP Tool Description ===
	The tool description is a concise metadata field that tells an AI agent what a tool does and when it should be used. It serves as the primary signal during the agent's planning and routing phase, where the agent decides which tool (if any) to call in response to a user's request.		The tool description is a concise metadata field that tells an AI agent what a tool does and when it should be used. It serves as the primary signal during the agent's planning and routing phase, where the agent decides which tool (if any) to call in response to a user's request. The tool description answers two questions for the agent:

	The tool description answers two questions for the agent:
	* What does this tool do? — A brief explanation of the tool's capability.		* What does this tool do? — A brief explanation of the tool's capability.
	* When should the agent use it? — The conditions, scenarios, or trigger signals that indicate this tool is the right choice.		* When should the agent use it? — The conditions, scenarios, or trigger signals that indicate this tool is the right choice.

	It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively.		It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively. During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:

	During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:
	* Every character in every description costs tokens — across all tools, not just the one ultimately selected.		* Every character in every description costs tokens — across all tools, not just the one ultimately selected.
	* Long descriptions risk truncation — some implementations silently cut off descriptions beyond 1,024–2,048 characters, potentially hiding critical information.		* Long descriptions risk truncation — some implementations silently cut off descriptions beyond 1,024–2,048 characters, potentially hiding critical information.

Ollvihe: /* MCP Tool Settings */

2026-05-18T21:52:58Z

MCP Tool Settings

← Older revision		Revision as of 21:52, 18 May 2026
Line 11:		Line 11:

	== MCP Tool Settings ==		== MCP Tool Settings ==

			=== MCP Tool Description ===
			The tool description is a concise metadata field that tells an AI agent what a tool does and when it should be used. It serves as the primary signal during the agent's planning and routing phase, where the agent decides which tool (if any) to call in response to a user's request.

			The tool description answers two questions for the agent:
			* What does this tool do? — A brief explanation of the tool's capability.
			* When should the agent use it? — The conditions, scenarios, or trigger signals that indicate this tool is the right choice.

			It does not need to explain how to format inputs or how to interpret outputs — those concerns belong to the input parameter descriptions and output schema descriptions, respectively.

			During planning, agents load all available tool descriptions into their context simultaneously to evaluate which tool best fits the task. This means:
			* Every character in every description costs tokens — across all tools, not just the one ultimately selected.
			* Long descriptions risk truncation — some implementations silently cut off descriptions beyond 1,024–2,048 characters, potentially hiding critical information.
			* Agents perform better with clear, concise signals — verbose descriptions introduce noise that can confuse tool selection.

	=== Input Parameters ===		=== Input Parameters ===

Ollvihe: /* MCP Tool Metadata */

2026-05-17T17:34:54Z

MCP Tool Metadata

← Older revision		Revision as of 17:34, 17 May 2026
Line 101:		Line 101:
	Every script can define its own '''McpTool''' configuration as JSON. Supported values are same as [https://modelcontextprotocol.io/specification/2025-11-25/server/tools#tool here], except for the '''name''' which is always generated automatically and can't be overridden. Defining the McpTool 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.		Every script can define its own '''McpTool''' configuration as JSON. Supported values are same as [https://modelcontextprotocol.io/specification/2025-11-25/server/tools#tool here], except for the '''name''' which is always generated automatically and can't be overridden. Defining the McpTool 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.

	Following annotations are available:		Following annotations are available to indicate about the MCP tool:
	* '''destructiveHint''': ~~Indicates that the~~ MCP tool call deletes data which might be permanently lost. Some LLM agents ask for confirmation from the user, to make sure that destructive tool calls are not made by mistake.		* '''destructiveHint''': MCP tool call deletes data which might be permanently lost. Some LLM agents ask for confirmation from the user, to make sure that destructive tool calls are not made by mistake.
	* '''idempotentHint''': ~~Indicates that all~~ MCP tool calls with the same parameters always provide the same result. Some LLM agents may cache tool call results for idempotent MCP tools to improve performance and reduce load from the MCP server.		* '''idempotentHint''': All MCP tool calls with the same parameters always provide the same result. Some LLM agents may cache tool call results for idempotent MCP tools to improve performance and reduce load from the MCP server.
	* '''openWorldHint''': ~~Indicates that all~~ MCP tool call in the MCP server will use external services. Open world tool calls are expected to be slower than ~~usually~~.		* '''openWorldHint''': MCP tool call in the MCP server will use some external services. Open world tool calls are expected to be slower than other tool calls.
	* '''readOnlyHint''': ~~Indicates that all~~ MCP tool call does not change any data, and thus the call may not have any potentially undesired effects. Some LLM agents ask for confirmation from the user, to make sure that tool calls that change data are not made by mistake.		* '''readOnlyHint''': MCP tool call does not change any data, and thus the call may not have any potentially undesired effects. Some LLM agents ask for confirmation from the user, to make sure that tool calls that change data are not made by mistake.

	Example: The following JSON configures the MCP tool with a customized title and description, as well as some additional [https://github.com/modelcontextprotocol/csharp-sdk/blob/main/src/ModelContextProtocol.Core/Protocol/ToolAnnotations.cs MCP tool annotations]:<syntaxhighlight lang="json">		Example: The following JSON configures the MCP tool with a customized title and description, as well as some additional [https://github.com/modelcontextprotocol/csharp-sdk/blob/main/src/ModelContextProtocol.Core/Protocol/ToolAnnotations.cs MCP tool annotations]:<syntaxhighlight lang="json">

Ollvihe: /* MCP Tool Settings */

2026-05-17T17:33:23Z

MCP Tool Settings

← Older revision		Revision as of 17:33, 17 May 2026
Line 48:		Line 48:
	}		}
	}		}
	</syntaxhighlight>~~<br>~~		</syntaxhighlight>

	After this, the tool can be called, for example, with the following set of parameters:<syntaxhighlight lang="json">		After this, the tool can be called, for example, with the following set of parameters:<syntaxhighlight lang="json">
	{		{
Line 61:		Line 62:
	=== Structured Tool Output ===		=== Structured Tool Output ===
	Structured tool output is described using a JSON schema following the [https://modelcontextprotocol.io/specification/2025-11-25/basic#json-schema-usage Model Context Protocol's JSON Schema]. By default, scripts don't enforce any schema and the result is considered to be just text.		Structured tool output is described using a JSON schema following the [https://modelcontextprotocol.io/specification/2025-11-25/basic#json-schema-usage Model Context Protocol's JSON Schema]. By default, scripts don't enforce any schema and the result is considered to be just text.
	~~<br>~~
	~~'''~~Example~~'''~~: The following example configures the script's return value to contain an object having the "models" property with information about each model:<syntaxhighlight lang="json">		Example: The following example configures the script's return value to contain an object having the "models" property with information about each model:<syntaxhighlight lang="json">
	{		{
	"type": "object",		"type": "object",