Pega DX MCP Server

save_assignment_action

Save assignment action form data without executing the action, preserving changes for later retrieval and continued editing.

Instructions

Save assignment action form data without executing the action. Implements "Save for later" functionality that preserves form data in progress so changes will not be lost when returned to the assignment. If no eTag is provided, automatically fetches the latest eTag from the assignment for seamless operation. Available for Connector actions like Collect info steps, screen flow assignments and customized approval steps. Required field validations are ignored - only server-side validations (dictionary validations) are performed. The saved form data can be retrieved later when the assignment is reopened for continued editing or action execution.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "assignmentID": "<assignmentID>",
      "actionID": "<actionID>"
    },
    "name": "save_assignment_action"
  }
}

Input Schema

Name	Required	Description
`eTag`	No	Optional. Auto-fetched if omitted. For faster execution, use eTag from previous response.
`content`	No	Optional map of scalar properties and embedded page properties containing form data to be saved. Only fields that are part of the assignment action's view can be saved. Field names should match the property names defined in the Pega application. Example: {"CustomerName": "John Doe", "RequestAmount": 5000, "Comments": "Initial request details"}. This data will be preserved and available when the assignment is reopened.
`actionID`	Yes	Action ID from assignment (Example: "pyApproval", "Submit"). CRITICAL: Action IDs are CASE-SENSITIVE and have no spaces even if display names do ("Complete Review" → "CompleteReview"). Use get_assignment to find correct ID from actions array - use "ID" field not "name" field.
`attachments`	No	Optional list of attachments to be added to specific attachment fields included in the assignment action's view during the save operation. Each attachment entry specifies the attachment details and target field. Only attachment fields included in the assignment action's view can be modified during save.
`assignmentID`	Yes	Assignment ID. Format: ASSIGN-WORKLIST {caseID}!{processID}. Example: "ASSIGN-WORKLIST MYORG-APP-WORK C-1001!PROCESS""ASSIGN-WORKLIST PBANK-LOAN-WORK V-76003!REVIEW_FLOW". This uniquely identifies the specific assignment instance where form data will be saved.
`originChannel`	No	Optional origin channel identifier for this service request. Indicates the source of the save request for tracking and audit purposes. Examples: "Web", "Mobile", "WebChat". Default value is "Web" if not specified.
`pageInstructions`	No	Optional list of page-related operations for embedded pages, page lists, or page groups. Required for setting embedded page references. Only pages included in the assignment action's view can be modified.
`sessionCredentials`	No	Optional session-specific credentials. If not provided, uses environment variables. Supports two authentication modes: (1) OAuth mode - provide baseUrl, clientId, and clientSecret, or (2) Token mode - provide baseUrl and accessToken.

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv1.0.0Jan 3, 2026

changedInput schema / properties / actionID / description

Previous value: -"Name of the assignment action - ID of the flow action rule for which form data is being saved. This corresponds to the Flow Action rule configured in the Pega application where the save functionality is available. Example: \"CompleteVerification\", \"CollectInformation\"."New value: +"Action ID from assignment (Example: \"pyApproval\", \"Submit\"). CRITICAL: Action IDs are CASE-SENSITIVE and have no spaces even if display names do (\"Complete Review\" → \"CompleteReview\"). Use get_assignment to find correct ID from actions array - use \"ID\" field not \"name\" field."

changedInput schema / properties / assignmentID / description

Previous value: -"Full handle of the assignment to save form data for. Format: ASSIGN-WORKLIST {caseID}!{processID}. Example: \"ASSIGN-WORKLIST PBANK-LOAN-WORK V-76003!REVIEW_FLOW\". This uniquely identifies the specific assignment instance where form data will be saved."New value: +"Assignment ID. Format: ASSIGN-WORKLIST {caseID}!{processID}. Example: \"ASSIGN-WORKLIST MYORG-APP-WORK C-1001!PROCESS\"\"ASSIGN-WORKLIST PBANK-LOAN-WORK V-76003!REVIEW_FLOW\". This uniquely identifies the specific assignment instance where form data will be saved."

changedInput schema / properties / eTag / description

Previous value: -"Required eTag unique value representing the most recent save date time (pxSaveDateTime) of the case. This must be equal to the eTag header from the response of the most recent case update request, or from a get_assignment_action request for this assignment. Used for optimistic locking to prevent concurrent modification conflicts."New value: +"Optional. Auto-fetched if omitted. For faster execution, use eTag from previous response."

changedInput schema / properties / pageInstructions / description

Previous value: -"Optional list of page-related operations to be performed on embedded pages, page lists, or page groups included in the assignment action's view during the save operation. These operations allow manipulation of complex data structures within the assignment. Each instruction specifies the operation type and target page structure."New value: +"Optional list of page-related operations for embedded pages, page lists, or page groups. Required for setting embedded page references. Only pages included in the assignment action's view can be modified."

changedInput schema / properties / pageInstructions / items / description

Previous value: -"Page operation object with instruction type and target"New value: +"Page operation for embedded pages. Use REPLACE instruction to set embedded page references with full object including pzInsKey. Example: {\"instruction\": \"REPLACE\", \"target\": \"PageName\", \"content\": {\"Property\": \"value\", \"pyID\": \"ID-123\", \"pzInsKey\": \"CLASS-NAME ID-123\"}}"

addedInput schema / properties / pageInstructions / items / properties / content

Added value: +{
+  "description": "Content to set on the embedded page (required for UPDATE and REPLACE)",
+  "type": "object"
+}

changedInput schema / properties / pageInstructions / items / properties / instruction / description

Previous value: -"The type of page instruction to perform"New value: +"Page instruction type. UPDATE (add fields to page), REPLACE (replace entire page), DELETE (remove page), APPEND (add item to page list), INSERT (insert item in page list), MOVE (reorder page list items)"

addedInput schema / properties / pageInstructions / items / properties / instruction / enum

Added value: +[
+  "UPDATE",
+  "REPLACE",
+  "DELETE",
+  "APPEND",
+  "INSERT",
+  "MOVE"
+]

changedInput schema / properties / pageInstructions / items / properties / target / description

Previous value: -"The target page or page list for the instruction"New value: +"Target embedded page name"

addedInput schema / properties / pageInstructions / items / required
```
Added value: +[
+  "instruction",
+  "target"
+]
```

addedInput schema / properties / sessionCredentials

Added value: +{
+  "description": "Optional session-specific credentials. If not provided, uses environment variables. Supports two authentication modes: (1) OAuth mode - provide baseUrl, clientId, and clientSecret, or (2) Token mode - provide baseUrl and accessToken.",
+  "properties": {
+    "accessToken": {
+      "description": "Direct access token (required for token mode)",
+      "type": "string"
+    },
+    "apiVersion": {
+      "default": "v2",
+      "description": "API version (optional, defaults to v2)",
+      "type": "string"
+    },
+    "baseUrl": {
+      "description": "Pega base URL (required if providing credentials)",
+      "type": "string"
+    },
+    "clientId": {
+      "description": "OAuth2 client ID (required for OAuth mode)",
+      "type": "string"
+    },
+    "clientSecret": {
+      "description": "OAuth2 client secret (required for OAuth mode)",
+      "type": "string"
+    },
+    "sessionId": {
+      "description": "Optional session ID. If not provided, a new session will be created.",
+      "type": "string"
+    },
+    "tokenExpiry": {
+      "description": "Token expiry in seconds from now (optional for token mode)",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

changedInput schema / required

Previous value: -[
-  "assignmentID",
-  "actionID",
-  "eTag"
-]New value: +[
+  "assignmentID",
+  "actionID"
+]

First observedAug 15, 2025

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behavioral traits: required field validations are ignored, only server-side validations are performed, eTag auto-fetches if omitted, and the tool is available for specific action types. Since no annotations are provided, the description carries full burden and covers most important behaviors, though it does not mention concurrency or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense paragraph with no wasted sentences. The first sentence immediately states the core purpose. While it could be more structured with bullet points, it remains concise and readable. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 parameters, nested objects, no output schema), the description covers purpose, usage context, validation behavior, eTag handling, and supported action types. It lacks explicit return value description, but the focus is on the save action itself. Overall, it is sufficiently complete for an AI agent to understand how to use the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is 3. The description adds meaningful context beyond schema: it clarifies that only fields part of the assignment action's view can be saved, gives detailed examples for pageInstructions and attachments, and explains the eTag auto-fetch behavior. This enhances understanding beyond the parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool saves assignment action form data without executing the action, implementing 'Save for later' functionality. It specifies the target resource (assignment action form data) and the verb (save), and distinguishes it from sibling tools like perform_assignment_action by emphasizing it does not execute.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool: for saving form data in progress for Connector actions like Collect info steps, screen flow assignments, and customized approval steps. It implicitly contrasts with perform_assignment_action. However, it does not explicitly state when not to use it or list alternative tools for specific scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server