Get detailed information about a specific action that can be performed on an assignment. Retrieves assignment action defined for an assignment step in a case process, including UI metadata and preprocessing execution. If the case type uses pessimistic locking and the client uses Constellation, th...
AI agents call get_assignment_action to retrieve information from Pega DX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata and details about an assignment action. While the pessimistic locking mechanism might temporarily affect case accessibility, the tool's primary function is to query and return information about what actions are available on an assignment, not to create, modify, delete, execute external operations, or move money.
From the tool's definition Tool description states 'Get detailed information' and 'Retrieves assignment action defined for an assignment step' - these are information retrieval operations with no data modification.
Documented attack patterns abuse exactly the kind of access get_assignment_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pega DX MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_assignment_action:
{
"version": "1",
"default": "deny",
"tools": {
"get_assignment_action": {}
}
}get_assignment_action is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get detailed information about a specific action that can be performed on an assignment. Retrieves assignment action defined for an assignment step in a case process, including UI metadata and preprocessing execution. If the case type uses pessimistic locking and the client uses Constellation, this request may lock the case. Get details for ONE specific action. Often optional - most workflows use: get_assignment (all actions + eTag) → perform_assignment_action. Use this when you need action-specific details. It is categorised as a Read tool in the Pega DX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pega DX MCP Server MCP server in PolicyLayer and add a rule for get_assignment_action: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pega DX MCP Server. Nothing to install.
get_assignment_action is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_assignment_action rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_assignment_action. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_assignment_action is provided by the Pega DX MCP Server MCP server (marco-looy/pega-dx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pega DX MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
65 Pega DX MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.