Navigate back to the previously visited step in a screen flow or multi-step form assignment. If no finalETag.trim() is provided, automatically fetches the latest finalETag.trim() from the assignment for seamless operation. Jumps to the previously visited navigation step from the current step. For...
AI agents invoke navigate_assignment_previous to trigger actions in Pega DX MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a navigation action that changes the state of a workflow assignment by moving to a previous step. This is not merely reading data (it modifies workflow state), nor is it creating/modifying case data directly (Write category). It triggers an operation in an external system (Pega Platform) whose behavioral outcome depends on the current assignment context - characteristic of Execute category.
From the tool's definition 'Navigate back to the previously visited step in a screen flow or multi-step form assignment' - this tool triggers navigation state changes and modifies the current step/stage of an assignment workflow, which is an action that triggers external operations…
Documented attack patterns abuse exactly the kind of access navigate_assignment_previous 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 navigate_assignment_previous:
{
"version": "1",
"default": "deny",
"tools": {
"navigate_assignment_previous": {
"limits": [
{
"counter": "navigate_assignment_previous_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}navigate_assignment_previous stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Navigate back to the previously visited step in a screen flow or multi-step form assignment. If no finalETag.trim() is provided, automatically fetches the latest finalETag.trim() from the assignment for seamless operation. Jumps to the previously visited navigation step from the current step. For multi-step forms and screen flows, navigation path steps are determined by the Enable navigation link checkbox. Returns assignment details with navigation breadcrumb information under uiResources when viewType is not. It is categorised as a Execute tool in the Pega DX MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pega DX MCP Server MCP server in PolicyLayer and add a rule for navigate_assignment_previous: 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.
navigate_assignment_previous is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the navigate_assignment_previous 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 navigate_assignment_previous. 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.
navigate_assignment_previous 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.