preview_undo_run
A execute tool on the Mapi Agent Memory MCP server.
This record as markdown: /tools/mapi-agent-memory/preview-undo-run.md
What preview_undo_run does on Mapi Agent Memory
AI agents invoke preview_undo_run to trigger actions in Mapi Agent Memory. 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.
Why preview_undo_run is rated High
While 'preview' suggests read-only inspection, the '_run' suffix combined with the governance/remediation context and sibling pattern (apply_* tools that execute memory operations) indicates this likely executes an operation rather than merely reading. The undo semantics suggest it modifies memory state.
From the tool's definition Tool name 'preview_undo_run' suggests execution of an undo operation, which triggers external state changes.
Attacks that exploit this kind of access
The rule that runs preview_undo_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mapi Agent Memory, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For preview_undo_run, this is the rule to start with:
preview_undo_run 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Mapi Agent Memory, apply this rule, and every preview_undo_run call is checked against it from then on.
Questions about preview_undo_run
preview_undo_run is a execute tool on the Mapi Agent Memory MCP server. It is categorised as a Execute tool in the Mapi Agent Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mapi Agent Memory MCP server in PolicyLayer and add a rule for preview_undo_run: 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 Mapi Agent Memory. Nothing to install.
preview_undo_run 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 preview_undo_run 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 preview_undo_run. 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.
preview_undo_run is provided by the Mapi Agent Memory MCP server (cabo0m/mapi-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mapi Agent Memory, and thousands of servers like it.
Across the catalogue