Undo or redo actions
AI agents use affinity_undo_redo to create or update resources in Affinity MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Affinity MCP Server environment.
Undo/redo operations modify document state by reverting or reapplying prior edits. These are Write-class actions (reversible state changes), not Destructive, as undo/redo can be reverted and do not permanently delete or irretrievably overwrite data.
From the tool's definition Tool named 'affinity_undo_redo' with description 'Undo or redo actions' — performs reversible modifications to document state within Affinity creative suite.
Attacks that exploit this kind of access
Undo or redo actions. It is categorised as a Write tool in the Affinity MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Affinity MCP Server MCP server in PolicyLayer and add a rule for affinity_undo_redo: 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 Affinity MCP Server. Nothing to install.
affinity_undo_redo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the affinity_undo_redo 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 affinity_undo_redo. 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.
affinity_undo_redo is provided by the Affinity MCP Server MCP server (sekharmalla/affinity-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →