Accept pending AI-generated changes
AI agents use accept_preview to create or update resources in Prowpt MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prowpt MCP Server environment.
This tool applies/commits AI-generated changes to a project, which is a write operation that modifies data. It is reversible in principle (changes could potentially be reverted), so it does not reach Destructive. The blast radius is medium since accepting incorrect AI-generated changes could alter project code or content in unintended ways.
From the tool's definition Accept pending AI-generated changes
Attacks that exploit this kind of access
Accept pending AI-generated changes. It is categorised as a Write tool in the Prowpt MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prowpt MCP Server MCP server in PolicyLayer and add a rule for accept_preview: 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 Prowpt MCP Server. Nothing to install.
accept_preview 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 accept_preview 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 accept_preview. 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.
accept_preview is provided by the Prowpt MCP Server MCP server (prowptai/prowpt-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 →