AI agents use pr_create to create or update resources in Pr Review — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pr Review environment.
This tool creates a new pull request, which is a reversible write operation. While creating a PR can trigger automated workflows and notifications, the operation itself is reversible (PR can be closed or deleted). It's classified as Write rather than Execute because the tool's primary function is to create/modify repository metadata (the PR object), not execute arbitrary code.
From the tool's definition Tool name: 'pr_create'; description: 'Create a new pull request from an existing branch'. The verb 'create' and explicit mention of creating a new PR indicates data creation.
Attacks that exploit this kind of access
Create a new pull request from an existing branch. It is categorised as a Write tool in the Pr Review MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pr Review MCP server in PolicyLayer and add a rule for pr_create: 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 Pr Review. Nothing to install.
pr_create 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 pr_create 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 pr_create. 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.
pr_create is provided by the Pr Review MCP server (thebtf/pr-review-mcp). 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 →