AI agents use pr_labels 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 performs both read and write operations on PR labels. Since it can add, remove, or set labels (modifying GitHub PR metadata), the most severe applicable category is Write. Label changes are reversible (labels can be re-added or removed), so it does not qualify as Destructive. Misuse could lead to mislabeled PRs affecting triage, automation triggers, or review workflows, giving it medium severity.
From the tool's definition 'Get, add, remove, or set labels on a PR' — the tool modifies label state on pull requests
Attacks that exploit this kind of access
Get, add, remove, or set labels on a PR. 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_labels: 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_labels 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_labels 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_labels. 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_labels 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 →