update_pr
AI agents use update_pr to create or update resources in GitHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub MCP Server environment.
Pull request updates (title, description, labels, etc.) are reversible modifications to data. This is a Write action rather than Execute because it modifies metadata/content, not triggering arbitrary code execution. Severity is high due to potential for unauthorized PRs to be modified, affecting code review processes and CI workflows in a repository.
From the tool's definition Tool name 'update_pr' indicates modifying pull requests; sibling tools like 'batch_update_issues', 'create_pr_with_content', and 'close_issue' all operate on GitHub resources with reversible write effects.
Attacks that exploit this kind of access
update_pr. It is categorised as a Write tool in the GitHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for update_pr: 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 GitHub MCP Server. Nothing to install.
update_pr 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 update_pr 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 update_pr. 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.
update_pr is provided by the GitHub MCP Server MCP server (rriesco/github-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 →