create_pull_request_review · Server Github MCP

WHAT IT DOES

What create_pull_request_review does on Server Github

AI agents use create_pull_request_review to create or update resources in Server Github — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Server Github environment.

PARAMETERS

Parameter	Type	Required	Description
`body`	string	Yes	The body text of the review
`repo`	string	Yes	Repository name
`event`	string	Yes	The review action to perform
`owner`	string	Yes	Repository owner (username or organization)
`comments`	array	—	Comments to post as part of the review (specify either position or line, not both)
`commit_id`	string	—	The SHA of the commit that needs a review
`pull_number`	number	Yes	Pull request number

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why create_pull_request_review needs a policy

This tool creates a new pull request review, which is a reversible write operation. Reviews can be edited, dismissed, or deleted. While it modifies the state of a pull request (adding commentary, approvals, or change requests), it does not irreversibly delete data, execute arbitrary code, or move financial resources.

From the tool's definition Tool name 'create_pull_request_review' and description 'Create a review on a pull request' indicate the tool creates new review data on GitHub.

Risk signalsAccepts raw HTML/template content (body)

Attacks that exploit this kind of access

Questions about create_pull_request_review

What does the create_pull_request_review tool do? +

Create a review on a pull request. It is categorised as a Write tool in the Server Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_pull_request_review accept? +

create_pull_request_review accepts 7 parameters: body, repo, event, owner, comments, commit_id, pull_number. Required: body, repo, event, owner, pull_number. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_pull_request_review? +

Register the Server Github MCP server in PolicyLayer and add a rule for create_pull_request_review: 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 Server Github. Nothing to install.

What risk level is create_pull_request_review? +

create_pull_request_review is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_pull_request_review? +

Yes. Add a rate_limit block to the create_pull_request_review 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.

How do I block create_pull_request_review completely? +

Set action: deny in the PolicyLayer policy for create_pull_request_review. 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.

What MCP server provides create_pull_request_review? +

create_pull_request_review is provided by the Server Github MCP server (@iflow-mcp/server-github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.