add_reply_to_pull_request_comment
Add a reply to an existing pull request comment. This creates a new comment that is linked as a reply to the specified comment.
This record as markdown: /tools/github/add-reply-to-pull-request-comment.md
What add_reply_to_pull_request_comment does on GitHub
AI agents use add_reply_to_pull_request_comment to create or update resources in GitHub, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
body | string | — | The text of the reply |
repo | string | — | Repository name |
owner | string | — | Repository owner |
commentId | number | — | The ID of the comment to reply to |
pullNumber | number | — | Pull request number |
Parameters from the server's own tool schema.
Why add_reply_to_pull_request_comment is rated Medium
This tool creates new data (a reply comment) in a reversible manner. While comments can be edited or deleted afterward, the primary action is write/create. The severity is medium because a malicious agent could spam comments, disrupt collaboration, or post harmful content to a repository, but the blast radius is limited to comment-level impact rather than code execution or data destruction.
From the tool's definition Tool description states it "creates a new comment" on a pull request, which is a reversible creation of data. The action is explicitly generative (adds/creates) rather than destructive, and does not execute code or move funds.
Risk signalsAccepts raw HTML/template content (body)
Attacks that exploit this kind of access
The rule that runs add_reply_to_pull_request_comment safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For add_reply_to_pull_request_comment, this is the rule to start with:
add_reply_to_pull_request_comment stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every add_reply_to_pull_request_comment call is checked against it from then on.
Questions about add_reply_to_pull_request_comment
Add a reply to an existing pull request comment. This creates a new comment that is linked as a reply to the specified comment. It is categorised as a Write tool in the GitHub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
add_reply_to_pull_request_comment accepts 5 parameters: body, repo, owner, commentId, pullNumber. The full parameter table on this page comes from the server's own tool schema.
Register the GitHub MCP server in PolicyLayer and add a rule for add_reply_to_pull_request_comment: 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. Nothing to install.
add_reply_to_pull_request_comment 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 add_reply_to_pull_request_comment 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 add_reply_to_pull_request_comment. 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.
add_reply_to_pull_request_comment is provided by the GitHub MCP server (oci:ghcr.io/github/github-mcp-server:1.3.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue