Add inline comment to a specific code line in PR/MR
AI agents use add_inline_comment to create or update resources in Code Review — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Review environment.
This tool creates new data (a comment) in a pull request/merge request system, which is a reversible write operation. It does not delete, execute code, move money, or destroy data. The severity is medium because while comments are reversible, an AI agent could spam comments, post misleading review feedback, or flood PRs with noise, impacting development workflows and team collaboration.
From the tool's definition The tool 'add_inline_comment' creates a new comment on a specific code line in a pull request or merge request. The description states it will 'Add inline comment', indicating it creates and posts new content to the PR/MR.
Attacks that exploit this kind of access
Add inline comment to a specific code line in PR/MR. It is categorised as a Write tool in the Code Review MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Code Review MCP server in PolicyLayer and add a rule for add_inline_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 Code Review. Nothing to install.
add_inline_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_inline_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_inline_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_inline_comment is provided by the Code Review MCP server (oldjii/code-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 →