Posts a comment to an Azure DevOps Pull Request. Can reply to existing threads or create new ones.
AI agents use ado_pr_comment to create or update resources in Git Stuff Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git Stuff Server environment.
This tool creates new comments/data in Azure DevOps pull requests, which is a Write operation (reversible modification). While comments can typically be deleted or edited afterward, the primary action is to create/add data.
From the tool's definition Tool description states it 'Posts a comment to an Azure DevOps Pull Request' and can 'reply to existing threads or create new ones.' The verb 'Posts' and the functionality of adding comments constitutes data creation.
Attacks that exploit this kind of access
Posts a comment to an Azure DevOps Pull Request. Can reply to existing threads or create new ones. It is categorised as a Write tool in the Git Stuff Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git Stuff Server MCP server in PolicyLayer and add a rule for ado_pr_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 Git Stuff Server. Nothing to install.
ado_pr_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 ado_pr_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 ado_pr_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.
ado_pr_comment is provided by the Git Stuff Server MCP server (skurekjakub/gitstuffserver). 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 →