Create a comment on a pull request.
AI agents use github_create_pr_comment to create or update resources in Integrations MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Integrations MCP environment.
This tool creates new content (a PR comment) which is reversible—comments can be deleted or edited—making it a Write operation rather than Destructive. The severity is medium because misuse could spam PR threads, disrupt collaboration, post sensitive information, or cause reputational harm, but the blast radius is limited to a single repository's PR discussion and the action is reversible.
From the tool's definition Tool name 'github_create_pr_comment' and description 'Create a comment on a pull request' indicate the tool creates/adds new data (a comment) to an existing pull request.
Attacks that exploit this kind of access
Create a comment on a pull request. It is categorised as a Write tool in the Integrations MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Integrations MCP server in PolicyLayer and add a rule for github_create_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 Integrations MCP. Nothing to install.
github_create_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 github_create_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 github_create_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.
github_create_pr_comment is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →