AI agents invoke merge_pull_request to trigger actions in Mcp Gmail. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Merging a pull request is an irreversible integration of code changes into a target branch. While a revert commit can undo the logical change, the merge commit itself remains in history. This constitutes a significant Execute action (triggering external operations and modifying repo state), bordering on Destructive.
From the tool's definition 'Merge a pull request' — merging combines branches and triggers CI/CD pipelines, modifies repository history, and cannot be easily undone without force-push or revert commits
Attacks that exploit this kind of access
Merge a pull request. It is categorised as a Execute tool in the Mcp Gmail MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for merge_pull_request: 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 Mcp Gmail. Nothing to install.
merge_pull_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the merge_pull_request 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 merge_pull_request. 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.
merge_pull_request is provided by the Mcp Gmail MCP server (@monsoft/mcp-gmail). 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 →