Merge a pull request
AI agents invoke merge_pull_request to trigger actions in GitHub MCP Tools. 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 Execute-level action: it runs an integration operation on GitHub that modifies branch history and can trigger downstream workflows. While technically not fully irreversible (a revert commit is possible), the merge itself cannot be undone cleanly, and misuse could introduce bad code into production branches.
From the tool's definition 'Merge a pull request' — merging integrates code changes into a target branch, triggering side effects (CI/CD pipelines, branch updates, commit history changes) that are difficult to reverse without additional action.
Attacks that exploit this kind of access
Merge a pull request. It is categorised as a Execute tool in the GitHub MCP Tools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GitHub MCP Tools 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 GitHub MCP Tools. 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 GitHub MCP Tools MCP server (pranesh-2005/usingmcp). 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 →