merge_pull_request
AI agents use merge_pull_request to create or update resources in Jira - GitHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jira - GitHub MCP Server environment.
Merging a pull request integrates code changes into a target branch, which is a significant write/execute-level action. It is not easily reversible (though it can be reverted, the merge itself is committed to history). Given the server context (GitHub PR management), merging a PR is a high-impact write operation.
From the tool's definition Tool name 'merge_pull_request'; description is empty and uninformative
Attacks that exploit this kind of access
merge_pull_request. It is categorised as a Write tool in the Jira - GitHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jira - GitHub MCP Server 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 Jira - GitHub MCP Server. Nothing to install.
merge_pull_request 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 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 Jira - GitHub MCP Server MCP server (tamarengel/jira-github-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 →