Open a pull request.
AI agents use create_pull_request to create or update resources in GitHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub MCP Server environment.
Creating a pull request is a reversible write operation—it adds metadata and change proposals to a repository without directly modifying production code or deleting data. While PRs can trigger CI/CD workflows (which could have Execute-like side effects), the tool itself is narrowly scoped to PR creation.
From the tool's definition Tool description states it 'Open[s] a pull request', which creates a new pull request object in GitHub. Creating a pull request is a write operation that modifies the repository state by adding a new PR entity.
Attacks that exploit this kind of access
Open a pull request. It is categorised as a Write tool in the GitHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for create_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 Server. Nothing to install.
create_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 create_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 create_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.
create_pull_request is provided by the GitHub MCP Server MCP server (maheshjagzap123/mcp-server). 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 →