Cierra un pull request sin mergearlo
AI agents use close_pull_request to create or update resources in Mcp Github — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Github environment.
Closing a pull request modifies its status but is reversible—the PR can be reopened and remains in the repository's history. This is a Write operation (state modification) rather than Destructive (which would be permanent deletion).
From the tool's definition Tool name 'close_pull_request' combined with description 'Cierra un pull request sin mergearlo' (Closes a pull request without merging it) indicates modification of pull request state from open to closed.
Attacks that exploit this kind of access
Cierra un pull request sin mergearlo. It is categorised as a Write tool in the Mcp Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Github MCP server in PolicyLayer and add a rule for close_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 Github. Nothing to install.
close_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 close_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 close_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.
close_pull_request is provided by the Mcp Github MCP server (pblarismendi/mcp-github-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 →