指定したスラグの記事を S3 から削除し、GitHub Actions ビルドを発火させる。
AI agents call blog_delete_post to permanently remove resources in Mcp Blog — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes a blog post from S3 storage, which is an irreversible destructive action. It also triggers a downstream GitHub Actions build, compounding the blast radius. Misuse by an AI agent could permanently remove published content with no undo path.
From the tool's definition 「削除し」(delete) — removes the article from S3 and triggers a GitHub Actions build; deletion from S3 is irreversible
Attacks that exploit this kind of access
指定したスラグの記事を S3 から削除し、GitHub Actions ビルドを発火させる。. It is categorised as a Destructive tool in the Mcp Blog MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Blog MCP server in PolicyLayer and add a rule for blog_delete_post: 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 Blog. Nothing to install.
blog_delete_post is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the blog_delete_post 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 blog_delete_post. 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.
blog_delete_post is provided by the Mcp Blog MCP server (masatoshisano/mcp-blog). 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 →