Crée un nouveau blog (non supporté par l\
AI agents use create_blog to create or update resources in Blogger MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blogger MCP Server environment.
Creating a blog is a write operation that adds new data to the Blogger platform. It is reversible (the blog can be deleted), so it does not qualify as Destructive. The severity is medium because misuse could create numerous unwanted blogs, but the impact is limited to blog creation without financial consequences or executing arbitrary code.
From the tool's definition Tool name is 'create_blog' and context describes 'enables AI models to interact with Google's Blogger platform, automating the creation and management of blogs'.
Attacks that exploit this kind of access
Crée un nouveau blog (non supporté par l\. It is categorised as a Write tool in the Blogger MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Blogger MCP Server MCP server in PolicyLayer and add a rule for create_blog: 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 Blogger MCP Server. Nothing to install.
create_blog 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_blog 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_blog. 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_blog is provided by the Blogger MCP Server MCP server (niyonabil/blogger-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 →