新しいGoogleフォームを作成します
AI agents use create_form to create or update resources in Google Forms MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Forms MCP Server environment.
Creating a new form is a reversible write operation. It generates new data (a form object) but does not execute arbitrary code, delete data, or commit financial obligations. The blast radius is medium because an AI agent could create many forms or forms with misleading/malicious content, consuming user resources or reputation, but the operation itself is not destructive or irreversible (forms can be deleted).
From the tool's definition Tool creates a new Google Form via the Google Forms API. Description states '新しいGoogleフォームを作成します' (creates a new Google Form). This is a create operation that adds new data to the user's Google Forms workspace.
Attacks that exploit this kind of access
新しいGoogleフォームを作成します. It is categorised as a Write tool in the Google Forms MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Forms MCP Server MCP server in PolicyLayer and add a rule for create_form: 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 Google Forms MCP Server. Nothing to install.
create_form 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_form 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_form. 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_form is provided by the Google Forms MCP Server MCP server (masatoshi118/mcp_google_froms). 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 →