リモートの変更をローカルプロジェクトに取得します(環境切替対応)
AI agents use clasp_pull to create or update resources in Google Apps Script MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Apps Script MCP Server environment.
A 'clasp pull' operation fetches remote Google Apps Script files and writes them to the local filesystem, potentially overwriting existing local files. This is a Write operation (modifying local files) rather than pure Read, since it changes the local project state. It is not Destructive in the irreversible sense as the remote source remains intact, but local unsaved changes could be lost.
From the tool's definition 「リモートの変更をローカルプロジェクトに取得します」— pulls remote changes into the local project, overwriting local files
Attacks that exploit this kind of access
リモートの変更をローカルプロジェクトに取得します(環境切替対応). It is categorised as a Write tool in the Google Apps Script MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Apps Script MCP Server MCP server in PolicyLayer and add a rule for clasp_pull: 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 Apps Script MCP Server. Nothing to install.
clasp_pull 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 clasp_pull 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 clasp_pull. 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.
clasp_pull is provided by the Google Apps Script MCP Server MCP server (utakata/google-apps-script-mcp). 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 →