insert_image
AI agents use insert_image to create or update resources in Google Connections — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Connections environment.
Image insertion modifies documents reversibly—images can be deleted or replaced later. This is a Write operation, not Destructive. Severity is medium because while inserting images is non-destructive, it could clutter or deface documents if used maliciously. The empty description lowers confidence slightly, but the tool name and server context provide strong evidence for the Write classification.
From the tool's definition Tool name 'insert_image' combined with server's 'full CRUD operations' capability on Google Docs/Sheets suggests the tool creates or modifies document content by embedding images.
Attacks that exploit this kind of access
insert_image. It is categorised as a Write tool in the Google Connections MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Connections MCP server in PolicyLayer and add a rule for insert_image: 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 Connections. Nothing to install.
insert_image 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 insert_image 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 insert_image. 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.
insert_image is provided by the Google Connections MCP server (michaelzrork/google-connections-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 →