Insert a drawing or shape into the document
AI agents use insert_drawing to create or update resources in LLM2Docs (Unofficial) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LLM2Docs (Unofficial) environment.
This tool creates new content (drawings/shapes) within a Google Docs document, which is a write operation that modifies the document state. While it adds content, it is fully reversible and does not commit to financial obligations, execute arbitrary code, or permanently delete data.
From the tool's definition Tool name 'insert_drawing' combined with description 'Insert a drawing or shape into the document' indicates creation and modification of document content. The action is reversible (drawings can be deleted) and non-destructive.
Attacks that exploit this kind of access
Insert a drawing or shape into the document. It is categorised as a Write tool in the LLM2Docs (Unofficial) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LLM2Docs (Unofficial) MCP server in PolicyLayer and add a rule for insert_drawing: 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 LLM2Docs (Unofficial). Nothing to install.
insert_drawing 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_drawing 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_drawing. 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_drawing is provided by the LLM2Docs (Unofficial) MCP server (nomannayeem/google-docs-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 →