Get the contents of a Google Doc
AI agents call docs_get_content to retrieve information from MCP Google Workspace Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from Google Docs without causing side effects. It does not create, modify, delete, or execute operations. The blast radius of misuse is limited to unauthorized information disclosure, which is lower severity than write/execute/destructive operations.
From the tool's definition Tool name 'docs_get_content' and description 'Get the contents of a Google Doc' indicate data retrieval with no modification. The verb 'get' and the absence of any mutative language confirm read-only semantics.
Attacks that exploit this kind of access
Get the contents of a Google Doc. It is categorised as a Read tool in the MCP Google Workspace Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Google Workspace Server MCP server in PolicyLayer and add a rule for docs_get_content: 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 MCP Google Workspace Server. Nothing to install.
docs_get_content is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the docs_get_content 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 docs_get_content. 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.
docs_get_content is provided by the MCP Google Workspace Server MCP server (josedu90/mcp-suiteg). 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 →