Get things learned about the user
AI agents call get_learnings to retrieve information from Google Workspace MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored learnings from the user's personal memory system without modifying, deleting, or executing any actions. It has no blast radius beyond potential privacy concerns about what data is exposed, which is inherent to any read operation. The low severity reflects that reading stored preferences poses minimal risk compared to write, execute, or destructive operations.
From the tool's definition Tool name 'get_learnings' and description 'Get things learned about the user' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get things learned about the user. It is categorised as a Read tool in the Google Workspace MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Workspace MCP Server MCP server in PolicyLayer and add a rule for get_learnings: 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 Workspace MCP Server. Nothing to install.
get_learnings 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 get_learnings 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 get_learnings. 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.
get_learnings is provided by the Google Workspace MCP Server MCP server (pbulbule13/google-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 →