Fetch raw (un-rolled-up) data points for a single Google Health dataType — use when you need
AI agents call list_data_points to retrieve information from Google Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves health data points from Google Health without creating, modifying, deleting, or executing external operations. It is a passive read operation that queries existing data.
From the tool's definition Tool name 'list_data_points' and description 'Fetch raw (un-rolled-up) data points' indicate data retrieval with no modification. The server description confirms it is used to 'read daily activity, sleep, heart rate, and body metrics' with no side effects.
Attacks that exploit this kind of access
Fetch raw (un-rolled-up) data points for a single Google Health dataType — use when you need. It is categorised as a Read tool in the Google Health MCP Server, which means it retrieves data without modifying state.
Register the Google Health MCP server in PolicyLayer and add a rule for list_data_points: 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 Health. Nothing to install.
list_data_points 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 list_data_points 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 list_data_points. 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.
list_data_points is provided by the Google Health MCP server (madfreakz/google-health-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 →