AI agents call get_personal_records to retrieve information from Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves personal record data (fastest times, longest distances) from Garmin Connect without modifying, deleting, or executing any operations. It is purely a data query operation with no side effects. The 'get_' prefix and context of read-only health/fitness metrics confirm it as a Read category tool.
From the tool's definition Tool name 'get_personal_records' and server description stating 'read-only MCP tools' with data retrieval operations like 'get_activity_details', 'get_body_battery', 'get_recent_activities' all following the 'get_*' read pattern.
Attacks that exploit this kind of access
Personal records across activity types (fastest 1K/5K/10K, longest run, etc.). It is categorised as a Read tool in the Garmin MCP Server, which means it retrieves data without modifying state.
Register the Garmin MCP server in PolicyLayer and add a rule for get_personal_records: 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 Garmin. Nothing to install.
get_personal_records 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_personal_records 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_personal_records. 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_personal_records is provided by the Garmin MCP server (tyler-irving/garmin-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 →