get_running_tolerance
AI agents call get_running_tolerance to retrieve information from Claude Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves running tolerance data from Garmin Connect without modifying, deleting, or executing operations. The 'get_' prefix and sibling context strongly suggest a read-only query operation. Confidence is 0.85 rather than higher due to the empty description, though the naming pattern provides good supporting evidence.
From the tool's definition Tool name 'get_running_tolerance' follows the naming pattern of sibling tools (get_activities, get_fitness, get_goals) which are all read operations retrieving Garmin Connect data.
Attacks that exploit this kind of access
get_running_tolerance. It is categorised as a Read tool in the Claude Garmin MCP Server, which means it retrieves data without modifying state.
Register the Claude Garmin MCP server in PolicyLayer and add a rule for get_running_tolerance: 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 Claude Garmin. Nothing to install.
get_running_tolerance 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_running_tolerance 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_running_tolerance. 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_running_tolerance is provided by the Claude Garmin MCP server (jack-abyss/claude-garmin). 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 →