get_recent_load
AI agents call get_recent_load 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 is a data retrieval operation with no side effects. It queries existing metrics (likely HRV-related or training load data mentioned in the server description) and returns them to the user. No data is created, modified, deleted, or executed. Confidence is slightly reduced due to empty description, but the naming pattern and context provide strong evidence of Read classification.
From the tool's definition Tool name 'get_recent_load' follows the 'get_*' pattern consistent with sibling tools (get_activities, get_fitness, get_goals, etc.), all of which retrieve data without modification.
Attacks that exploit this kind of access
get_recent_load. 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_recent_load: 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_recent_load 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_recent_load 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_recent_load. 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_recent_load 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 →