Get today
AI agents call get_strain_today to retrieve information from Health 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 today's strain data from the health aggregation system without modifying, deleting, or executing external operations. It fits the Read category pattern of querying health metrics. Confidence is slightly reduced due to the incomplete tool description, but context from sibling tools and naming convention strongly indicate a simple read operation with minimal risk.
From the tool's definition Tool name is 'get_strain_today' which follows a 'get_*' retrieval pattern. Description states 'Get today' (incomplete but indicates data retrieval).
Attacks that exploit this kind of access
Get today. It is categorised as a Read tool in the Health MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Health MCP Server MCP server in PolicyLayer and add a rule for get_strain_today: 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 Health MCP Server. Nothing to install.
get_strain_today 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_strain_today 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_strain_today. 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_strain_today is provided by the Health MCP Server MCP server (marholoubek/health_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 →