bp_read_readings
AI agents call bp_read_readings to retrieve information from Blood Pressure Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries blood pressure readings with no side effects. It falls squarely into the Read category. Severity is low because reading medical data poses minimal immediate risk even if misused by an AI agent—no data is modified, deleted, or irreversible action is taken. Confidence is high despite the empty description because the tool name and server context clearly indicate a read-only operation.
From the tool's definition Tool name 'bp_read_readings' indicates retrieval of blood pressure data. The server description confirms it supports 'read' operations on blood pressure readings without modification or deletion.
Attacks that exploit this kind of access
bp_read_readings. It is categorised as a Read tool in the Blood Pressure Tool MCP Server, which means it retrieves data without modifying state.
Register the Blood Pressure Tool MCP server in PolicyLayer and add a rule for bp_read_readings: 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 Blood Pressure Tool. Nothing to install.
bp_read_readings 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 bp_read_readings 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 bp_read_readings. 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.
bp_read_readings is provided by the Blood Pressure Tool MCP server (mclarkson/bptool). 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 →