根据估计孕龄（EGA）计算预产期，适用于超声检查结果
AI agents call calculate_edd_from_ega to retrieve information from Awesome Medical without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a medical calculation — computing an estimated due date based on gestational age from ultrasound results. It reads/computes a result from input parameters with no side effects, data writes, or destructive actions. It is purely a calculation/query tool, similar to its sibling tools on this server.
From the tool's definition calculate_edd_from_ega — '根据估计孕龄（EGA）计算预产期，适用于超声检查结果' (calculates estimated due date from estimated gestational age from ultrasound)
Attacks that exploit this kind of access
根据估计孕龄（EGA）计算预产期，适用于超声检查结果. It is categorised as a Read tool in the Awesome Medical MCP Server, which means it retrieves data without modifying state.
Register the Awesome Medical MCP server in PolicyLayer and add a rule for calculate_edd_from_ega: 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 Awesome Medical. Nothing to install.
calculate_edd_from_ega 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 calculate_edd_from_ega 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 calculate_edd_from_ega. 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.
calculate_edd_from_ega is provided by the Awesome Medical MCP server (shanggqm/awesome-medical-mcp-server). 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 →