Calculate the score you need on your final exam to achieve a target grade in a course.
AI agents call predict_grade to retrieve information from Shiori 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 and processes existing academic data (current grades, targets) to compute a predictive value. It is purely informational with no side effects on the student's records, coursework, or external systems. No data is created, modified, deleted, or executed—only read and mathematically transformed for the user's planning purposes.
From the tool's definition Tool performs calculation based on existing grade data ('score you need', 'target grade') with no modification of records, creation of data, or execution of external operations.
Documented attack patterns abuse exactly the kind of access predict_grade gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Shiori MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for predict_grade:
{
"version": "1",
"default": "deny",
"tools": {
"predict_grade": {}
}
}predict_grade is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Calculate the score you need on your final exam to achieve a target grade in a course. It is categorised as a Read tool in the Shiori MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Shiori MCP Server MCP server in PolicyLayer and add a rule for predict_grade: 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 Shiori MCP Server. Nothing to install.
predict_grade 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 predict_grade 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 predict_grade. 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.
predict_grade is provided by the Shiori MCP Server MCP server (kaorii-ako/shiori-v1). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Shiori MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Shiori MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.