Show your grades in a course.
AI agents call get_grades to retrieve information from Moodle Student MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves academic performance data without side effects. The Moodle server operates in read-only mode using a personal authentication token, and get_grades simply queries and displays existing grade information. No data is created, modified, deleted, or used to trigger external operations. Misuse risk is minimal—an AI agent could only retrieve grades the authenticated user already has access to.
From the tool's definition Tool explicitly described as 'Show your grades in a course' with server marked 'read-only querying'. No modification, deletion, or execution capability. Returns student's own grade data only.
Attacks that exploit this kind of access
Show your grades in a course. It is categorised as a Read tool in the Moodle Student MCP MCP Server, which means it retrieves data without modifying state.
Register the Moodle Student MCP server in PolicyLayer and add a rule for get_grades: 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 Moodle Student MCP. Nothing to install.
get_grades 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_grades 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_grades. 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_grades is provided by the Moodle Student MCP server (tcpassos/moodle-student-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 →