Retrieve marks and grades for subjects
AI agents call get_marks to retrieve information from LMS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries academic performance data (marks and grades) from the LMS database. It performs no write operations, does not execute code, and does not irreversibly modify or delete data. The operation is non-destructive and informational. Severity is low because unauthorized access to a user's marks may have privacy implications but no direct operational harm, financial impact, or system damage.
From the tool's definition Tool name 'get_marks' and description 'Retrieve marks and grades for subjects' indicate a read-only operation that retrieves existing academic data without modification or side effects.
Attacks that exploit this kind of access
Retrieve marks and grades for subjects. It is categorised as a Read tool in the LMS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LMS MCP Server MCP server in PolicyLayer and add a rule for get_marks: 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 LMS MCP Server. Nothing to install.
get_marks 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_marks 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_marks. 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_marks is provided by the LMS MCP Server MCP server (qaziabsaar/lms_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 →