AI agents use grade_exam to create or update resources in Leafeep — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leafeep environment.
Grading a submission creates or modifies a grade record in the system. This is a reversible write operation (grades could potentially be changed), not destructive. However, misuse could incorrectly assign grades affecting student performance records, hence medium severity.
From the tool's definition Grade student submissions. Use answerId from get_results.
Attacks that exploit this kind of access
Grade student submissions. Use answerId from get_results. It is categorised as a Write tool in the Leafeep MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Leafeep MCP server in PolicyLayer and add a rule for grade_exam: 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 Leafeep. Nothing to install.
grade_exam is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the grade_exam 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 grade_exam. 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.
grade_exam is provided by the Leafeep MCP server (xhae123/leafeep-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 →