AI agents use tool_set_extension to create or update resources in Gradescope MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gradescope MCP Server environment.
This tool modifies student-facing assignment parameters (submission deadlines/extensions) without deleting data, making it Write category. Severity is high because an AI agent misusing this could grant inappropriate extensions to many students, affecting grading fairness and course integrity.
From the tool's definition Tool name 'tool_set_extension' in context of Gradescope course management and grading workflows indicates modification of assignment submission deadlines or timeframes for students.
Documented attack patterns abuse exactly the kind of access tool_set_extension gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gradescope MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for tool_set_extension:
{
"version": "1",
"default": "deny",
"tools": {
"tool_set_extension": {
"limits": [
{
"counter": "tool_set_extension_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}tool_set_extension stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
tool_set_extension. It is categorised as a Write tool in the Gradescope MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gradescope MCP Server MCP server in PolicyLayer and add a rule for tool_set_extension: 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 Gradescope MCP Server. Nothing to install.
tool_set_extension 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 tool_set_extension 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 tool_set_extension. 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.
tool_set_extension is provided by the Gradescope MCP Server MCP server (yuanpeng-li/gradescope-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gradescope 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.
37 Gradescope MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.