List classes (groups) for a course with student count and join code.
AI agents call list_classes to retrieve information from Easycslearning without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves educational class metadata from Firebase. It has no ability to modify, delete, or execute operations—it only fetches and presents information. The join code disclosure is a minor information exposure concern but does not elevate beyond Read category. Low severity reflects the limited blast radius of exposing class roster structure and metadata in an educational context.
From the tool's definition Tool name 'list_classes' and description 'List classes' indicate data retrieval. Server description explicitly states 'read-only access'. The tool returns metadata (class name, student count, join code) without modification or side effects.
Attacks that exploit this kind of access
List classes (groups) for a course with student count and join code. It is categorised as a Read tool in the Easycslearning MCP Server, which means it retrieves data without modifying state.
Register the Easycslearning MCP server in PolicyLayer and add a rule for list_classes: 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 Easycslearning. Nothing to install.
list_classes 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 list_classes 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 list_classes. 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.
list_classes is provided by the Easycslearning MCP server (tsfir/easycslearning_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 →