get_course_fces
AI agents call get_course_fces to retrieve information from Scottylabs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing evaluation data from a course catalog with no indication of modification, deletion, or execution capabilities. The 'get_' prefix and sibling tools all indicate passive retrieval operations. The empty description lowers confidence slightly, but the context and naming pattern strongly suggest a simple data retrieval function with minimal security impact.
From the tool's definition Tool is part of a server for searching and retrieving course details from CMU course catalog. The tool name 'get_course_fces' follows the pattern of other Read-only tools on this server (get_course, get_course_schedules, get_requisites) that retrieve data.
Attacks that exploit this kind of access
get_course_fces. It is categorised as a Read tool in the Scottylabs MCP Server, which means it retrieves data without modifying state.
Register the Scottylabs MCP server in PolicyLayer and add a rule for get_course_fces: 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 Scottylabs. Nothing to install.
get_course_fces 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_course_fces 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_course_fces. 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_course_fces is provided by the Scottylabs MCP server (shivendoo123/scottylabs_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 →