search_courses
AI agents call search_courses 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 searches a course catalog to retrieve course information. Search operations on read-only catalogs are non-destructive queries that return data without modifying state. The blast radius of misuse is minimal—an agent could perform excessive queries but cannot delete, modify, or create courses, nor execute arbitrary code or move money.
From the tool's definition Tool name 'search_courses' and sibling tools (get_course, get_course_fces, get_course_schedules, get_geneds, get_instructor_fces, get_instructor_schedules, get_requisites, search_instructors) all follow retrieval/query patterns consistent with Read operations.
Attacks that exploit this kind of access
search_courses. 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 search_courses: 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.
search_courses 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 search_courses 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 search_courses. 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.
search_courses 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 →