search_instructors
AI agents call search_instructors 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 instructor information from the CMU course catalog. Search operations on catalog data have no side effects—they retrieve but do not modify, create, or delete data. The server's purpose (enabling queries of course details and instructor information) and the pattern of sibling tools all confirm this is a read-only retrieval operation with minimal risk.
From the tool's definition Tool name 'search_instructors' indicates a search operation; sibling tools like 'search_courses', 'get_course', 'get_instructor_fces', and 'get_instructor_schedules' are all read-only retrieval operations from a course catalog API.
Attacks that exploit this kind of access
search_instructors. 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_instructors: 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_instructors 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_instructors 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_instructors. 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_instructors 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 →