AI agents call search_threads to retrieve information from Edstem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries discussion threads based on search criteria. It has no capability to create, modify, delete, or execute operations. The search operation is read-only with no destructive, financial, or executable side effects. Low severity due to minimal blast radius if misused by an AI agent — worst case being inefficient or irrelevant search queries.
From the tool's definition Tool description states 'Search threads in a course by title, content, or category' — a query operation with no side effects. The verb 'search' and the context of querying existing discussion content without modification confirms this is a retrieval operation.
Attacks that exploit this kind of access
Search threads in a course by title, content, or category. It is categorised as a Read tool in the Edstem MCP Server, which means it retrieves data without modifying state.
Register the Edstem MCP server in PolicyLayer and add a rule for search_threads: 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 Edstem. Nothing to install.
search_threads 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_threads 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_threads. 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_threads is provided by the Edstem MCP server (rob-9/edstem-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 →