AI agents call get_course_thread 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 a single thread from the Ed Discussion platform using its course-local identifier. It performs a simple lookup query without modifying, deleting, or executing any operations. The read-only nature and limited scope (single thread retrieval) present minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_thread' and description 'Get a thread by its course-local number' indicate a retrieval operation with no side effects. The verb 'Get' and the context of querying by identifier are characteristic of read-only access.
Attacks that exploit this kind of access
Get a thread by its course-local number (the # shown in the Ed UI). 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 get_course_thread: 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.
get_course_thread 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_thread 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_thread. 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_thread 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 →