AI agents use post_thread to create or update resources in Edstem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Edstem environment.
post_thread creates new discussion threads, which is a reversible write operation. The severity is medium because while the action itself is reversible (threads can be edited or deleted by moderators), misuse could result in spam, off-topic content, or harassment in an educational discussion platform affecting course participants.
From the tool's definition Tool description states 'Create a new discussion thread' with markdown content conversion. The sibling tools include write operations (edit_thread, endorse_comment, post_thread) and read operations (get_thread, list_threads, get_user).
Attacks that exploit this kind of access
Create a new discussion thread. Content can be markdown (auto-converted to Ed XML). It is categorised as a Write tool in the Edstem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Edstem MCP server in PolicyLayer and add a rule for post_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.
post_thread is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the post_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 post_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.
post_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 →