AI agents use post_comment 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.
This tool creates new data (comments/answers) in a course discussion platform in a reversible manner. Users can typically edit or delete their own posts afterward. It is Write rather than Execute because it doesn't run arbitrary code—it specifically posts formatted content.
From the tool's definition Tool description states "Post a comment or answer on a thread", which creates new content. The server description confirms it enables "managing threads, comments, and course activity" and "posting content".
Attacks that exploit this kind of access
Post a comment or answer on a thread. Content can be markdown. 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_comment: 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_comment 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_comment 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_comment. 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_comment 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 →