AI agents call format_content 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 is a pure transformation utility that converts markdown to XML for preview purposes only. It does not interact with external APIs, does not modify or delete data, does not execute code or commands, and produces no persistent side effects. The explicit "no API call" descriptor confirms it is a read-only preview function, making it the lowest-risk category.
From the tool's definition Tool performs content conversion from markdown to XML format as a preview with explicit "no API call" - it retrieves/transforms input data without side effects or persistence.
Attacks that exploit this kind of access
Convert markdown text to Ed Discussion XML format (preview, no API call). 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 format_content: 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.
format_content 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 format_content 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 format_content. 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.
format_content 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 →