AI agents call get_option_of_custom_field to retrieve information from Eduframe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about custom field options without side effects. It falls squarely into the Read category—querying configuration data. The blast radius is minimal: incorrect data retrieval affects only the user's view, not data integrity or system state.
From the tool's definition Tool name and description indicate retrieval of a custom field option: 'Get an option of a custom field'. No modification, deletion, or execution of code is suggested. This is a query/fetch operation.
Attacks that exploit this kind of access
Get an option of a custom field. It is categorised as a Read tool in the Eduframe MCP Server, which means it retrieves data without modifying state.
Register the Eduframe MCP server in PolicyLayer and add a rule for get_option_of_custom_field: 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 Eduframe. Nothing to install.
get_option_of_custom_field 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_option_of_custom_field 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_option_of_custom_field. 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_option_of_custom_field is provided by the Eduframe MCP server (martijnpieters/eduframe-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 →