AI agents call get_referrals 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 queries and retrieves referral data without modifying, executing external operations, or causing irreversible changes. It is a straightforward data retrieval operation with minimal security risk unless the referral data itself is highly sensitive, but the action itself is non-destructive.
From the tool's definition Tool name 'get_referrals' and description 'Get all referral records' indicate a retrieval operation with no side effects. The verb 'get' and the absence of any modification language (create, update, delete, approve) confirm read-only behavior.
Attacks that exploit this kind of access
Get all referral records. 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_referrals: 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_referrals 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_referrals 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_referrals. 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_referrals 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 →