Follow a HATEOAS link from a previous API response
AI agents call follow_api_link to retrieve information from pfSense Enhanced MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool follows existing hypermedia links returned by prior API calls to retrieve additional data. It has no side effects—it queries and navigates through API responses without creating, modifying, deleting, or executing operations. The function is analogous to clicking a link in a web browser.
From the tool's definition Tool name 'follow_api_link' and description 'Follow a HATEOAS link from a previous API response' indicate retrieval of data via hypermedia navigation.
Attacks that exploit this kind of access
Follow a HATEOAS link from a previous API response. It is categorised as a Read tool in the pfSense Enhanced MCP Server MCP Server, which means it retrieves data without modifying state.
Register the pfSense Enhanced MCP Server MCP server in PolicyLayer and add a rule for follow_api_link: 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 pfSense Enhanced MCP Server. Nothing to install.
follow_api_link 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 follow_api_link 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 follow_api_link. 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.
follow_api_link is provided by the pfSense Enhanced MCP Server MCP server (mmaxwellcb/pfsesen_mcp_2). 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 →