AI agents call get_hubs to retrieve information from APS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about hubs accessible to the authenticated user. It performs no modifications, deletions, code execution, or financial transactions. The operation is a straightforward read/list action with minimal risk if exposed to an AI agent, as it only reveals existing organizational structures the user already has access to.
From the tool's definition Tool name 'get_hubs' and description 'Get all available hubs the user has access to' indicate a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_hubs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and APS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_hubs:
{
"version": "1",
"default": "deny",
"tools": {
"get_hubs": {}
}
}get_hubs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all available hubs the user has access to. It is categorised as a Read tool in the APS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the APS MCP Server MCP server in PolicyLayer and add a rule for get_hubs: 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 APS MCP Server. Nothing to install.
get_hubs 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_hubs 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_hubs. 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_hubs is provided by the APS MCP Server MCP server (kpphillips/aps-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from APS MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 APS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.