Get the user
AI agents call get_active_split to retrieve information from Arvo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the user's currently active training split—a read-only query with no side effects. It returns data about the user's training program state but does not create, modify, delete, or execute external actions. Low severity: misuse would only expose training split information, not enable harmful actions.
From the tool's definition Tool name 'get_active_split' and prefix 'get_' indicate a retrieval operation. Description states 'Get the user' which implies querying user state/data without modification.
Attacks that exploit this kind of access
Get the user. It is categorised as a Read tool in the Arvo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Arvo MCP Server MCP server in PolicyLayer and add a rule for get_active_split: 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 Arvo MCP Server. Nothing to install.
get_active_split 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_active_split 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_active_split. 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_active_split is provided by the Arvo MCP Server MCP server (khaoss85/arvo-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 →