AI agents call get_active_program to retrieve information from Pelaris without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about the user's active training programs, including progress metrics, training phases, and session structure. It performs no writes, deletions, code execution, or financial transactions.
From the tool's definition Tool name 'get_active_program' and description 'View your current training programs' indicate data retrieval with no modification or side effects. The verb 'View' and the absence of any modification language confirm read-only access to existing program data.
Attacks that exploit this kind of access
View your current training programs with progress, phase, weekly structure, and session details. It is categorised as a Read tool in the Pelaris MCP Server, which means it retrieves data without modifying state.
Register the Pelaris MCP server in PolicyLayer and add a rule for get_active_program: 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 Pelaris. Nothing to install.
get_active_program 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_program 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_program. 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_program is provided by the Pelaris MCP server (thedonk/pelaris-mcp-server). 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 →