AI agents call get_all_agents to retrieve information from Mythic MCP 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 information about active agents from the Mythic C2 framework without side effects. It is a read operation. Severity is medium rather than low because the information returned (list of active compromised agents) is sensitive in a penetration testing context and could inform further malicious actions by an AI agent, but the tool itself performs no destructive or executing operations.
From the tool's definition Tool name is 'get_all_agents' and description states 'Returns a list of active agents' — a retrieval operation with no modification or execution of external actions.
Documented attack patterns abuse exactly the kind of access get_all_agents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mythic MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_all_agents:
{
"version": "1",
"default": "deny",
"tools": {
"get_all_agents": {}
}
}get_all_agents 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.
Returns a list of active agents. It is categorised as a Read tool in the Mythic MCP MCP Server, which means it retrieves data without modifying state.
Register the Mythic MCP server in PolicyLayer and add a rule for get_all_agents: 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 Mythic MCP. Nothing to install.
get_all_agents 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_all_agents 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_all_agents. 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_all_agents is provided by the Mythic MCP server (xpn/mythic_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Mythic MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Mythic MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.