Attempt to authenticate as another user (network calls only) for the current session.
AI agents invoke run_as_user to trigger actions in Mythic MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes authentication attempts as another user, which is an operational action with external side effects (network calls, session state changes). While not destructive or financial, it clearly performs operations beyond simple data retrieval.
From the tool's definition "Attempt to authenticate as another user" indicates the tool executes authentication operations that change session context and can trigger network calls with potentially privileged access.
Documented attack patterns abuse exactly the kind of access run_as_user 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 run_as_user:
{
"version": "1",
"default": "deny",
"tools": {
"run_as_user": {
"limits": [
{
"counter": "run_as_user_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_as_user stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Attempt to authenticate as another user (network calls only) for the current session. It is categorised as a Execute tool in the Mythic MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mythic MCP server in PolicyLayer and add a rule for run_as_user: 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.
run_as_user is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_as_user 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 run_as_user. 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.
run_as_user 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.