Run Mimikatz on a beacon
AI agents invoke spawn_mimikatz to trigger actions in Cobalt Strike MCP Server. 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 is Execute (not Read/Write) because it triggers external operations (spawning and running a sophisticated post-exploitation tool on a remote system) whose effects depend on the target system state and Mimikatz's behavior.
From the tool's definition The tool 'spawn_mimikatz' executes Mimikatz, a well-known credential dumping tool that runs code on a compromised system ('beacon'). The description explicitly states it 'Run[s]' the tool, indicating code execution.
Attacks that exploit this kind of access
Run Mimikatz on a beacon. It is categorised as a Execute tool in the Cobalt Strike MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cobalt Strike MCP Server MCP server in PolicyLayer and add a rule for spawn_mimikatz: 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 Cobalt Strike MCP Server. Nothing to install.
spawn_mimikatz 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 spawn_mimikatz 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 spawn_mimikatz. 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.
spawn_mimikatz is provided by the Cobalt Strike MCP Server MCP server (mickeydb/cobalt-strike-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 →