Get help for beacon commands
AI agents call get_beacon_help to retrieve information from Cobalt Strike MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about available beacon commands. It is a read-only operation that retrieves help documentation without modifying state, executing code, or affecting beacon operations. The low severity reflects that misuse would only expose command documentation to an AI agent, which is already accessible in standard Cobalt Strike usage.
From the tool's definition Tool name is 'get_beacon_help' and description states 'Get help for beacon commands' - this retrieves documentation/help text with no side effects.
Attacks that exploit this kind of access
Get help for beacon commands. It is categorised as a Read tool in the Cobalt Strike MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cobalt Strike MCP Server MCP server in PolicyLayer and add a rule for get_beacon_help: 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.
get_beacon_help 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_beacon_help 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_beacon_help. 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_beacon_help 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 →