Get keystrokes for a beacon
AI agents call get_beacon_keystrokes 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 retrieves keystroke logs from a beacon (compromised endpoint), which is a read operation with no side effects on the target system. However, severity is high because keystroke data may contain sensitive information such as passwords, credentials, and private communications. The high severity reflects the sensitivity of the data accessed, not the nature of the operation itself.
From the tool's definition Tool name 'get_beacon_keystrokes' and description 'Get keystrokes for a beacon' indicate retrieval of logged keystroke data from a compromised host without modification or deletion of that data.
Attacks that exploit this kind of access
Get keystrokes for a beacon. 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_keystrokes: 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_keystrokes 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_keystrokes 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_keystrokes. 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_keystrokes 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 →