Link to SMB beacon
AI agents invoke execute_link_smb 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 tool directly facilitates establishing a control channel between beacons in an active compromise scenario. While not destructive in itself, the act of linking SMB beacons enables the execution of arbitrary commands and lateral movement on target systems.
From the tool's definition 'Link to SMB beacon' enables execution of SMB protocol operations through a Cobalt Strike beacon, which is a remote code execution mechanism.
Attacks that exploit this kind of access
Link to SMB 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 execute_link_smb: 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.
execute_link_smb 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 execute_link_smb 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 execute_link_smb. 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.
execute_link_smb 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 →