AI agents invoke bbs_set_size to trigger actions in Mcp Bbs. 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 does more than read or write local data; it triggers an external operation by transmitting a Telnet protocol negotiation (NAWS) to the connected BBS server. This constitutes executing an action that affects the remote session state. The blast radius is low since it only changes terminal display dimensions, but it is an active protocol operation rather than a passive read or simple local write.
From the tool's definition 'Set terminal size and send NAWS' — actively sends a NAWS (Negotiate About Window Size) Telnet protocol signal to the remote BBS session
Attacks that exploit this kind of access
Set terminal size and send NAWS. It is categorised as a Execute tool in the Mcp Bbs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Bbs MCP server in PolicyLayer and add a rule for bbs_set_size: 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 Mcp Bbs. Nothing to install.
bbs_set_size 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 bbs_set_size 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 bbs_set_size. 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.
bbs_set_size is provided by the Mcp Bbs MCP server (livingstaccato/mcp-bbs). 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 →