AI agents use bbs_auto_learn_menus to create or update resources in Mcp Bbs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Bbs environment.
This tool modifies stored rules/configuration for menu learning behavior. While reversible (rules can be updated again), it has potentially high blast radius if an AI agent sets malicious menu rules that cause the BBS client to misinterpret screens, navigate incorrectly, or trigger unintended actions on legacy systems.
From the tool's definition Tool description states 'Set auto-learn menu rules from JSON' — the verb 'set' indicates modification of configuration state.
Attacks that exploit this kind of access
Set auto-learn menu rules from JSON. It is categorised as a Write tool in the Mcp Bbs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Bbs MCP server in PolicyLayer and add a rule for bbs_auto_learn_menus: 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_auto_learn_menus is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the bbs_auto_learn_menus 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_auto_learn_menus. 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_auto_learn_menus 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 →