AI agents call bbs_debug_bot_state to retrieve information from Mcp Bbs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval and debugging diagnostics. It queries and returns the current state of an active bot without making changes to the system, executing commands, or affecting data integrity. The description explicitly lists what it retrieves (strategy, errors, progress) rather than what it modifies or executes, placing it clearly in the Read category.
From the tool's definition The tool 'bbs_debug_bot_state' retrieves runtime state information including 'strategy, errors, and progress' with no indication of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get active bot's runtime state including strategy, errors, and progress. It is categorised as a Read tool in the Mcp Bbs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bbs MCP server in PolicyLayer and add a rule for bbs_debug_bot_state: 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_debug_bot_state 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 bbs_debug_bot_state 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_debug_bot_state. 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_debug_bot_state 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 →