AI agents call get_account_pool 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 retrieves account pool and identity information from a BBS system. While it is a Read operation (no data modification), the severity is elevated to medium because account and identity data is sensitive in nature. An AI agent could misuse this to enumerate credentials, gather personal information, or identify accounts for targeted attacks.
From the tool's definition Tool name is 'get_account_pool' with description 'Fetch manager account-pool and identity summary.' The verb 'Fetch' and the retrieval-oriented nature indicate data query without modification.
Attacks that exploit this kind of access
Fetch manager account-pool and identity summary. 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 get_account_pool: 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.
get_account_pool 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_account_pool 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_account_pool. 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_account_pool 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 →