AI agents call capabilities 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 queries and returns information about available capability groups and task entrypoints. It performs a lookup or enumeration operation typical of introspection tools, which are informational and non-destructive. There is no indication of modification, deletion, code execution, or financial operations. The read operation has minimal blast radius—an AI agent cannot cause damage by invoking this tool.
From the tool's definition Tool name is 'capabilities' and description states 'Describe TW2002 MCP capability groups and fastest task entrypoints.' The word 'describe' and the stated purpose of providing information about capabilities and entrypoints indicate a read-only retrieval…
Attacks that exploit this kind of access
Describe TW2002 MCP capability groups and fastest task entrypoints. 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 capabilities: 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.
capabilities 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 capabilities 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 capabilities. 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.
capabilities 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 →