AI agents call get_goal_phases 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 and returns goal phase data from the active strategy without modifying, creating, or deleting anything. It has no side effects and merely exposes information already present in the system. The blast radius of accidental misuse is minimal—returning incorrect or nonsensical data would not cause operational damage. Low severity is appropriate for read-only operations on a legacy BBS system.
From the tool's definition Tool name 'get_goal_phases' and description 'Return raw goal phase data' indicate a retrieval operation with no modification of state. The verb 'return' and context of 'reading' data from an active strategy confirms read-only semantics.
Attacks that exploit this kind of access
Return raw goal phase data (if the active strategy supports it). 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_goal_phases: 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_goal_phases 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_goal_phases 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_goal_phases. 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_goal_phases 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 →