Get prioritized list of tasks based on organizational context.
AI agents call get_priorities to retrieve information from Quarterback 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 prioritized task information without creating, modifying, deleting, or executing any operations. It is purely informational, making it a Read category tool with low severity since data retrieval has minimal security risk unless the data itself is highly sensitive (which is not indicated here).
From the tool's definition Tool name 'get_priorities' and description 'Get prioritized list of tasks' indicate a retrieval operation with no side effects. The word 'Get' explicitly denotes a read action that queries existing data.
Attacks that exploit this kind of access
Get prioritized list of tasks based on organizational context. It is categorised as a Read tool in the Quarterback MCP Server, which means it retrieves data without modifying state.
Register the Quarterback MCP server in PolicyLayer and add a rule for get_priorities: 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 Quarterback. Nothing to install.
get_priorities 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_priorities 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_priorities. 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_priorities is provided by the Quarterback MCP server (bobbyrgoldsmith/quarterback). 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 →