Present decision points in workflows (requirements, ideation, specification, conceptual work) where you need human input to choose the next focus area or approach. Use this when you have multiple viable paths forward and need human judgment to decide which direction to pursue. The user will see o...
AI agents call choose-next to retrieve information from AskMeMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a user input solicitation mechanism with no side effects. While it affects control flow, it is fundamentally a read operation that retrieves a human decision. The tool cannot independently execute actions, modify data, or commit to operations; it only gathers information to guide downstream logic. The phrase 'pause execution and wait for responses' confirms it is blocking communication, not autonomous action.
From the tool's definition The tool presents decision points and requests human input via interactive selection ('animated boxes they can click to select').
Attacks that exploit this kind of access
Present decision points in workflows (requirements, ideation, specification, conceptual work) where you need human input to choose the next focus area or approach. Use this when you have multiple viable paths forward and need human judgment to decide which direction to pursue. The user will see options as visually appealing, animated boxes they can click to select. Perfect for: workflow decisions, requirement prioritization, feature selection, design direction choices, technical approach decisions, or any. It is categorised as a Read tool in the AskMeMCP MCP Server, which means it retrieves data without modifying state.
Register the AskMe MCP server in PolicyLayer and add a rule for choose-next: 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 AskMeMCP. Nothing to install.
choose-next 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 choose-next 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 choose-next. 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.
choose-next is provided by the AskMe MCP server (thlandgraf/askme-mcp). 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 →