select_prompt
AI agents call select_prompt to retrieve information from PromStack MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name alone, 'select_prompt' most likely retrieves or selects a prompt for use, which is a read operation. However, the empty description significantly lowers confidence. In the context of sibling tools (get_prompt, list_prompts, query_context, export_skill), this tool appears to be part of a prompt discovery/selection workflow, suggesting a read/query operation.
From the tool's definition Tool name is 'select_prompt'; description is empty or uninformative.
Attacks that exploit this kind of access
select_prompt. It is categorised as a Read tool in the PromStack MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PromStack MCP Server MCP server in PolicyLayer and add a rule for select_prompt: 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 PromStack MCP Server. Nothing to install.
select_prompt 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 select_prompt 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 select_prompt. 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.
select_prompt is provided by the PromStack MCP Server MCP server (promstack-1/mcp-server). 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 →