Get useful development prompts for code improvement
AI agents call get_prompts to retrieve information from Shell Executor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static prompts for developer use. It has no side effects, does not execute code, does not modify data, and does not access sensitive resources. Despite being on a Shell Executor MCP server, this particular tool is purely informational and falls squarely under the Read category with minimal risk.
From the tool's definition Tool name is 'get_prompts' and description states 'Get useful development prompts for code improvement' — retrieves or queries prompts without modifying data or executing commands.
Attacks that exploit this kind of access
Get useful development prompts for code improvement. It is categorised as a Read tool in the Shell Executor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Shell Executor MCP Server MCP server in PolicyLayer and add a rule for get_prompts: 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 Shell Executor MCP Server. Nothing to install.
get_prompts 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_prompts 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_prompts. 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_prompts is provided by the Shell Executor MCP Server MCP server (kosiew/zmcp). 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 →