check_prompts

Check all sessions for interactive prompts that need user attention.

Server Claude Code MCP Controller mostafa-drz/claude-code-mcp-controller
Category Read
Risk class Low
Parameters 00 required

What check_prompts does on Claude Code MCP Controller

AI agents call check_prompts to retrieve information from Claude Code MCP Controller without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why check_prompts needs a policy

This tool retrieves status information about pending prompts across sessions without modifying, executing, or deleting anything. It is informational/observational in nature. Low severity because the information disclosed (pending prompts) is unlikely to cause substantial harm even if misused by an agent, though it could reveal sensitive context from user interactions.

From the tool's definition Tool name 'check_prompts' and description 'Check all sessions for interactive prompts that need user attention' indicate a query/monitoring operation with no side effects.

Questions about check_prompts

What does the check_prompts tool do? +

Check all sessions for interactive prompts that need user attention. It is categorised as a Read tool in the Claude Code MCP Controller MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on check_prompts? +

Register the Claude Code MCP Controller MCP server in PolicyLayer and add a rule for check_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 Claude Code MCP Controller. Nothing to install.

What risk level is check_prompts? +

check_prompts is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit check_prompts? +

Yes. Add a rate_limit block to the check_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.

How do I block check_prompts completely? +

Set action: deny in the PolicyLayer policy for check_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.

What MCP server provides check_prompts? +

check_prompts is provided by the Claude Code MCP Controller MCP server (mostafa-drz/claude-code-mcp-controller). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

check_prompts is one line of Claude Code MCP Controller's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.