"How to allow an LLM to ask questions to a user" matching MCP servers:

LLM Optimizer is an AI visibility intelligence platform. It analyzes how large language models and AI search engines perceive, cite, and recommend brands; then provides research-backed optimization strategies to improve that visibility.

Local MCP server for asynchronous coding-agent delegation, enabling Claude Code or Codex to delegate tasks to Cursor, Pi, Codex, or Claude Code and collect results later.

Human-in-the-loop MCP hub for Claude Code agents, enabling agents to ask questions, request approval, or report status to a human via an Obsidian plugin.

Turn any OpenAPI/Swagger/Postman spec into an MCP server — give your LLM live access to any API.

Probe LLM API endpoints and report health metrics including time to first token, latency, and throughput.

MCP server that exposes Kafka debugging to an LLM: find messages, measure lag, unblock consumers. Read-only endpoints, previews before writes.

An MCP server that lets AI publish markdown documents to a clean, themed web UI. One tool call creates a shareable doc.

Connect Legacy Databases to AI Agents via Model Context Protocol. Open-source bridge for LLM data analysis.

A TypeScript server implementing the Model Context Protocol that provides secure code execution in isolated Docker containers, allowing LLM applications to safely run Python, Go, or JavaScript code snippets.

Open-source MCP and LLM gateway that aggregates MCP tools behind a unified endpoint with governance, observability, and explicit execution controls.

The official Hostim MCP server, built into the hostim CLI. An agent can deploy a Docker image or a Git repository, create managed Postgres, MySQL and Redis, add volumes and custom domains, and read app status, logs and events. Hostim runs on EU bare metal in Falkenstein, Germany. Read-only by default; tools that create, change or delete need --allow-write.

Enables AI coding assistants to search and retrieve information from a locally ingested knowledge base using hybrid search, grounded in user-curated documentation.

Enables publishing self-contained HTML files or directories to get short, readable links, with an MCP tool for agents to create and manage previews.

Enables LLMs to read and search X posts, manage users and lists, upload media, and publish posts using the X API v2 with OAuth user context.

Enables an assistant to work inside gitlab.com projects as the signed-in user: issues, merge requests, code reviews, repositories, CI pipelines and job logs, plus optional gated toolsets for wiki, snippets, releases, planning, deployments and activity. It authenticates through a user-supplied OAuth application with the token kept in the OS keyring, and registers only the tools that are switched on.

Description: Introduce Beelzebub, an MCP‑based honeypot framework that enables creating decoy tools to detect prompt injection and malicious agent behavior. Motivation: Strengthen the security of LLM workflows by adding a non‑intrusive detection mechanism.

An MCP server to create secure code sandbox environment for executing code within Docker containers.

An MCP server for the Last.fm API, exposing artist, album, track, chart, and user data as read-only tools. Supports optional writes, auth, and experimental methods over stdio or HTTP.

Enables AI assistants to structurally understand a Moodle installation and its plugins, so they can answer codebase questions and scaffold plugins that follow existing conventions. It scans Moodle sources and generates Markdown context files, indexes, and MCP tools/resources/prompts for querying, diagnosing, and maintaining that understanding.

A policy and audit layer for Model Context Protocol (MCP). MCP Firewall sits transparently between any MCP client (Claude Desktop, Cursor, VS Code, etc.) and an upstream MCP server, allowing you to inspect, allow, block, or audit requests before they reach the server.