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

Enterprise support memory agent that remembers customer context across sessions, retrieves relevant memories, and forgets stale facts to reduce re-ask rates.

A multi-modal user intent collection MCP server that allows AI agents to ask users questions and receive text/image replies.

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the results. Free AI moderation. Uses an organization API token from askone.org

An MCP server for the EaseCation user center that provides admin and user tools to interact with UC backend services.

Enables voice assistants to find nearby service providers, connect users to live video representatives for natural conversation, and handle appointment booking. It also returns confirmed bookings so the assistant can add them to its calendar.

Enables Boneyard to call authenticated, stateless Streamable HTTP tools for searching tickets and adding ticket comments, with caller context, attribution, and bounded results.

Fetches category data from a Q&A service API and returns a markdown summary grouped by category.

Enables agents to search answered tickets, ask new questions, and answer waiting questions on the shared help desk, while providing read-only observation of visits.

Enables AI assistants and agents to ask support questions, search knowledge articles, and list available articles from a configured support bot through MCP tools.

Enables users to ask natural-language questions about why an account's bill changed and receive ranked, evidence-linked explanations grounded in computed SQL diffs, with enforced per-session authorization so agents cannot access unauthorized accounts or modify ledgers.

Enables LLM clients to answer identity-aware questions about customer calls using a multi-tenant B2B call analytics platform with role-based access.

Enables Claude to make outbound phone calls through Vapi API, supporting any call type and language with features like call initiation, result polling, and structured data extraction.

Enables AI agents to prompt users for input directly within the chat UI using MCP's elicitation capabilities, allowing for interactive multi-turn conversations without leaving the conversation interface.

Provides MSP support tools (ticket search, draft response, KB search, update) with a deterministic security guardrail that refuses to draft responses for security tickets based on content scanning, even if mislabeled.

Provides ServiceNow ITSM tools (incidents, knowledge, CMDB, user lookups) to AI agents, with an evaluation harness that measures tool-selection accuracy, task completion, and latency.

Enables MCP-compatible clients to act as an AI receptionist for a small medical clinic, handling appointment booking and rescheduling, patient registration, intake, reminders, and FAQ answers.

Enables reading Apple App Store customer reviews, publishing developer responses, and deleting them via the App Store Connect API with a narrow Customer Support role.

MCP server that synthesizes user feedback from multiple sources into actionable insights. Aggregates reviews, support tickets, and survey responses to identify patterns and priorities.

Enables Turkish e-commerce sellers to manage Trendyol marketplace store operations through AI assistants, including viewing products, orders, returns, and customer questions, with optional guarded write actions for answering questions and updating stock and prices.

Enables small-business AI assistants to answer customer questions about hours, offerings, FAQs, staff, and booking from a single business.yaml config, with industry-specific tools and guardrails.