"Allowing an AI agent to ask user questions during a task" matching MCP servers:

Enables AI models to ask users questions through a local web interface, supporting batch questions, multi-select, and free text for human-in-the-loop interactions.

MCP server that enables Claude to pause and ask clarifying questions via Emacs.

Enables Codex to clarify requirements via native MCP elicitation controls, supporting single/multiple-choice and free-text questions with recommended answers and a discuss-first option.

Lets Claude Code conduct long, structured interviews via a keyboard-driven local web form, with unlimited questions and options, recommendations, ranking, previews, and live follow-up questions.

It enables AI agents to parse user agent strings into structured data such as browser, OS, device type, engine, and bot status, with pay-per-call micropayments via x402 and no API key or signup required.

Enables AI agents to decompose high-level goals into structured task plan DAGs with dependencies, acceptance criteria, and quality gates, and to validate or export those plans in multiple formats.

Enables real-time user intervention for MCP agents through a web UI, allowing users to review context and provide feedback when AI agents drift from intent, keeping them on track.

Local MCP server that connects VS Code agents like Cline to OpenAI and provides workspace file tools (read, write, list) with restricted file access.

Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor. This is especially useful for developing desktop applications that require complex user interactions to test.

Enables AI agents like Claude to interact with Figma designs through 50+ tools for creating, styling, and manipulating design elements, components, and variables via a WebSocket relay and Figma plugin.

Enables users to request a second opinion from a locally authenticated Claude Code model via MCP tools, supporting asynchronous jobs with restricted tools for safety.

It enables AI agents to call a small set of reliable, permission-aware tools generated from an existing website through the Model Context Protocol, without rebuilding the site.

Enables real-time user intervention for MCP agents via a Web UI and interactive_feedback tool, allowing users to review context and send instructions when agents drift from intent.

An MCP server for AI-to-AI collaboration via the Gemini CLI. Available on npm: ask-gemini-mcp. Works with Claude Code, Claude Desktop, Cursor, Warp, Copilot, and 40+ other MCP clients. Leverage Gemini's massive 1M+ token context window for large file and codebase analysis while your primary AI handles interaction and code editing.

Provides AI coding agents with a read-only live view of a project's task state, including progress, blockers, and evidence, via zero-token conditional polling and an optional widget for rendering a dashboard card.

Provides access to multiple AI models (Grok, Gemini 2.5 Pro, Kimi, Qwen3 Coder, GLM-4.5) through OpenRouter, enabling users to query different specialized models for reasoning, coding, translation, and general tasks with automatic fallback to free variants.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Enables Oracle Database schema introspection and SQL execution over stdio, letting MCP hosts list tables, describe columns, and run SQL—read-only by default with opt-in writes.

Enables MCP clients to send raw text prompts to inexpensive LLM models via the Devin/Windsurf backend, returning answers in result files to avoid context bloat, with support for multi-turn sessions and model discovery.

A cross-AI-agent local task context sharing MCP server that allows clients like Codex, Claude Code, Hermes, and VS Code to read and write the same task state, enabling task tracking and context distillation.