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

An MCP server for external computer-use that launches, observes, and interacts with any X11 application via AT-SPI2 accessibility tree and xdotool input injection.

Official public, read-only Helena Bioinformatics MCP for source-cited answers about the company and its published products.

Exposes user, membership, and role administration tools via MCP, acting as a thin passthrough to a coordinator API with RBAC enforced by the coordinator using caller bearer tokens.

Enables AI assistants to query PostgreSQL, MySQL, SQL Server, Oracle, and MongoDB databases through MCP with read-only, audited access.

MCP server for Majico.xyz that enables coding agents to read (and limited write) brand guidelines, design tokens, studio canvas, and export manifests.

MCP server that turns AI IDEs into a Feedico coupon agent, enabling natural language queries for live affiliate coupons and merchants across multiple languages.

AgentTask is a governed work platform where human teams and AI agents share one backlog. Hosted remote MCP server (streamable HTTP, OAuth 2.1 or org API keys) with 60+ tools for tasks, subtasks, projects, groups, labels, notes, comments, attachments, search, crews, and agent runs.

Enables AI agents to search, browse, and read a field-tested Xperience by Kentico knowledge pack, fetch checklists and blog articles, request consultations, and access L402-gated premium playbooks via Lightning payment.

Enables MCP clients to run local scans for known AI coding-assistant backdoor indicators and risky Claude Code/MCP configuration patterns, returning findings directly in chat.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

Calibrd Agent scores a job against your CV from inside your assistant: fit, seniority gaps, ATS/recruiter CV read, and predicted interview questions. Reports are free (3/day); cover letter and a time-boxed pass unlock when you ask, voice mock stays in Calibrd.com/workspace.

Ask 200+ AI models (Claude, GPT, Gemini, Llama, DeepSeek, Qwen) privately from any MCP client via Obscurify AI zero-data-retention routes. Tools: ask, chat, second_opinion (one prompt to 2-5 models side by side), list_models (prices, context, plan), generate_image and balance.

Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.

MCP server for Winston AI's detection tools, enabling AI content detection, plagiarism checking, image analysis, and text comparison.

CLI and MCP server for AI agent strategy and deployment. Read blueprints, business cases, implementation plans, and specs from your coding agent. 18 tools for listing, retrieving, downloading, and updating blueprints. Exports full implementation specs as Agent Skills directories.

Enables any MCP-capable AI agent to discover and trade onchain Solana funds — launching a fund, depositing, rebalancing, redeeming, swapping tokens, managing an app wallet, and following other traders against the live DFM API. Includes onboarding tools for headless agents and read-only versus write access controlled by an API key and a write-enabled flag.

A local stdio MCP server for visual AI work, offering an Excalidraw infinite canvas, image generation and editing, HTML drafts, presentations, and durable task recovery within a project workspace.

A Model Context Protocol (MCP) server that exposes the EasyDeploy public REST API as tools for Claude, Cursor, Claude Code, and other MCP clients.

Enables agents to hold a local Base USDC wallet, receive funds, make bounded x402 payments, prepare seller registration, and recover Voidpay Marketplace results over stdio.

Enables an agent to run whole browser tasks on live web pages from a plain-language goal — opening tabs, clicking, typing, scrolling, and returning the relevant page sections as markdown — with every step reported alongside its confidence. Tabs can be reused and closed across calls, so multi-step flows continue on the page the previous task ended on.

Official Bitget MCP server for Claude Desktop, Cursor, Windsurf & ChatGPT. Trade crypto via natural language — 89 UTA v3 ops through 14 intent verbs. Local stdio, HMAC signing, read-only & paper-trading modes.

Open-source MCP server for Google Ads (Meta Ads coming soon) that lets AI assistants manage ad campaigns, reporting, keywords, and targeting in plain English from any MCP client, with safety-first creation of paused campaigns.

An AI Concierge replaces static forms with adaptive AI conversations that understand real situations, structure key information automatically, and trigger the right next step. Rigid forms cause drop-off, weaken qualification, and strip away context. Perspective uses adaptive AI to capture structured data and trigger automation, so you understand what truly matters to your customers and can make d

MCP server that provides browser automation capabilities through a Chrome extension, enabling terminal-based agents to interact with any website via a live browser session with optimized context.

Emblem Vault AI. Get a cross-chain wallet out of the box and do everything crypto with our terminal! Token discovery, swaps, cross-chain bridges, NFTs, prediction markets...

Provides AI agents with a free, functional email address via the Model Context Protocol without requiring manual registration. It enables comprehensive email capabilities including sending, receiving, and managing messages, contacts, and automated settings.

Enables long-horizon autonomous task checkpointing and resumption through cryptographic event-sourced state persistence, idempotency key deduplication, timeout heartbeats, human-in-the-loop pause/resume tokens, and fail-safe recovery.

Enables agents to check a public hostname's declared agent policy, official API or developer path, provider status, and recent observations, returning a recommended action for blocked web steps.

A neutral verification court for AI tools that ranks MCP servers by executing them against ground truth and recording results. Enables agents to consult execution records, contribute verdicts, and challenge claims.

This MCP server lets AI agents connect to Figma to read, analyze, create, and modify designs, including elements, styles, assets, and code generation. It works with free Figma accounts and supports parallel multi-agent use across MCP-compatible clients.