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

Provides read-only tools to search and retrieve timestamped transcript evidence from the Pinkbike Podcast, enabling bike research questions to be answered with cited source passages.

Enables LLMs to query documents using semantic search, supporting PDFs, Word, Excel, and more. Organizes documents by topics from folder structure and provides advanced search features like phrase matching and date filtering.

Exposes two tools, ask and search, over both streamable HTTP and stdio transports, letting MCP clients pull grounded, inline-cited answers or ranked chunks from an indexed corpus of registered repositories and web pages. The HTTP endpoint is unauthenticated and pinned to the public visibility tier, while the stdio proxy carries the caller's API key and therefore their tier.

Enables users to search Samin Yasar's video library and receive full-video recommendations grounded in transcript evidence with links to exact matched caption cues.

About Your task manager is the best agent memory you're not using. An agent-native context layer over your existing task app.

MCP server for querying PanDA documentation, analyzing job errors, and retrieving JSON data using multiple AI models.

Lets Claude Code and Claude Desktop retrieve and explore an Obsidian vault through tools for semantic search, reading notes, following graph neighbors, and listing topics.

Enables Claude to answer plain-English questions by listing and describing database tables, running read-only SQL queries, and searching a folder of policy documents.

Improves AI agent task performance by providing task area segmentation, hierarchical RAG, and hybrid search capabilities.

Enables AI assistants to answer questions about the operator's current focus, engagements, reusable patterns, availability, and service offerings, with responses grounded in structured data and including confidence labels and source citations.

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.

A stdio MCP server that provides a single tool to query Gemini with Google Search grounding for current web information, returning synthesized answers with source links.

Async MCP server for running long-running AI tasks with real-time progress monitoring, enabling users to start, monitor, and manage complex AI workflows across multiple models.

Enables MCP clients like Claude Desktop to query a grounded, citable corpus of five 2025 publications and a CV summary through tools and a resource, preventing hallucinations about the profile.

Local RAG MCP server for documentation that indexes markdown repos (local paths or git URLs) and provides retrieval-only tools (ask_docs, list_docs, reindex) returning grounded passages and citations for the MCP host to synthesize answers.

Enables natural-language querying of historical AI news through tools that return database statistics and semantic search results over existing SQLite and Chroma data, including titles, links, sources, content, and vector distances.

Enables AI agents to interact with any website through MCP, providing structured knowledge graph contexts, generated actions, and readiness scoring.

Enables AI assistants to handle customer support by looking up order status, semantically searching knowledge bases, and creating support tickets through MCP tools, with grounded answers and automated evaluations.

Automatically routes natural language questions to RAG or Text2SQL paths to answer queries about virtual construction site data, supporting semantic search and structured aggregation.

Enables natural language question answering over academic PDFs with grounded answers, exact source attribution, and explicit uncertainty handling.

Enables travel-related queries and planning including weather, train and flight information, itinerary generation, and travel knowledge retrieval via RAG, using an AI agent with MCP protocol.

Exposes task management (add, list, complete tasks) and document search (RAG) as MCP tools for AI agents.

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.

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.

Provides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.

Enables searching and retrieving documentation from crawled documentation sites as an MCP server, allowing coding agents to query real docs instead of relying on training data.

A tool that creates MCP (Model Context Protocol) servers from OpenAPI/Swagger specifications, enabling AI assistants to interact with your APIs.

Enables loading CSV text, filtering and aggregating datasets over Streamable HTTP, and optionally using Amazon Bedrock to turn query results into concise answers suitable for speech.

Enables a unified AI assistant that combines document retrieval (RAG), database queries via MCP tools, and web search, allowing users to ask complex questions and receive answers from multiple enterprise sources.

An AI apprentice system that allows users to train AI through demonstration, correction, and review, with structured task execution and emphasis on packaging design workflow.