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

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.

A local MCP server that lets AI agents send desktop notifications during tasks, ask for attention, and report completion. Supports macOS, Linux, and Windows, with optional webhook delivery.

Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates

Universal session & handoff layer for AI coding agents: shared task, decision, blocker and test state, checkpoints, and deterministic handoff between Claude Code, Codex, OpenCode, Cursor, Cline, pi and omp. Local SQLite, git-aware, 25 tools + 7 resources over stdio or streamable-http.

Encoding-aware, indentation-smart file tools for AI coding agents. 20+ tools including read/edit with automatic encoding detection, smart indentation conversion, SSH, SFTP, process management, and system utilities.

Provides git-aware safe file operations, allowing AI agents to delete files while protecting git-tracked source code from accidental deletion.

A powerful MCP tool for forging and managing AI agent personalities with customizable expert traits and behaviors.

Enables ChatGPT on Windows to securely access codebases, Git, terminals, language servers, debuggers, SQLite, local HTTP services, adaptive project memory, engineering skills, checkpoints, audit logs, and sandboxed command execution through MCP tools.

Enables agents to capture task-scoped residue evidence during test and build workflows, exposing files, directories, processes, and ports for user-authorized cleanup and post-cleanup verification without deleting or modifying anything itself.

Enables AI agents to create, manage, and track tasks within plans using Valkey as the persistence layer. Supports plan and task management with Markdown notes, status tracking, and prioritization through multiple transport protocols (SSE, Streamable HTTP, STDIO).

Enables AI assistants to search PatchXNote records, inspect AI-generated results, create Markdown drafts, and send user-approved messages to webhooks while keeping server data read-only.

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

MCP server that keeps language server sessions warm and routes multiple languages through one process. Agents get persistent cross-file awareness, speculative execution (simulate edits before writing to disk), and 20 skills that encode correct multi-step operations like safe rename, blast-radius analysis, and end-to-end refactoring. Single Go binary, no runtime dependencies.

Enables AI assistants to manage tasks, projects, and dependencies through MCP protocol with embedded Web UI, multi-workspace support, and Turkish language capabilities for productivity tracking.

Exposes three read-only tools that list local Agent and MCP runtime candidates, inspect running processes, and check a live runtime against an approved artifact expectation. Returns explicit verdicts such as matched, stale, leaked, conflict, unknown, or not running without exposing argv, environment values, or file contents.

MCP Guard Server - Budget control, approval workflows and audit logging for AI agents (Claude Code, Cursor, ChatGPT)

Enables coding agents to coordinate in spaces through direct messages, topics, blackboards, and durable inboxes, exposing bus tools over MCP and RPC while pushing inbox updates over SSE.

A memory, docs, and repo context layer for engineering agents, providing typed persistent memory, RAG document retrieval, and repository-aware tools to recall decisions, runbooks, and operational knowledge across sessions.

MCP server for browser debugging, inspection, and verification that streams console logs, network errors, and user actions into AI coding assistants.

Zabbix MCP server and CLI in one Go binary. 15 task-shaped tools: current problems, host investigation, why an alert did or did not arrive, metrics, maintenance. Zabbix 6.4+.

An MCP bridge that lets Codex and Claude Code interact with OpenLinker agents, and allows the host to serve as a callable agent in the OpenLinker network.

Enables AI assistants to explore a PostgreSQL database, run bounded read-only SQL, inspect query plans, test hypothetical indexes, find slow queries, and check database health with compact CSV output.

Provides AI assistants with persistent graph database memory using Neo4j, enabling task management, relationship understanding, semantic search with embeddings, file indexing, and multi-agent coordination through the Model Context Protocol.

Enables AI agents to communicate with business agents across company boundaries using Google's A2A protocol, with tools for discovery, messaging, and connection management.

Stop runaway agents. One gateway in front of all your agent traffic — MCP tools and LLM models — one budget, one kill switch. Sits between AI clients (Cursor, Claude Desktop, Windsurf) and remote MCP servers / OpenAI-compatible model APIs; hard token budgets; a single static Go binary.

Serves the review notes left at lines of a diff in seam, a terminal diff viewer, to an agent with the code around them. The agent answers each note, and the answer shows in seam at that line.

An MCP server that exposes tools for issuing scoped agent credentials, delegating narrower child credentials, handling approvals, revoking task trees, and retrieving audit trails and evidence packets.

A wallet for AI agents: test funds, payments, paid APIs and escrow on Aether. Give an AI agent its own wallet on Aether, a proof-of-work chain with post-quantum (ML-DSA-44) signatures. The agent gets an address and testnet funds in one step, then sends and receives AETH or USDC under per-payment and daily limits you set. It can pay for APIs that answer HTTP 402, sell its own, rate the services it

Agent memory for facts that change. When a user corrects something, Recall replaces the old fact, tells the agent what it replaced, and keeps the old value in a history. Ask what was believed on any date, see every change to a fact, or diff two dates. Runs locally on polign_db, Postgres with pgvector, MongoDB, or Qdrant. Apache 2.0.

An MCP server and an agent skill for imagor, a fast, secure image processing server. An agent writes a layout (OG cards, product grids, quotes, testimonials) and it compiles to one imagor URL, served from your own instance.