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

Enables AI agents to manage prompts and sessions via the ai-agent-logs API, with tools for health checks, login, listing/creating prompts, and retrieving sessions.

Exposes read-only tools for OPC UA PLC tag monitoring and diagnostics, and enables template-driven, validated IEC 61131-3 SCL code generation with a mandatory human review gate before download.

Enables AI agents to analyze text and retrieve real-time system metrics such as CPU, memory, and uptime through LangChain tool calling, with an embedded web UI for testing queries and viewing tool execution logs.

Enables read-only, workspace-bound inspection of repositories and log files, returning JSON reports with file counts, largest files, TODO/FIXME markers, and warning/error counts.

Enables natural language queries for device support, including resolving device references, retrieving device details, historical metrics, and checking provisioning status. Maintains conversation context for multi-turn interactions.

Enables AI SRE agents to query a DynamoDB incidents table using short-lived, read-only STS credentials, with no standing AWS access keys.

Provides a Twitter-like timeline interface where AI agents can post thoughts and progress updates in real-time while working on tasks. It enables users to monitor agent activities through a web GUI and persistent database storage for debugging and session tracking.

Registers a set of inert, tempting decoy tools with any MCP-capable client so that any call from a hijacked or prompt-injected agent instantly raises an alert with full attack context and a per-call trace token. Also plants worthless canary tokens in honeypot files that trigger zero-false-positive leak alerts when they surface in agent output, files, or outbound requests.

Tracks AI agent token usage and spending in real time, with budget alerts, per-task cost breakdown, and a visual dashboard.

MCP server exposing AI agent observability tools: list, inspect, and deterministically replay recorded agent execution traces for debugging failures.

Exposes rate-limit and usage data for AI coding agent CLIs as MCP tools, enabling querying of usage snapshots and reset times.

Self-hosted AI orchestrator that monitors and manages homelab services, exposing them as MCP tools for LLMs to drive.

Find the step that caused an AI agent’s failure. Ask your assistant why a run failed, see the evidence, and check whether a suggested fix works.

Enables AI agents to explore a synthetic product-event dataset and answer questions about signups, trends, funnels, and property breakdowns using a small set of composable, self-describing tools that return precomputed totals and actionable error hints.

Enables AI agents to self-report every tool call, token usage, decision, and session grade into a local SQLite store, so users can trace execution, audit reasoning, and see per-session costs in a local dashboard. Also supports proxy mode to intercept and trace MCP tool invocations for agents that cannot self-report.

An MCP server that provides append-only, tamper-evident local receipts for AI agent actions, capturing command executions, outputs, and handoff evidence.

Local-first observability for AI agent stacks. Provides MCP tools for agents to check health, shadow configs, and burnout metrics proactively.

Enables AI assistants to query system health, metrics, service reconnaissance, run multi-node patrols, and send incident alerts across distributed infrastructure through MCP tools.

Enables real-time communication and orchestration of multiple AI agents with a web dashboard for monitoring agent activities, tasks, and artifacts.

A scheduled MCP server that monitors Auth0 users by periodically collecting summaries, detecting suspicious admins, and auto-blocking them; it provides instant reports via SQLite and exposes tools for on-demand collection and configuration.

Enables natural language queries for AWS CloudWatch logs, metrics, and alarms via an LLM agent with MCP tools.

Local-first MCP server for credit risk analysis. It enables explainable rule discovery, statistical validation, PSI drift monitoring, and root-cause diagnosis on user-approved Parquet data while preserving privacy.

Universal database copilot for diagnostics, operations, and performance analysis via MCP and CLI.

Computes AI agent reliability metrics like success rates, latency statistics, and failure patterns from provided numbers, with zero external API cost.

MCP server that diagnoses Apache Spark job failures and optimizes performance using stack-trace analysis and LLM providers, supporting EMR and local sources.

Enables querying Margint per-customer AI margins and costs from MCP clients. Provides tools to list customers, drill into costs, check budgets, and view workspace-wide cost breakdowns.

Enables AI apps to inspect and manage a NextDNS account in plain language — profiles, analytics, query logs, blocklists, security and parental control settings — with every change saved and reversible via undo. It runs self-hosted on your own computer or server, keeps per-profile read/write/hidden permissions, and requires double confirmation for deletions or overwrites.

An MCP server that provides cost and reliability observability for LLM and agent workflows. It records model calls and allows querying and aggregating telemetry data through MCP tools.

Exposes network-monitoring tools (query metrics, analyze windows, compare, logs, status, runbooks, speed tests) as an MCP server for agentic workflows. Designed with evaluation suites, cost-aware model routing, and semantic tool retrieval.

Provides cost analysis of AI agent usage by previewing scrubbed metadata before upload and analyzing spend, cache-hit rates, and waste recovery through a local or remote server.