"Search for HITL (Human-in-the-Loop or other possible acronyms)" matching MCP servers:

Enables AI assistants to interact with humans through GUI dialogs for text input, choices, confirmations, and information display.

Enables AI assistants like Claude to interact with humans through intuitive GUI dialogs, supporting text input, choices, confirmations, and information displays.

MCP server that lets an AI analyst place real bets on Binance prediction markets, using Kelly criterion sizing, and tracks its performance through a transparent record of betting slips and outcomes.

Enforces mandatory human approval before LLM agents can edit files, create files, or execute shell commands, using session tokens and audit logging.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

MCP server that analyzes your writing style to generate personal voice rules, scores drafts for AI slop, and verifies authorship, enabling LLMs to write in your specific voice.

An MCP server that allows AI assistants to utilize human capabilities by sending requests to humans and receiving their responses through a Streamlit UI.

DingDawg Loop Protocol (DDLP) — safe scheduled AI agents with governance gates. Every loop execution is verified, receipted, and fail-closed. MCP-native, works with CrewAI, LangGraph, Claude Code, Cursor.

A cross-platform MCP server implementing the Ralph Loop iterative development technique where a worker model does the work and a reviewer model provides cross-model review until approval.

Enables structured learning with a verified loop: define goals as observable claims, learn through teach-lab-test-gate per claim, and get independently graded by an adversarial examiner to ensure genuine progress.

Enables AI agents to index, search, and validate lessons learned across project repositories via a local SQLite index, providing learning-loop resources and verified-solution tracking without loading full files into conversations.

Enables Codex and DeepSeek Harness to maintain a local, traceable record of current task intent, separating requirements, evidence, unknowns, and disagreements while preserving corrections without erasing history.

Enables context-loop navigation in agents by exposing goto and loop_start_marker tools that delegate to a host over a Unix socket, allowing bookmarking and jumping between context iterations.

Enables AI agents to request human actions or decisions by opening a local browser page for input, allowing the agent to pause and wait for human response.

Lets AI agents retrieve, search, and inspect generated lesson packs and rubrics, and enqueue new concepts for the lesson production workflow.

MCP server that gives AI agents access to current web information through web_search and fetch_url tools, using Tavily, Brave, and DuckDuckGo providers with automatic fallback.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

Human-in-the-Loop approval gate for AI agents to assess risky operations and require user approval via Cursor forms.

The industry-standard persistent memory and state manager for long-running agentic workflows.

Enables AI agents to orchestrate tasks as a DAG with automated validation loops, executing validation commands, tracking statuses, and allowing iterative code fixes until tasks pass.