Passive loop detection MCP server for AI coding agents

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

MCP server for self-verifying AI agent loops: schedules, independent checker gates, stop rules, worktree isolation & durable state. Built for Cursor/Kiro/Claude via MCP. Inspired by the loop-engineering work of @addyosmani, @anthropics, and Codez (@0xCodez).

Stop your agent replying to an autoresponder, a bounce, or another bot. Checks a thread before every reply for the signs of a loop, on any channel, with an optional ledger across threads. CLI, MCP server, library. Zero dependencies.

Loop Factory MCP — a local-first supervisor for evidence-gated AI agent loops. Mines past agent sessions for workflows that worked, improves them generation over generation, and only promotes a measured, re-verified win. Zero dependencies, MCP over stdio.

Self-correcting 7-stage agent reasoning loop (SENSE→GKP→DECIDE+ACT→CHALLENGE-TEST→UPDATE→LEARN→REPORT). MCP server + CLI that scaffolds instruction files for GitHub Copilot, Cursor, and Claude Code.

Stop your agent replying to an autoresponder, a bounce, or another bot. Checks a thread before every reply for the signs of a loop, on any channel, with an optional ledger across threads. CLI, library, and MCP server. Zero dependencies.

MCP server that detects and prevents infinite agent loops — circuit breakers, pattern detection, and stuck-agent recovery for agentic systems

MCP Server for ORACLE-H — Human-on-the-Loop validation for autonomous AI agents

A MCP server implementing the Dual-Cycle Metacognitive Reasoning Framework for autonomous agents. A loop prevention and experience recall mechanism.

WhatsApp MCP Server: Human-in-the-loop for AI agents via WhatsApp for confirmations, notifications, and interactive questions.

Read-only MCP server for the AI Loop Library: pick bounded, verifiable agent work loops and render runnable protocols. Single file, stdlib-only.

VantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents

MCP server that closes the feedback loop for AI coding agents — CI results, deployments, test outcomes, file changes

Human-in-the-loop review and approval for AI agents. MCP server at mcp.agentfabric.dev

Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn

MCP server that detects and prevents infinite agent loops — circuit breakers, pattern detection, and stuck-agent recovery for agentic systems

Official MCP server for Datashift — human-in-the-loop review workflows for AI agents

🐝 The Swarm Orchestration Layer for Complex Agentic Work. Breaking the Hallucination Loop with high-force parallel delegation.

MCP server that enforces multi-agent scope boundaries — prevents scope drift, work duplication, and infinite delegation loops in agentic systems

Elicitly Free Edition — human-in-the-loop for prompts and Agent Skills over MCP elicitation. Local MCP server (npx -y elicitly) + embeddable toolkit (@elicitly/tools).

Browser for agents: isolated login environments, human-in-the-loop, local MCP + workflows. 给 Agent 用的本机浏览器。官网 browser.xyun.dev

MCP server that allows AI agent ask you questions in the middle of its work (Human-in-the-loop)

Open source agent workforce platform. Next.js + Postgres + MCP server for AI agent teams with human-in-the-loop review, built in.

A股多Agent量化交易决策框架 — LangGraph 15位AI分析师辩论式分析，反思闭环+Token优化，支持DeepSeek/Qwen/GLM，附零依赖MCP server | Multi-agent A-share trading framework with reflection loop & MCP server

Autonomous operational reporting agent built on TrueForge with custom Slack MCP (SSE), sandboxed Python analytics, and human-in-the-loop safety gates.

Whiskers — Zero-Trust MCP Control Plane for Docker & Kubernetes. Tactile observability, mTLS mesh, blast-radius guardrails, and human-in-the-loop approvals for AI agents.

BFT Progress Council MCP — 5-voter Byzantine council halts agentic loops when no real progress is happening. Stops tokens bleeding on infinite spins. By MEOK AI Labs.

MCP server that allows AI agents to ask questions to a human expert via Telegram. Provides a human-in-the-loop solution when agents need expert guidance.

Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.

Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.

MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

Spend approval gate for AI agents — enforce budget limits, per-asset caps and human-in-the-loop thresholds before an agent moves money, with a signed audit hash.

A local message hub that connects multiple Claude Code sessions and a human. Agents get named mailboxes, roles and subscriptions; a browser UI shows who is waiting on you. The human stays in the loop — no automatic forwarding.

A Model Context Protocol (MCP) server exposing ERP-style data (sales orders, inventory, purchase requisitions) to AI agents — with a real human-in-the-loop approval gate on write actions. FastAPI + FastMCP + PostgreSQL, Streamable HTTP transport, Dockerized, tested.

MCP server that lets coding agents (Claude Code or any MCP client) work autonomously within a session budget — with a dependency graph, human decision queue, required validation and exact handoff. OUTSIDE_MODE for bounded autonomy, DESK_MODE for human-in-the-loop.

Deprecated: replaced by hitl (Human In The Loop, npx hitl), which does everything questionme does. Questions from an LLM agent, answered on your phone: hundreds at a time, with rich content (files, code, diffs, diagrams, mockups), branching follow-ups, an

MCP server that lets Claude Code, Codex & AI agents drive a real Chrome browser with JEV (TypeSafe System One): ~100 ms typed decisions, calibrated confidence, human-in-the-loop questions, safety gates and a debug trace.

️ Litagatoro: The Premium Human-in-the-Loop Voice Oracle for AI Agents. Enables AI to hire real humans for voice tasks (verifications, acting, identity checks) on the Polygon network. Includes a Python SDK and MCP server for seamless integration with Claude, GPT-4, and autonomous agents using USDC escrow.

Undo for AI agents: an MCP proxy that checkpoints every tool call before it runs, so a bad `DROP TABLE` or `rm -rf` rolls back in seconds. Risk scoring, human-in-the-loop approval, tamper-evident audit log, dashboard, and MCP servers for PostgreSQL/MySQL/SQLite. Local-first, MIT, TypeScript, Node 20+.

Loop engineering substrate for coding agents — state, lossless optimization, and hook enforcement: verify-gated loops that can't lie, run away, or go broke. For Claude Code, Codex, Cursor, Gemini CLI, VS Code Copilot, and any MCP client.

Context management platform for agentic, human-in-the-loop development

Looped agent orchestrator: an MCP server that runs Claude Code sessions against machine-checkable success criteria

an agentic tool that simplifies complex institutional texts to meet readability targets using a multi-agent feedback loop.

Alice: the continuity layer for AI agents. Local-first memory with provenance, open loops, resumption, and review-governed writes.

Secure local MCP bridge for ChatGPT and local agents, with workspace-scoped task loops, safe summaries, audits, and Direct editing.

FastAPI chat agent & FastMCP weather server, end-to-end Model Context Protocol with a local MCP client and agentic tool loop

AI coding agent orchestration at scale. Karpathy optimization loops, multi-agent pipelines, DAG dependencies, autoscaling workers. Claude, Codex, Gemini.

Agent Replay Debugger MCP — record every agent step + replay deterministically. Step-debugger for agentic loops. Audit-evidence signed exports. By MEOK AI Labs.

Python MCP server (gen-loop-mcp) for self-scheduling follow-up checks in AI agents - no external cron or gateway required

Personal AI strategist & mentor — goals-first planning with an agentic loop. .NET 10 + Model Context Protocol (MCP)

Local-first Python SDK for AI agents: DOM compression, Action Map, SchemaSnap, self-healing selectors, MCP, and shadow-web exec agent loop

Closed-loop, state-verified Windows automation runtime for AI agents — from EDA and CAD to any desktop application.

Autonomous AI SRE & operations platform for Kubernetes and homelabs. Powered by Hermes Agent, a FastMCP tool gateway, and zero-trust Telegram Human-in-the-Loop guardrails.

Agent-driven eval authoring via a new authoring-loop archetype — draft → subagent-review → surgical-revise → submit, with server-enforced self-consistent graders; compiles to standard harnesses.

Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent

AI Agent Hub for Notion — orchestrate AI agents through Notion databases with human-in-the-loop approval. Built with MCP.

A Browser MCP Agent service that fetches various resources（XHS notes,Yelp Posts） with a NL query and a Human-in-the-loop pipeline for safety.

Real-machine, real-browser web perf measurement with ~99% iframe coverage. LLM-native + AI-agent-loop ready.