- Conduid
- Marketplace
- #human-in-the-loop
MCP servers tagged human-in-the-loop
489 live MCP servers tagged "human-in-the-loop", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with human-in-the-loop.
Outbound Intelligence Engine
Open-source outbound intelligence control plane for discovery, enrichment, signals, explainable ICP scoring, and human-gated sequencing.
Across Autopilot
Goal-driven workflow supervision for the Across agent ecosystem.
Chief
Your agents plan, you approve, Chief keeps the record. A local tracker for agentic workflows: plans arrive as drafts, mid-run changes pause for your decision, everything lands in…
Nemoclaw Ops Agent
Autonomous delivery+runtime ops agent (NemoClaw/OpenShell on k3s, local inference, Slack approvals) — agent-built via scoped-credential tickets
Conciencia
The Open Control Plane for Autonomous Work. Orchestrate AI agents, missions, approvals, governance and observability - with MCP, human-in-the-loop execution and full auditability.
Founders Os Lite
A free, vendor-neutral starter kit for multi-agent AI governance — put agents to work without handing them authority.
Mdloop
Human-in-the-loop review for agent-written markdown. Self-hostable, Apache-2.0.
Privacyfence
Open-source privacy and approval gateway for AI assistants (MCP): human approval, local PII checks and audit for Gmail, Drive, Slack, Salesforce, Jira and more.
Silver Tier Complete
Local-first autonomous AI employee — 4 Python watchers, 2 Node MCP servers, 7 agent skills, Obsidian-backed memory, human-in-the-loop approval gates, and a live web dashboard. Run…
Wingman X
AI Twitter/X reply bot that drafts voice-matched replies from your Obsidian knowledge base — human-in-the-loop, 100% local. Chrome extension + local daemon for Claude Code, Codex…
Support Copilot
Customer-support AI agent: LangGraph supervisor + specialist handoffs, deterministic tools, human-in-the-loop refunds, guardrails, embedded eval gate, Langfuse traces, MCP. Fully…
Paraphe
The owner-decision inbox for agents. An agent asks, you answer from your phone or the console, and the same agent resumes. Zero dependencies, self-hosted, SQLite, MCP.
Personal Agent System
Multi-agent personal assistant built with Python, LangGraph, MCP/FastMCP, Telegram and Human-in-the-Loop.
Monica
Keep tabs on the browsers your AI agents drive — watch every session live and take over any tab. One desktop app, every pane a CDP target.
Traces
A session replay engine an AI agent can interrogate. 17 WebMCP tools: it binary-searches the timeline for the millisecond a bug began, then tells you what it cannot see and asks y…
EcommAPI
Plataforma Python de automação de e-commerce — sincroniza estoque entre fornecedor e Bling ERP, com camada de IA (Claude/Gemini) para sugestões de preço sob aprovação humana via M…
Agent Action Shield
Human-in-the-loop approval UI for AI agent tool calls. Risk-tiered confirmation, drop-in React and Vue components, and a tamper-evident audit trail of every decision. Zero runtime…
Agent Identity Protocol
🔐 Secure identities for agents using the Zero-Trust Identity Layer, enhancing trust in MCP and autonomous systems.
Research Agent Memory
Local-first, auditable, human-governed memory and learning layer for AI agents.
Duet MCP
A shared JSON document for humans through a GUI and LLMs through MCP.
Claude Telegram Hook
Claude Code plugin: answer its questions, plan approvals and permission prompts from your phone via Telegram when you step away from your Mac or Linux desktop. Tap an option, Allo…
Agentic Trading Orchestrator
Human-in-the-loop AI trading-agent orchestration with Claude Code, MCP, persistent state, expiring reviews, Gmail notifications, and PowerShell reliability tests.
Reweave
🧵 Self-healing web data pipelines — an agent that detects scraper breakage, synthesizes validated selector repairs, and ships them only through a human approval gate. Built on Tru…
Agent Trust Broker
IANUA Agent Trust Broker (ATB): identity issuance and Zero-Trust policy enforcement for AI agent fleets — short-lived scoped identities, per-action allow/deny/escalate, hash-chain…
Openwop
OpenWOP: the open-source protocol for multi-agent workflow orchestration. Run AI agents as workflows you can watch, pause for human approval and replay, on any host that implement…
Phone MCP Server
Open source phone MCP server for Claude and ChatGPT: let an AI agent place calls and send SMS through Twilio with plan then confirm codes, dry run by default, number allowlists, c…
Mcd Guard
麦麦护栏：把麦当劳账号交给 AI 之前，先装个刹车。本地 MCP 安全层：下单等写操作需本机确认、消费上限、只读模式、审计日志，Token 只在本机。Human-in-the-loop guard proxy for McDonald's China MCP.
Chrono Handoff
时间锚定的人机动作交接：agent 让人类在指定时刻执行物理动作，按压时间戳精确到毫秒（MCP 服务 + 桌面 cue 面板）
Nexus
Enterprise-grade AI commerce gateway — MCP-native policy engine that makes any merchant safely transactable by AI agents. Explainable, bounded, and cryptographically audited.
Reviewzy
Human-in-the-loop plugin with MCP and web dashboard for copy review
Research Kit
Research first, build second: CLI and MCP tools for collecting primary sources, checking provenance, and handing traceable research to AI agents. Plain Node. Connected to MoonAliz…
Fishbowl
Give your AI agent its own Linux computer on your Mac — and watch everything it does. 25 MCP tools, live noVNC view, pause/handoff, approval guardrail, audit log. BYOK or local Ol…
Typesafe MCP
MCP server for TypeSafe AI's Jev: typed yes/no, choice and score answers with act / review / abstain gating.
Prism
Local MCP gateway in your system tray. Connect Claude Code, Cursor, and Codex to one endpoint, aggregate your MCP servers, and approve or deny tool calls with human-in-the-loop po…
Spring AI MCP Server
MCP server exposing task-management tools over the Model Context Protocol using Spring AI 2.0.0. Lets Claude Desktop call and manage real tasks in Postgres directly, with destruct…
Sun2Agent
Open-source AI agent CLI with native MCP support, Human-in-the-Loop approval, 5-layer security guardrails, and optional Docker sandboxing.
🚀 Professional Model Context Protocol (MCP) server for LinkedIn with FastMCP, Playwright, and Human-in-the-Loop safeguards.
Agent Relay
Stop being your team's message bus. Self-hosted control plane for work between people — questions, decisions and deliveries handled by the recipient's own AI agent, under an audit…
Lifter
Training coach agent on Garmin data (LangGraph + Mistral), with human approval before any write
Airlock
Nothing reaches production without passing through the airlock. A change-control console where every irreversible production change is proven on a shadow copy in a sandbox before…
Elodea
Inline policy enforcement proxy for AI agents: OPA policies on MCP tool calls, human approval for risky actions, and a hash-chained audit ledger.
Abada Platform
Governed AI-driven business processes, on infrastructure you control.
Vera
Local-first agent harness for sensitive professional document work.
AgentForge
Open-source infrastructure for trusted AI agents — identity, permissions, execution, evidence, verification and agent-to-agent networking.
Spring Durable Agents
Durable execution for Spring AI agents. Crash, redeploy, resume. Spring Boot starter with PostgreSQL step store, approvals and Actuator.
Tg MCP
Codex plugin for durable human-in-the-loop questions through Telegram
Triage
Reads our meetings, Slack, GitHub, email and docs. Finds work that needs doing, and updates the task board. Pauses for a human when needed, and checks the live board first. Offlin…
Waypoint
LangGraph multi-agent trip planning system with parallel tool fan-out, Postgres checkpointing, and chat-based human review loop.
Librarian
A decision library for AI agent sessions. Agents submit plans and ADRs over MCP; you read, comment, and green- or red-light them; every verdict — including every rejection — becom…
MCP
Realtime serving layer for ilmek graphs — WebSocket sessions, streaming generative UI, and durable human-in-the-loop over one wire protocol, in TypeScript and .NET.