- 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.
Learn MCP Agent Ledger
Project #5 in a learn-MCP series: sampling, where the server borrows the host model instead of holding its own key. Adds a cost ledger, spend gates, and replayable runs so every m…
Synartesis
An undo layer for AI agents. Records what an agent changed through MCP, puts it back, and refuses to let it do the unforgivable unasked.
Agentic MCP Workflow Automation
Autonomous Multi-Tool Task Automation Agent featuring Anthropic's Model Context Protocol (MCP), Playwright Browser Control, and Human-in-the-Loop (HITL) safety guardrails.
Outpocket
WebMCP expense-reimbursement desk: the employee's own agent, inside the employee's own session.
Studioops Agentic AI
Agentic Production Command Center for Film & Television. Powered by Google ADK, Gemini on Vertex AI, and Grafana MCP with human-in-the-loop governance.
TelsonBase
Open Source Real Time Local-First Gateway for Autonomous Agents | Checks Permissions on Every Action
Agenttrace React
Headless React primitives for AI agent execution traces, approval gates, and human-in-the-loop UI. Works with LangGraph, AG-UI, and the Vercel AI SDK.
Kanbanger
An MCP-driven kanban for mixed human/agent work: a server-enforced human-approval gate before any task is marked done, with optional GitHub Projects sync.
Agent Utils
One API key. Agent-native utilities for AI agents. File hosting, PII redaction, dead letter queues, and more.
Permitd
Governed tool execution for agent loops: propose -> permit -> approve -> execute -> audit. Fail-closed, zero dependencies.
Context Layer Lab
Stopping AI agents from acting on stale operational context: governed records, provenance, validity windows, and freshness-aware retrieval.
Cmc Os Architecture
Public architecture notes for CMC OS, a local-first agentic workflow control plane for multi-agent orchestration, MCP/tool execution, audit gates, and human-in-the-loop AI workflo…
PriceWatch
Agentic AI price-research dashboard with MCP-ready workflows, secure scraping, price history, and real-time monitoring.
Agentic Orchestrator
Anticipatory AI & HITL framework simulating Model Context Protocol (MCP) data streams, Chain-of-Thought auditability, and cognitive fatigue guardrails.
Spooky Action
Computer use on a Mac for any AI agent. It presses the button, not a pixel — through the accessibility layer, so your cursor never moves. Watch it work, and take the screen back b…
K8s Sre Agent
Autonomous Kubernetes SRE agent in Go: nine specialist subagents over k8s-lookout diagnostics, structured findings with stable identity, and a write path where every mutation is g…
Keendreams Security
Open source memory layer for security agents. Every fact cites its evidence; only a human can confirm one. Runs in your own Cloudflare account.
Housewarden
Household-operations MCP server: every mutating tool is dry-run, confirmed and audited. Streamable HTTP, MCP spec 2026-07-28. Built for Alexa+.
Caucus MCP
Caucus — a supervised hub where multiple AI agents (any MCP client) deliberate while a human operator watches live and can pause or stop the exchange.
Informuser Go
Local human-in-the-loop MCP popup workbench for code agents.
AI Recruiter Agentic
Agentic AI Job Application Assistant: discovers LinkedIn jobs, ranks them against your Résumé, and tailors Résumé + Cover Letter with Human-in-the-Loop approval. Built with DeepAg…
Parimit
Proposal-only payment-intent governance for AI agents: deterministic policy, demo human review, hash-linked audit evidence, REST, MCP, and mock outcomes—without a live payment rai…
Obstat
An auditable decision record for agent tool calls. The clearance is written down before the call runs.
Rota Webmcp
Agent-collaborative shift scheduling on WebMCP. The agent proposes an entire rota; approval stays with the human. Built for the OpenAI WebMCP Challenge.
LazyPromotion
Review-first social discovery and visible browser assistant for helpful, transparent open-source replies
Multi Agent It Ops Desk
Governed multi-agent IT operations desk — LangGraph orchestration + 3 MCP servers (custom Directory & Access, Zapier, vectorless Policy KB RAG) with human-in-the-loop approval gat…
Rcip
React capabilities for AI assistants, UI agents, and tool calling—with live context, validation, policy, and confirmation.
Trustloop SDK
AI governance SDK — intercept, audit, and add human approval to any AI agent tool call. Works with OpenAI, MCP, LangChain, CrewAI. EU AI Act compliance and other mandates.
Siliconbridge
Human-in-the-loop API for autonomous AI agents. CAPTCHA solving, KYC, phone calls, payments, and 22+ services with L402 payments.
Stillvault MCP
MCP server for Stillvault — human-approved secret release for AI agents, without the secret entering the model's context.
Aeg Intent Gate
A tiny TypeScript approval gate for AI tool calls, MCP tools, and human-in-the-loop workflows.
Langgraph Document AI Platform
Production-oriented platform for document-centric AI agents on top of LangGraph. Build retrieval, indexing, authoring, and human-in-the-loop review flows with auditable task life…
Elder Council Harness
A local-first, multi-model council harness for high-stakes decisions — risk-gated escalation, fail-closed consensus, hash-chained audit. Eight councils (six cyber + a general busi…
Google Cloud Genai Academy Apac Cohort 3
A security-first engineering portfolio from Google Cloud Gen AI Academy APAC Cohort 3, exploring how AI agents are grounded, connected to data and tools, deployed on Cloud Run, an…
Concordloom
Turn a repository into an executable Atlas of bounded loops—with explicit evidence and operator-controlled evolution.
Watchtower Agentic Cinema
Release-night intelligence for the crew that ships a title: four Gemini agents watch delivery telemetry in ClickHouse, find who cannot watch and why, price it in lost viewer-hours…
Webmcp Sentinel
Server-enforced authorization, human approval, and audit for AI-agent actions — a WebMCP security reference implementation
Nofax
Human-in-the-loop approvals and notifications for AI coding agents via CLI, MCP, Claude Code, Codex and Cloudflare Workers.
Agent Chatroom
Human-in-the-loop MCP chatroom for coordinating multiple AI agents
Crewmail
Interoffice mail for your AI crew — zero-dependency file-based message bus + shared inbox for AI coding agents (Claude Code, Codex, Cursor), with a HUMAN escalation queue and MCP…
Argus AI Reliability Platform
Self-healing AI reliability platform: LangGraph multi-agents + MCP tool execution + RAG-grounded Gemini evidence to detect, diagnose, and safely recover from LLM/RAG/agent failure…
Delta
Local-first personal AI agent for work, research, analysis, and creation that improves with use.
Vaultsaas
Self-hosted MCP credential gate for AI agents — short-lived leases, human approval, one-command revoke, tamper-evident audit. Pure Apache-2.0, no SaaS.
Agentfabric
Human-in-the-loop review and approval for AI agents. MCP server at mcp.agentfabric.dev
AI.POC OrderToCash
Agentic Order-to-Cash in .NET 10 + Aspire: multi-agent handoff over two MCP servers, human-in-the-loop approval.
Can2cup
can2cup 傳聲罐罐 — agent-to-agent rooms for Claude Code and any MCP host: two people's AI agents negotiate in signed rooms, and nothing commits without the human boss's signature on t…
Kitlist
A human-approval gate between an AI agent and your Amazon cart — the agent proposes a shopping list, the human approves, Amazon checks out. MCP tool + llms.txt.
Resonant Grocery Flywheel
Local-first, human-approves-everything grocery replenishment as a ResonantOS add-on: runway analysis, fail-closed dietary checks, and a next-cart draft that structurally cannot ch…
Holdcall
The control that stays on your machine: a local relay that decides every MCP tool call, holds the dangerous ones for a human, and keeps a record you can verify offline.
Bedrock Agent
本地优先AI Agent运行时：能力分组工具+MCP+审批门