MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for human-in-the-loop surveys, A/B preference tests, ratings, and rankings. Get real human feedback inside Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP client — powered by Datapoint AI.
MIT ★ 7 -
MCP server for Claude to request human feedback through Slack
MIT -
tasksync-mcpgithub.com/vikrant82/tasksync-mcpupdated this year
Human-in-the-loop feedback for AI coding agents. Pause your agent, give feedback (text + images), get Telegram notifications, reply from your phone. Works with OpenCode (plugin), VS Code Copilot, Claude Desktop (MCP).
npm MIT ★ 1 -
Ask real people from your AI agent: human feedback, user testing, surveys and usability as one MCP tool call. Open standard (draft) + reference server. No key needed to try.
-
Mark feedback for your agent — human-in-the-loop design review over Laravel MCP
NOASSERTION ★ 3 -
Small SaaS building blocks a coding agent can set up, verify and hand to a human: waitlists, feedback widgets, changelogs, deploy checks, onboarding checklists, CSV import and more. CLI and local MCP server.
npm MIT -
Multi-agent CTI platform — LangGraph + MCP + RAG + STIX KG + human-in-the-loop feedback
★ 1 -
Multi-agent payment failure triage built with Spring AI — diagnoses failures via an agentic feedback loop, explains card-network rules with RAG (pgvector), and opens GitHub incidents through bidirectional MCP, with human-in-the-loop execution.
-
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. It's also cheaper than using coderabbit ;)
★ 2 -
Sentinel-AIOpsgithub.com/Anbu-00001/Sentinel-AIOpsupdated this year
A production-grade AIOps framework focused on model integrity and autonomous reliability. Features a LightGBM-driven multiclass inference engine via FastMCP, validated against data leakage through NMI analysis. Includes real-time Population Stability Index (PSI) drift monitoring and a closed-loop human-in-the-loop feedback system for sustainable ML
MIT ★ 2 -
Cursor Feedback Image MCP
MIT ★ 8 -
feedback-loop-mcpgithub.com/tuandinh-org/feedback-loop-mcpupdated this year
Interactive human-in-the-loop desktop GUI & Model Context Protocol (MCP) server for AI agents
MIT ★ 5 -
Save your Cursor monthly quota! Unlimited AI interactions in one conversation via MCP feedback loop.
npm MIT ★ 31 -
Human capability for AI agents - delegate bounded physical-world action and human judgment through MCP and REST.
-
flask-feedbackactive
One-shot setup for Flask (flask.do), the video review MCP server for AI agents. Connects the Flask MCP server to Claude Code, Cursor and Codex.
npm MIT -
Pluralistic human evaluation infrastructure for AI in production
pypi MIT ★ 2 -
Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor.
MIT ★ 54 -
PM-agentsgithub.com/thuonglbl/PM-agentsupdated this year
PM Agents website gives PMs with AI agents such as status, risk, communication, etc. Get input from Jira, Confluence, Bitbucket, Teams, and Calendar via MCP server, orchestrate with LangGraph.
-
claude-redlinegithub.com/switchbm/claude-redlineupdated this year
An interactive Human-in-the-Loop (HITL) review tool for Claude. Opens a local UI to 'redline' specifications and plans before code is written.
MIT ★ 2 -
my-last-feedback-pythongithub.com/isWittHere/my-last-feedback-pythonupdated this year
A Model Context Protocol (MCP) server that enables a human-in-the-loop workflow for AI-assisted development tools such as Cursor, Cline, and Windsurf. Based on the original work by Fábio Ferreira (@fabiomlferreira).
MIT ★ 2 -
Flag-mcpgithub.com/the-nine-nation/Flag-mcpupdated this year
When your AI assistant hits a crossroads, instead of guessing and potentially wasting your time, it pauses — presenting you with meaningful choices, like dialogue options in a game.
MIT ★ 2 -
Cobro = co-browse. The human and the agent watch the same screen together.
npm Apache-2.0 ★ 10 -
Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.
npm MIT ★ 49 -
Show a prototype. Let a human click it. Get the result back into your agent. A small MCP server for HTML prototypes on Linux, Windows and macOS.
Apache-2.0 ★ 2 -
Point at the frame. Send it back to the AI that made the video. Self-hosted video review for humans, Codex and Claude Code.
MIT -
Local-first Android reporter that turns bug reports into portable, reviewed evidence parcels for humans and coding agents. Offline validator, viewer and read-only MCP. AGPL-3.0-only; source candidate, not yet released.
Apache-2.0 -
Collaborative realtime multiplayer AI workspace for your team and your agents. Never loose context. Don't let decisions get lost in chats. Don't wait for someone else to be online if you have a question for them. Focus on shipping features for your customer, bugs/feedbacks get fixed & shipped automagically.