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 providing code feedback, validation, compilation, and linting
npm MIT -
User Dispatch MCP: AI Feedback Widget + Server 2026 - One Command Install
-
saai-skill-feedbackgithub.com/ServiceNow/saai-skill-feedbackupdated this year
MCP skill for submitting feedback about Claude skills - auto-detects context and creates ServiceNow SBOs
MIT ★ 1 -
Customer feedback for your AI assistant: CSAT, NPS and CES scores, response search, AI themes.
MIT -
Quality signals for MCP tools — community-driven quality database
MIT -
feedbacksgithub.com/ytubecoder/feedbacksupdated this year
Point-and-talk feedback capture for AI analysis. Share your screen, click on things, say what you think.
NOASSERTION ★ 1 -
MCP server for Website Feedback Tool: let Claude Code, Cursor or Codex read design reviews captured on live web pages
MIT -
feedback-analyzer-ai-mcpgithub.com/csoai-org/feedback-analyzer-ai-mcpupdated this year
Feedback Analyzer Ai tools for AI agents. Capabilities: analyze feedback, extract themes, sentiment trend. Built by MEOK AI Labs.
npm MIT -
MCP server that lets AI assistants read and analyze Feedback Hub data
MIT -
RAG Q&A + autonomous triage agent for customer feedback. Built on Gemini free tier with ChromaDB, structured JSON validation, and deterministic routing.
-
Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor.
MIT ★ 54 -
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 -
md-feedbackgithub.com/yeominux/md-feedbackupdated this year
MCP server for markdown plan review — companion to the MD Feedback VS Code extension. AI agents read annotations, mark tasks done, evaluate quality gates, and generate session handoffs. 27 tools for Claude Code, Cursor, and other MCP-compatible clients.
npm SUL-1.0 -
md-feedbackgithub.com/yeominux/md-feedbackupdated this year
Browser-first markdown plan review. Start local web review in one command, then let your agent continue through MCP.
NOASSERTION ★ 5 -
A powerful, open-source Model Context Protocol (MCP) server for automated, multi-language code feedback, validation, and project analysis. Designed for developers, teams, and LLM-powered workflows to ensure code quality, correctness, and maintainability across diverse languages and build systems.
MIT ★ 1 -
AI analyst agent (Gemini + MCP tools over SQLite) tested on 22,641 clothing reviews. Compares its judgments with an ML baseline on 200 held-out reviews, audits disagreements, fixes a silent wrong-question bug (2/5 to 5/5), documents governance and limits. Includes a no-setup replay site.
-
Digaso for Claude: conversational research agents (feedback, reviews, A/B, price, MaxDiff, user tests) for 12 sectors, with sample-sized findings.
MIT -
Heresay by Sibhimanyu: in-app feedback and bug reports for web, iOS and macOS apps. Your team accepts each report; accepted ones go to your coding agent (Claude Code, Cursor, Codex) via MCP. Self-hosted on Firebase.
npm -
userdispatch-mcpgithub.com/kiruna-labs/userdispatch-mcpupdated this year
User feedback widget + MCP server for AI coding agents. One command to install.
MIT ★ 2 -
MCP server for Layerdock: read website feedback (selector, screenshot, console and network trace) in Claude Code, Cursor and other coding agents, then fix and resolve it.
MIT -
obseigithub.com/obsei/obseiactive
Open source, privacy-first Voice of Customer analytics. A self-hosted alternative to Enterpret and Unwrap that strips PII from feedback before any LLM sees it.
pypi Apache-2.0 -
loopbackgithub.com/joshidikshant/loopbackupdated this year
Interactive feedback layer between the app you're building and your coding agents (MCP). Pins carry the failing request; Claude Code, Codex, and Gemini CLI work one queue; a verified fix turns the pin green.
MIT -
@opensourceops/canny-mcpgithub.com/opensourceops/canny-mcp-serverupdated this year
MCP server for Canny feedback management with Jira integration
npm MIT -
CLI + MCP server for reading FeedbackKit dashboard feedback from a coding agent.
npm other -
@mseep/mentor-mcp-serverstale
MCP server that provides insightful feedback and guidance on various types of user requests
npm ISC -
userdispatchgithub.com/kiruna-labs/userdispatch-mcpupdated this year
CLI installer for UserDispatch feedback widget + MCP server
npm MIT -
@loopsense/mcpgithub.com/jarvisassistantux/loopsenseupdated this year
MCP server that closes the feedback loop for AI coding agents — CI results, deployments, test outcomes, file changes
npm MIT -
fixui-bridgegithub.com/hulbu/fix-uiupdated this year
Local daemon that stores fix-ui feedback entries in each project's .fix-ui.jsonl inbox.
npm MIT -
Trace reviewer feedback to the evidence that it was addressed in a revised document. Local-first, evidence-based DOCX review auditor with CLI and MCP server.
MIT -
MCP server providing healthcare analytics capabilities for Smartsheet, including clinical note summarization, patient feedback analysis, and research impact assessment
MIT ★ 14 -
Claude Code plugin for Deixis, the Mac app for screenshot feedback: point, say or type what should change, and the round arrives in your session.
MIT -
Open-source, free webpage annotator with real-time collaboration. Share a link, no account needed. AI agents work the feedback over MCP.
Apache-2.0 ★ 53 -
AnnotateKit for React Native and Expo (iOS), and the annotate CLI that delivers visual feedback from your running iOS app to coding agents (MCP server, watcher, headless runner).
npm MIT -
Record your screen, narrate feedback, get structured Markdown with screenshots. Desktop app, CLI, and MCP server for AI coding agents like Claude Code, Cursor, and Windsurf.
npm MIT -
@iflow-mcp/eddiesanjuan-markuprgithub.com/eddiesanjuan/markuprupdated this year
Record your screen, narrate feedback, get structured Markdown with screenshots. Desktop app, CLI, and MCP server for AI coding agents like Claude Code, Cursor, and Windsurf.
npm MIT -
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 -
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 simulating harsh user review and feedback
npm MIT -
rlaifgithub.com/a9lim/rlaifactive
Single-user MCP server with negative and positive feedback channels
AGPL-3.0 -
rlaif-mcpgithub.com/a9lim/rlaifupdated this year
Single-user MCP server with negative and positive feedback channels
pypi AGPL-3.0-or-later -
This MCP server lets AI agents ask for assistance or feedback from more capable models
MIT ★ 3 -
MCP server for AI-powered UI feedback across React Native, Flutter, and native Android development.
MIT ★ 26 -
MCP Service for Agents to use Apple Store Connect and gather TestFlight user feedback and screenshots.
BSD-3-Clause ★ 2 -
Local-first surveys, feedback, and NPS analytics studio in pure Rust with SQLite storage.
-
Bayesian memory that learns from feedback for LLM agents
MIT ★ 9 -
MCP server that connects Claude to Canvas LMS: courses, assignments, rubrics, feedback, and submissions through conversation
MIT ★ 1 -
Connect Picflow to ChatGPT, Claude, Codex and Claude Code through Cotlet.dev. Client galleries, proofing and feedback workflows.
NOASSERTION -
Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.
npm MIT -
context-sherpagithub.com/hackafterdark/context-sherpaupdated this year
Context Sherpa MCP server provides code mapping, deterministic feedback loops, and tiered inference for AI coding agents to increase accuracy and optimize token usage.
MIT ★ 26 -
leetcode-helpergithub.com/Navoren/leetcode-helperupdated this year
MCP server for Claude Desktop & Claude Code that provides LeetCode/DSA guidance, hints, complexity analysis, and optimization feedback without spoilers.
★ 1 -
ClarityOSgithub.com/RishiBuilds/ClarityOSupdated this year
an agentic tool that simplifies complex institutional texts to meet readability targets using a multi-agent feedback loop.
MIT ★ 1 -
Agent-optimized code feedback MCP server for JavaScript and TypeScript projects.
npm MIT -
@retentioncheck/mcp-servergithub.com/brianfofficial/retentioncheck-v2updated this year
MCP server for AI-powered churn analysis. Analyze cancellation feedback to identify churn patterns and get actionable recommendations.
npm MIT -
Route Telegram project messages, context, files, and client-ready feedback through Claude Code or Codex.
AGPL-3.0 -
tracepulsegithub.com/sourjya/tracepulseupdated this year
Runtime feedback MCP server for AI coding agents. ViewGraph sees the UI - TracePulse feels the backend.
npm AGPL-3.0 -
Playwright browser automation for AI agents — screenshots, GIF/MP4/WebP recording, JSON feedback sidecar, MCP server.
pypi MIT -
Calls, specs and feedback become deduped Linear issues, PRDs and weekly project updates.
Apache-2.0 ★ 1 -
Share and hone skills across your organization: an MCP server where agents get skills and submit feedback, and each skill is revised from it.
MIT ★ 1 -
Churnsolution-MCPgithub.com/Churnsolution/Churnsolution-MCPupdated this year
Official MCP server for Churn Solution — read-only access to subscription retention analytics: cancellation flows, failed payment recovery, and customer feedback.
MIT -
MCP server that lets an AI agent scan resumes on Big Interview ResumeAI, read structured feedback, and tailor → rescan to Gold.
MIT ★ 2