MCP server/ai-tools

Feedback Pipeline MCP Server

Bridges Notion custom agents with Claude Code for automated bug reproduction

ericNotion/feedback-pipeline-mcp ↗by ericNotionupdated
Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1

Prepare the server locally

Run this once before adding it to Claude Code.

npm install
node server.js
2

Register it in Claude Code

claude mcp add -e "NOTION_API_TOKEN=${NOTION_API_TOKEN}" feedback-pipeline -- node /path/to/server.js

Replace any placeholder paths in the command with the real path on your machine.

Required:NOTION_API_TOKEN
3

Make your agent remember this setup

feedback-pipeline's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session. 

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

  • Automated bug reproduction using Playwright browser automation
  • Integration with Claude Code to implement and test software fixes
  • Callback system to notify Notion agents via thread messages and page comments
  • Live progress tracking with screenshots for ongoing tasks

Tools 4

reproduce_bugReproduce a bug using Playwright browser automation.
build_fixBuild a fix or feature using Claude Code.
get_task_statusCheck the status of a running or completed task.
pingTest connectivity - returns pong.

Environment Variables

NOTION_API_TOKENrequiredAPI token for Notion integration and callbacks

Try it

→Reproduce the bug where the login button fails to trigger on the dashboard page.
→Build a fix for the reported navigation issue and verify it using Playwright.
→Check the status of the bug reproduction task with ID 12345.
→Implement a new feature to export reports as PDF and verify the output.
Original README from ericNotion/feedback-pipeline-mcp

Feedback Pipeline MCP Server

An MCP (Model Context Protocol) server that bridges Notion custom agents with Claude Code for automated bug reproduction and fix building.

Overview

This server allows a Notion custom agent to:

  1. Reproduce bugs - Uses Playwright browser automation to reproduce reported bugs and capture screenshots
  2. Build fixes - Uses Claude Code to implement fixes, run tests, and verify with Playwright

Setup

  1. Install dependencies:

    npm install

  2. Create a .env file with your Notion API token:

    NOTION_API_TOKEN=your_token_here

  3. Start the server:

    node server.js

  4. Expose via ngrok (for Notion to connect):

    ngrok http 3001

Architecture

Notion Custom Agent
        │
        ▼ (via ngrok)
   MCP Server (port 3001)
        │
        ▼
   Claude Code CLI
        │
        ▼
   Playwright MCP
        │
        ▼
   Notion Dev Server (port 3030)

MCP Tools

`reproduce_bug`

Reproduce a bug using Playwright browser automation.

Parameters:

  • bug_description (required): Description of the bug
  • reproduction_steps (optional): Steps to reproduce
  • callback_agent_id (required): Agent ID for callback
  • callback_thread_id (required): Thread ID for callback
  • callback_page_id (required): Page ID for comment notification

`build_fix`

Build a fix or feature using Claude Code.

Parameters:

  • description (required): What to build or fix
  • plan (optional): Implementation plan
  • verify_with_playwright (optional): Whether to verify with Playwright (default: true)
  • callback_agent_id (required): Agent ID for callback
  • callback_thread_id (required): Thread ID for callback
  • callback_page_id (required): Page ID for comment notification

`get_task_status`

Check the status of a running or completed task.

Parameters:

  • task_id (required): The task ID to check

`ping`

Test connectivity - returns "pong".

Endpoints

  • GET / - SSE endpoint for MCP connection
  • POST / - MCP message handler
  • GET /health - Health check
  • GET /tasks - List all tasks
  • GET /tasks/:taskId - Get task details
  • GET /demos - List demo recordings
  • GET /demos/:taskId/ - Live progress page with screenshots

Callbacks

When a task completes, the server:

  1. Posts results to the agent thread via Notion Agents SDK API
  2. Adds a comment to the task page with demo URL and summary

Configuration

The server expects:

  • Notion dev server running on port 3030
  • Playwright MCP configured in the Claude Code environment
  • NOTION_API_TOKEN environment variable for callbacks

Frequently Asked Questions

What are the key features of Feedback Pipeline?

Automated bug reproduction using Playwright browser automation. Integration with Claude Code to implement and test software fixes. Callback system to notify Notion agents via thread messages and page comments. Live progress tracking with screenshots for ongoing tasks.

What can I use Feedback Pipeline for?

Automating the reproduction of reported bugs from Notion tickets. Streamlining the development-to-verification loop for software fixes. Providing visual proof of bug fixes to stakeholders via Notion comments. Managing automated testing workflows directly from Notion custom agents.

How do I install Feedback Pipeline?

Install Feedback Pipeline by running: npm install && node server.js

What MCP clients work with Feedback Pipeline?

Feedback Pipeline works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep Feedback Pipeline docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest

Related MCP Servers

Skill Seekers
The data layer for AI systems.
ai-tools11.1K stars
Context Mode
The other half of the context problem.
ai-tools5.6K stars
Semiotic
A React data visualization library designed for AI-assisted development.
ai-tools2.6K stars
RocketRide
Self-hosted, open-source AI pipeline platform for MCP tools
ai-tools1.6K stars
Context+
Semantic Intelligence for Large-Scale Engineering.
ai-tools1.5K stars
ShipSwift
AI-native SwiftUI component library — production-ready code for LLMs
ai-tools1.3K stars