OpenReplay Session Analysis MCP Server
About
A Model Context Protocol (MCP) server for analyzing OpenReplay session recordings and user behavior patterns
Details
- License
- MIT license
Explore
- 🔍 Session Search & Filtering - Find sessions by date, user, errors, duration
- 📊 User Journey Analysis - Track page flows and navigation patterns
- 🐛 Problem Detection - Identify rage clicks, form abandonment, errors
- 🤖 AI-Powered Insights - Generate intelligent session summaries
- 👥 User Behavior Analysis - Analyze patterns across multiple sessions
- 🔗 Similar Session Finding - Discover sessions with comparable issues
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
OpenReplay Session Analysis MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
1. Clone and setup:
git clone https://github.com/rsp2k/openreplay-mcp-server.git
cd openreplay-mcp-server
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
2. Configure OpenReplay credentials:
cp .env.example .env
Set these environment variables in your .env file:
OPENREPLAY_API_URL=https://api.openreplay.com
OPENREPLAY_API_KEY=your_api_key_here
OPENREPLAY_PROJECT_ID=your_project_id_here
To get your OpenReplay API credentials:
1. Go to your OpenReplay dashboard
2. Navigate to Settings → API Keys
3. Generate a new API key
4. Copy your Project ID from the URL or project settings
Add to your Claude Desktop MCP configuration (claude_desktop_config.json):
{
"mcpServers": {
"openreplay-analysis": {
"command": "python",
"args": ["/path/to/openreplay-mcp-server/run_server.py"],
"env": {
"OPENREPLAY_API_KEY": "your_api_key_here",
"OPENREPLAY_PROJECT_ID": "your_project_id_here"
}
}
}
}
For containerized deployment:
docker-compose up
Or build and run manually:
docker build -t openreplay-mcp .
docker run -e OPENREPLAY_API_KEY=your_key -e OPENREPLAY_PROJECT_ID=your_project openreplay-mcp
```
analyze_user_journey
Map user navigation patterns and page flows
detect_problem_patterns
Find rage clicks, form issues, and errors
generate_session_summary
AI-powered session insights and recommendations
find_similar_sessions
Discover related problematic sessions
- analyze_user_journey - Map user navigation patterns and page flows
- detect_problem_patterns - Find rage clicks, form issues, and errors
- generate_session_summary - AI-powered session insights and recommendations
- find_similar_sessions - Discover related problematic sessions
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"openreplay session analysis mcp server": {
"openreplay-mcp-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}
}McpServers
{
"openreplay-mcp-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}A Model Context Protocol (MCP) server for analyzing OpenReplay session recordings and user behavior patterns. This server enables AI assistants to analyze user sessions, detect problems, and provide actionable insights from OpenReplay data.
🔥 Features
- 🔍 Session Search & Filtering - Find sessions by date, user, errors, duration
- 📊 User Journey Analysis - Track page flows and navigation patterns
- 🐛 Problem Detection - Identify rage clicks, form abandonment, errors
- 🤖 AI-Powered Insights - Generate intelligent session summaries
- 👥 User Behavior Analysis - Analyze patterns across multiple sessions
- 🔗 Similar Session Finding - Discover sessions with comparable issues
🚀 Quick Start
1. Clone and setup:
git clone https://github.com/rsp2k/openreplay-mcp-server.git
cd openreplay-mcp-server
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
2. Configure OpenReplay credentials:
cp .env.example .env
# Edit .env with your OpenReplay API credentials
3. Run the server:
python run_server.py
⚙️ Configuration
Set these environment variables in your .env file:
OPENREPLAY_API_URL=https://api.openreplay.com
OPENREPLAY_API_KEY=your_api_key_here
OPENREPLAY_PROJECT_ID=your_project_id_here
To get your OpenReplay API credentials:
1. Go to your OpenReplay dashboard
2. Navigate to Settings → API Keys
3. Generate a new API key
4. Copy your Project ID from the URL or project settings
🛠️ Available Tools
Session Management
-search_sessions - Search sessions with advanced filters
- get_session_details - Get detailed session information
- get_user_session_history - View all sessions for a specific user
Analysis Tools
-analyze_user_journey - Map user navigation patterns and page flows
- detect_problem_patterns - Find rage clicks, form issues, and errors
- generate_session_summary - AI-powered session insights and recommendations
- find_similar_sessions - Discover related problematic sessions
📋 Usage with Claude Desktop
Add to your Claude Desktop MCP configuration (claude_desktop_config.json):
{
"mcpServers": {
"openreplay-analysis": {
"command": "python",
"args": ["/path/to/openreplay-mcp-server/run_server.py"],
"env": {
"OPENREPLAY_API_KEY": "your_api_key_here",
"OPENREPLAY_PROJECT_ID": "your_project_id_here"
}
}
}
}
💬 Example Queries
Once connected to Claude Desktop or another MCP client, you can ask:
- "Find sessions with errors from the last week"
- "Analyze user journey for session ABC123"
- "Generate a summary of problematic sessions today"
- "Show me all sessions for user [email protected]"
- "Find sessions similar to XYZ456 that had form abandonment"
- "Debug session DEF789 and tell me what went wrong"
🐳 Docker Usage
For containerized deployment:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
