What are the requirements to run this server?
You need an OpenReplay account with API access, a valid API key and project ID, network access to OpenReplay API endpoints, and Python 3.8+.
@rsp2k
基本信息
A Model Context Protocol (MCP) server for analyzing OpenReplay session recordings and user behavior patterns
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"openreplay-mcp-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
An MCP server that enables AI assistants to analyze OpenReplay session recordings and user behavior patterns. It searches, filters, and provides actionable insights from OpenReplay data, helping developers and UX researchers detect problems and understand user journeys.
Install by cloning the repository, creating a Python virtual environment, and installing dependencies. Configure OpenReplay API credentials in a .env file (API key, project ID, API URL). Run the server with python run_server.py or via Docker. Connect to an MCP client like Claude Desktop by adding the server to claude_desktop_config.json.
You need an OpenReplay account with API access, a valid API key and project ID, network access to OpenReplay API endpoints, and Python 3.8+.
Add the server to your `claude_desktop_config.json` under `mcpServers` with the `python` command pointing to `run_server.py` and environment variables for `OPENREPLAY_API_KEY` and `OPENREPLAY_PROJECT_ID`.
Tools include `search_sessions`, `get_session_details`, `get_user_session_history`, `analyze_user_journey`, `detect_problem_patterns`, `generate_session_summary`, and `find_similar_sessions`.
Yes. Use `docker-compose up` with environment variables in `.env`, or run `docker build` and `docker run` with the appropriate environment variables.
It detects rage clicks, form abandonment, dead clicks, and errors; maps page flows and action breakdowns; and provides AI-generated summaries and behavioral patterns.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Hindsight: Agent Memory That Learns

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
评论