OpenDeRisk
AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
What is OpenDeRisk?
OpenDeRisk is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-native risk intelligence systems, openderisk——your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI-Native Risk Intelligence Systems, OpenDeRisk——Your applic
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx openderiskConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use OpenDeRisk
OpenDeRisk is an AI-native risk intelligence system that provides 24/7 automated monitoring, root cause analysis, and intelligent protection for application systems through a multi-agent orchestration framework. It integrates AI-SRE capabilities including OpenRCA root cause analysis, flame graph performance profiling for Java and Python applications, and conversational data analysis over metrics, logs, traces, and tabular data. DevOps and SRE teams deploy OpenDeRisk to reduce mean time to resolution by having AI agents proactively identify, analyze, and explain application risks with a transparent visualized evidence chain.
Prerequisites
- Python 3.10+ and the uv package manager installed
- curl for the one-line installer or git for source installation
- An AI model API key (configured in ~/.openderisk/configs/derisk-proxy-aliyun.toml after install)
- An MCP client such as Claude Desktop for conversational interaction
- Application data sources: metrics, logs, traces, or flame graph files to analyze
Install OpenDeRisk via one-line installer
Run the official install script to set up OpenDeRisk and its dependencies automatically.
curl -fsSL https://raw.githubusercontent.com/derisk-ai/OpenDerisk/main/install.sh | bashOr install from source with uv
Clone the repository and install all packages using uv for a full development setup.
git clone https://github.com/derisk-ai/OpenDerisk.git
cd OpenDerisk
uv sync --all-packages --frozen \
--extra "base" --extra "proxy_openai" --extra "rag" \
--extra "storage_chromadb" --extra "derisks" \
--extra "storage_oss2" --extra "client" \
--extra "ext_base" --extra "channel_dingtalk"Configure your AI model API keys
Edit the default config file to add your LLM provider API keys. This file is created automatically after installation.
# Edit the config file
nano ~/.openderisk/configs/derisk-proxy-aliyun.tomlStart OpenDeRisk with quickstart
Launch the OpenDeRisk service using the quickstart command. Specify a custom port if needed.
uv run derisk quickstart
# Or with a custom port:
uv run derisk quickstart -p 8888Connect your MCP client
Add OpenDeRisk to your Claude Desktop or other MCP client configuration, then restart the client.
Upload data and start analysis
Upload flame graphs, log files, metrics exports, or Excel data files via the web interface, then begin conversational analysis with your MCP client.
OpenDeRisk Examples
Client configuration for OpenDeRisk
Configure Claude Desktop to connect to a running OpenDeRisk MCP server instance.
{
"mcpServers": {
"openderisk": {
"command": "npx",
"args": ["openderisk"],
"env": {
"OPENDERISK_SERVER_URL": "http://localhost:8888",
"OPENDERISK_API_KEY": "your-api-key-if-configured"
}
}
}
}Prompts to try
Example prompts for AI-native risk analysis and SRE workflows.
- "Analyze this Java flame graph and identify the top performance bottlenecks"
- "My service latency spiked at 2am—run root cause analysis on the attached metrics and logs"
- "What are the most common error patterns in the last 24 hours of application logs?"
- "Analyze this Excel export of API response times and show me anomalies with an evidence chain"
- "Compare the Python flame graph from before and after the deployment and explain the difference"Troubleshooting OpenDeRisk
uv run derisk quickstart fails with import errors
Ensure all required extras were installed during 'uv sync'. Re-run the sync command with all --extra flags as shown in the source installation step. Missing extras like 'storage_chromadb' or 'rag' cause import failures at startup.
AI model API calls fail after installation
Edit ~/.openderisk/configs/derisk-proxy-aliyun.toml and add your LLM provider API keys. The configuration file is created during installation but keys must be populated manually before the service can make LLM calls.
Flame graph analysis returns no results or generic output
Ensure the flame graph is in a supported format (Java async-profiler or Python py-spy output). Upload the raw .html or .svg flame graph file rather than a screenshot for accurate parsing by the analysis engine.
Frequently Asked Questions about OpenDeRisk
What is OpenDeRisk?
OpenDeRisk is a Model Context Protocol (MCP) server that ai-native risk intelligence systems, openderisk——your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install OpenDeRisk?
Follow the installation instructions on the OpenDeRisk GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with OpenDeRisk?
OpenDeRisk works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is OpenDeRisk free to use?
Yes, OpenDeRisk is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
OpenDeRisk Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to OpenDeRisk? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up OpenDeRisk in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use OpenDeRisk?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.