JoySafeter
đ JoySafeter: An enterprise AI Agent PlatformâNot just chatting. buildingărunningătesting, and tracing autonomous Agent Teams with visual orchestration...
What is JoySafeter?
JoySafeter is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to đ joysafeter: an enterprise ai agent platformânot just chatting. buildingărunningătesting, and tracing autonomous agent teams with visual orchestration...
đ JoySafeter: An enterprise AI Agent PlatformâNot just chatting. buildingărunningătesting, and tracing autonomous Agent Teams with visual orchestration...
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- đ JoySafeter: An enterprise AI Agent PlatformâNot just chatt
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx joysafeterConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use JoySafeter
JoySafeter is an enterprise AI Agent platform that lets you build, run, test, and trace autonomous agent teams with visual orchestration. It integrates over 200 tools via the MCP protocolâincluding pre-bundled security tools like Nmap, Nuclei, and Trivyâand supports multi-agent collaboration with persistent memory across sessions. Developers and security engineers use it to automate penetration testing, APK vulnerability analysis, document review, and complex multi-step workflows without writing glue code.
Prerequisites
- Docker and Docker Compose installed on your system
- Git to clone the repository
- A supported LLM provider API key (e.g. OpenAI, Anthropic, or a compatible local endpoint)
- At least 8 GB RAM recommended for running the full stack (frontend, backend, PostgreSQL, Redis)
- An MCP-compatible client to interact with the exposed MCP services
Clone the repository
Clone the JoySafeter repository to your local machine.
git clone https://github.com/jd-opensource/JoySafeter.git
cd JoySafeterRun the quick-start script
Execute the provided quick-start script which sets up all services including the frontend, backend API, PostgreSQL, and Redis automatically.
./deploy/quick-start.shConfigure your LLM provider
After the stack starts, open the web UI at http://localhost:3000 and navigate to Settings to enter your LLM provider credentials (API key, model endpoint, and model name).
Access the platform and explore pre-built agents
Browse to http://localhost:3000 to access the visual orchestration interface. JoySafeter ships with 30+ pre-built skills and security agent templates you can use immediately or customize.
Connect via MCP
The MCP service runs alongside the backend. Point your MCP client at the JoySafeter MCP endpoint to expose agent capabilities as MCP tools. Check the API docs at http://localhost:8000/docs for available endpoints.
{
"mcpServers": {
"joysafeter": {
"command": "npx",
"args": ["joysafeter"],
"env": {
"JOYSAFETER_API_URL": "http://localhost:8000"
}
}
}
}Start the middleware only (lightweight option)
If you only need PostgreSQL, Redis, and the MCP service without the full frontend, use the middleware-only script.
./deploy/scripts/start-middleware.shJoySafeter Examples
Client configuration
MCP client configuration pointing to a locally running JoySafeter instance.
{
"mcpServers": {
"joysafeter": {
"command": "npx",
"args": ["joysafeter"],
"env": {
"JOYSAFETER_API_URL": "http://localhost:8000"
}
}
}
}Prompts to try
Example prompts once JoySafeter agents are connected.
- "Upload this APK file and run a full OWASP Mobile Top 10 vulnerability analysis"
- "Create a penetration testing agent for https://example.com and report discovered endpoints"
- "Run Nmap on 192.168.1.0/24 and summarize open services"
- "Analyze this Docker image with Trivy and list all critical CVEs"
- "Start a multi-agent workflow: one manager agent coordinating three worker agents for recon, exploitation, and reporting"Troubleshooting JoySafeter
Services fail to start or database connection errors on first run
Run `docker compose logs` to identify the failing service. PostgreSQL may need 30-60 seconds to initialize before the backend connects. Run `./deploy/quick-start.sh` again after PostgreSQL is fully healthy.
Frontend at localhost:3000 shows blank page or CSP errors
Check that NEXT_PUBLIC_CSP_CONNECT_SRC_EXTRA is set correctly in the frontend environment config to include your backend host. For remote deployments, configure the nginx.conf with the correct backend IP and port.
LLM API calls fail inside agents
Verify your LLM credentials in Settings â Model Configuration. Ensure the model endpoint URL is reachable from inside the Docker network (use the host machine's IP rather than localhost when running Docker).
Frequently Asked Questions about JoySafeter
What is JoySafeter?
JoySafeter is a Model Context Protocol (MCP) server that đ joysafeter: an enterprise ai agent platformânot just chatting. buildingărunningătesting, and tracing autonomous agent teams with visual orchestration... It connects AI assistants to external tools and data sources through a standardized interface.
How do I install JoySafeter?
Follow the installation instructions on the JoySafeter GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with JoySafeter?
JoySafeter works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is JoySafeter free to use?
Yes, JoySafeter is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
JoySafeter Alternatives â Similar Coding Agents Servers
Looking for alternatives to JoySafeter? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
â 142.2kProduction-ready platform for agentic workflow development.
Ruflo
â 54.0kđ The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
â 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
â 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
â 25.5kBuild and run agents you can see, understand and trust.
Serena
â 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up JoySafeter 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 JoySafeter?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.