Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
mcpcan
MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container deployment method. The platform supports container monitoring and MCP service token verification, solving security risks and enabling rapid deployment of MCP services. It uses SSE, STDIO, and STREAMABLEHTTP acces
722stars
24forks
Go
aiapitomcpcontainerdify-synchronousdockerhelmkubernetesmcpmcp-servermodelcontextprotocolopenaiopenapi
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Centralized platform for deploying, monitoring, and managing MCP services in containers with security and protocol conversion.
Use this when
- Managing multiple MCP services across teams
- Need containerized MCP deployments
- Want real-time monitoring of MCP services
- Need protocol conversion between MCP architectures
- Running MCP services in Kubernetes
Don't use when
- Single MCP service with no scaling needs
- No container orchestration environment
- Need lightweight local MCP tools
Capabilities
- Container-based MCP service deployment
- Multi-protocol compatibility and conversion
- Real-time service monitoring dashboard
- Role-based access control and authentication
- One-click service deployment and configuration
- Kubernetes-native architecture support
InstallMCPRun via npx (Node)
Universal installANY TOOL
$ npx skillcity@latest Kymo-MCP/mcpcanAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
npx -y mcpcan
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"mcpcan": {
"command": "npx",
"args": [
"-y",
"mcpcan"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
mcpcan — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt