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 de
What is MCPCAN?
MCPCAN is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 verifica...
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 de
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCPCAN is a centralized management platform for MCP services
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcpcanConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCPCAN
MCPCAN is a centralized management platform for MCP services that deploys each service as an isolated container, providing a web dashboard for monitoring, configuration, and access control. It solves the security and operational challenges of running many MCP servers by adding token-based authentication, role-based permissions, real-time performance monitoring, and Kubernetes-native scalability. Teams can manage dozens of MCP service instances from a single interface without manual per-server configuration.
Prerequisites
- Docker 20.10+ and Docker Compose installed
- Kubernetes cluster and Helm (optional, for production cloud-native deployment)
- Network access to pull container images from Docker Hub or a configured registry
- A modern web browser to access the management dashboard
- Basic familiarity with container orchestration concepts
Clone the repository and navigate to the Docker Compose directory
Pull the MCPCAN source code and move into the Docker Compose deployment folder, which contains all the service definitions and configuration templates.
git clone https://github.com/Kymo-MCP/mcpcan.git
cd mcpcan/deploy/docker-compose/Create and configure the environment file
Copy the example environment file and edit it to set your registry prefix and any other environment-specific values. The REGISTRY_PREFIX setting switches between global and China-local container mirrors.
cp example.env .env
# Edit .env to set REGISTRY_PREFIX and other settingsGenerate service configuration files
Run the replacement script to apply your environment values into the service configuration templates before launching.
chmod +x replace.sh
./replace.shLaunch all services
Start the full MCPCAN platform in detached mode. This brings up the management API, web dashboard, and supporting infrastructure containers.
docker compose up -dAccess the web dashboard
Open the MCPCAN management dashboard in your browser. Use the default credentials to log in and begin registering MCP service instances.
open http://localhost
# Default credentials: admin / admin123Register and monitor MCP services
From the dashboard, add your MCP servers as managed service instances. Configure token-based authentication, assign role permissions, and view real-time health metrics for each service.
MCPCAN Examples
Client configuration
Connect an MCP client to a service managed by MCPCAN. The platform exposes each MCP service through its authenticated gateway endpoint.
{
"mcpServers": {
"mcpcan-gateway": {
"command": "npx",
"args": ["mcpcan"],
"env": {
"MCPCAN_BASE_URL": "http://localhost",
"MCPCAN_TOKEN": "your-service-token"
}
}
}
}Prompts to try
Interactions that leverage MCPCAN's centralized service management and routing capabilities.
- "List all MCP services currently running on the platform and their health status."
- "Route my file-system tool calls through the MCPCAN gateway and log the usage metrics."
- "Deploy a new instance of the web-search MCP service with rate limiting enabled."Troubleshooting MCPCAN
Dashboard is unreachable at http://localhost after docker compose up
Check that port 80 is not already in use on your host with `docker compose ps` and `lsof -i :80`. If another service is using port 80, edit the docker-compose.yml to remap the dashboard to an alternate port.
Container images fail to pull during startup
If you are in China, set REGISTRY_PREFIX in your .env file to point to a domestic mirror. Internationally, ensure your Docker daemon has internet access and is authenticated to any private registries referenced.
Token verification fails when connecting MCP clients
Generate service tokens from the dashboard under Settings > Service Tokens. Tokens are scoped per service instance — make sure the token in your client config matches the specific service you are connecting to.
Frequently Asked Questions about MCPCAN
What is MCPCAN?
MCPCAN is a Model Context Protocol (MCP) server that 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 de It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCPCAN?
Follow the installation instructions on the MCPCAN GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCPCAN?
MCPCAN works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCPCAN free to use?
Yes, MCPCAN is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
MCPCAN Alternatives — Similar Cloud Services Servers
Looking for alternatives to MCPCAN? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCPCAN 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 MCPCAN?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.