Model Context Protocol
How CloudShip connects AI agents to your infrastructure
What is MCP?
The Model Context Protocol (MCP) is an open standard created by Anthropic that connects AI agents directly to data sources and tools. It breaks down information silos by providing a universal way for AI systems to access contextual information.
Instead of AI models being "trapped behind information silos and legacy systems," MCP creates secure, two-way connections between AI agents and your infrastructure tools, enabling better decisions with full context.
Why MCP Matters for DevOps
- •Agents can securely access AWS, Kubernetes, monitoring tools, and more
- •Standardized protocol means any tool can become an agent capability
- •Fine-grained access control keeps your infrastructure secure
- •Agents maintain context across different tools and data sources
How CloudShip Station Uses MCP
Fine-Grained Access Control
Limit agents to specific tools and permissions. For example, give an agent read-only access to AWS Cost Explorer without broader AWS permissions. Each agent gets exactly the access it needs.
OpenAPI to MCP
Station automatically converts any OpenAPI/Swagger specification into an MCP server. Turn any REST API into an agent tool instantly without writing custom integration code.
Self-Hosted Runtime
Deploy agents on your own infrastructure with full control. Station runs MCP servers locally, keeping your credentials secure and your data on your infrastructure. No cloud credentials leave your environment.
MCP in Action: Real Use Cases
How DevOps teams use CloudShip Station with MCP to automate operations
Cost Analysis Agent
An agent with read-only access to AWS Cost Explorer analyzes spending patterns across your organization. Through MCP, it securely queries cost data without needing full AWS credentials.
# AWS Cost Explorer - read only
Security Scan Agent
Perform automated security scans by connecting to your security tools via MCP. The agent can read vulnerability data, query compliance status, and generate reports.
- name: security-api
type: openapi
Kubernetes Monitor
Monitor your Kubernetes clusters by connecting to the K8s API through MCP. The agent tracks deployments, pod health, and resource usage without storing credentials.
'k8s_get_deployments']
Compliance Validator
Validate deployments against compliance requirements by querying multiple data sources through MCP. Cross-reference infrastructure state with policy requirements.
- compliance-db
- infrastructure-api
Ready to Build Your Own AI Agents?
CloudShip Station is open source. Deploy AI agents on your infrastructure with full control using the Model Context Protocol.