DevOps / Cloud Stack for Claude Desktop
Configuration
{
"mcpServers": {
"docker-mcp": {
"command": "npx",
"args": [
"-y",
"docker-mcp"
]
},
"kubernetes-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-kubernetes"
]
},
"cloudflare-mcp": {
"command": "npx",
"args": [
"-y",
"@cloudflare/mcp-server-cloudflare"
],
"env": {
"CLOUDFLARE_API_TOKEN": "YOUR_CLOUDFLARE_API_TOKEN",
"CLOUDFLARE_ACCOUNT_ID": "YOUR_CLOUDFLARE_ACCOUNT_ID"
}
},
"github-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-github"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PERSONAL_ACCESS_TOKEN"
}
},
"sentry-mcp": {
"command": "npx",
"args": [
"-y",
"sentry-mcp"
],
"env": {
"SENTRY_AUTH_TOKEN": "YOUR_SENTRY_AUTH_TOKEN"
}
}
}
}Where to save
Paste the config above into:
~/Library/Application Support/Claude/claude_desktop_config.jsonEnvironment Variables
Replace the YOUR_ placeholders with your actual values.
CLOUDFLARE_API_TOKENrequiredCloudflare API token
Used by: Cloudflare MCP
CLOUDFLARE_ACCOUNT_IDrequiredCloudflare account ID
Used by: Cloudflare MCP
GITHUB_PERSONAL_ACCESS_TOKENrequiredGitHub personal access token
Used by: GitHub MCP
SENTRY_AUTH_TOKENrequiredSentry auth token
Used by: Sentry MCP
What’s in this stack
Manage Docker containers, images, volumes, and networks. Run, stop, inspect, and monitor containers from your AI editor.
Build, run, and debug containers without leaving your editor. The foundation of modern deployment pipelines.
Interact with Kubernetes clusters via kubectl. Manage pods, deployments, services, and configurations from your AI editor.
Manage clusters, pods, and deployments from your AI assistant. Complex K8s YAML becomes conversational.
Interact with Cloudflare services including Workers, KV, R2, D1, and DNS management from your AI editor.
DNS, Workers, and edge config in one place. Pairs with K8s for the full infrastructure picture — edge to cluster.
Access the GitHub API to manage repositories, issues, pull requests, branches, and workflows directly from your AI editor.
CI/CD pipelines, Actions workflows, and infrastructure-as-code PRs. The glue between your code and your deployment.
Query Sentry for error tracking, performance monitoring, and issue management directly from your AI editor.
Monitor what you deploy. Surface production errors immediately so you can correlate issues with recent infrastructure changes.