@microservices-sh/mcp

MCP serverCloud & infra

With this app added, your AI can plan, verify, and deploy apps built for Cloudflare. It takes a Cloudflare-native app from a first plan through checks to a finished deployment. This means you can hand cloud app work to your AI instead of doing each step yourself.

Available today. Use it from your connected AI after setup.

Add the app, then ask your AI to plan, verify, or deploy a Cloudflare-native app. You can look at github.com/microservices-sh/mcp to see what it does.

Then ask your AI: use @microservices-sh/mcp

What your AI can do with it

  • Plan how a Cloudflare-native app will be built
  • Verify an app before anything is deployed
  • Deploy Cloudflare-native apps
  • Carry an app from plan to deployment in one place

From the project's README

As published by microservices-sh/mcp in README.md.

MCP server for AI agents that generate, verify, and deploy Cloudflare-native apps from reusable microservices.sh modules.

This package is a standalone stdio MCP server. It vendors a small microservices.sh SDK/module-contract snapshot until the public SDK is split out.

Why Agents Use It

@microservices-sh/mcp gives coding agents a typed planning layer for building production-oriented Cloudflare apps. Agents can discover verified templates and modules, inspect module contracts, compose an app plan, validate configuration, generate project files for review, run readiness checks, and prepare approval-gated preview deployments through the microservices.sh control plane.

It is useful when an agent needs to build apps with common product modules such as auth, booking, customer records, payments, files, and audit logs without inventing each integration from scratch.

Install

pnpm add -D @microservices-sh/mcp

Or run it directly after publish:

pnpm dlx @microservices-sh/mcp

Or install from Glama:

MCP Client Config

{
  "mcpServers": {
    "microservices": {
      "command": "microservices-mcp",
      "env": {
        "MICROSERVICES_API_URL": "https://api.microservices.sh",
        "MICROSERVICES_API_KEY": "favored-secret-manager-reference"
      }
    }
  }
}

For local development inside this repo:

{
  "mcpServers": {
    "microservices-local": {
      "command": "node",
      "args": ["/absolute/path/to/mcp/dist/index.js"]
    }
  }
}

Build the local package first:

pnpm build

For agent-oriented one-click install guidance, see llms-install.md.

Tools

Read-only and local planning tools:

  • list_templates
  • inspect_template
  • list_modules
  • inspect_module
  • list_module_docs
  • get_module_doc
  • compose_app
  • validate_config
  • generate_project
  • run_checks
  • plan_add_module
  • check_updates
  • plan_module_upgrade
  • get_secrets_status
  • create_preview_plan

Remote control-plane tools:

  • deploy_preview
  • get_deployment_status

deploy_preview is mutating and requires confirm: "preview". Run create_preview_plan first.

Environment

VariablePurpose
MICROSERVICES_API_URLRemote control-plane URL. Defaults to https://api.microservices.sh.
MICROSERVICES_API_KEYBearer token for remote tools.
MICROSERVICES_TOKENFallback bearer token.

Secret values are never returned by the MCP tools.

Registry Notes

The package is published to npm, listed in the official MCP Registry, and verified by Glama:

The package declares "mcpName": "sh.microservices/mcp" in package.json. Docker/OCI packaging should wrap this same stdio server rather than forking behavior.

Signals

GitHub stars
1
Last commit
Sep 2026
Advanced
Delivery
mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
sh-microservices-mcp
Source
github.com/microservices-sh/mcp
Hosted endpoint
https://api.microservices.sh/mcp