Provision Stack MCP
Cloud infrastructure provisioning via natural language. Enables deploying production-ready infrastructure on AWS, GCP, Azure, or Oracle with a single prompt.
README
Provision Stack MCP
Cloud infrastructure provisioning via natural language. Deploy production-ready infrastructure on your own AWS, GCP, Azure, or Oracle account with a single prompt.
Quick Start
Remote (recommended)
Point your MCP client directly at the hosted API — no local process needed:
{
"mcpServers": {
"provision-stack": {
"url": "https://api.provision-stack.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}
Get a token: curl -X POST https://api.provision-stack.com/auth/tokens -H 'Content-Type: application/json' -d '{"agentId":"your-agent","scopes":[]}'
Local stdio (via npx)
npx @provision-stack/mcp
Or add to your MCP client config:
{
"mcpServers": {
"provision-stack": {
"command": "npx",
"args": ["-y", "@provision-stack/mcp"],
"env": {
"PROVISION_STACK_API_TOKEN": "YOUR_TOKEN"
}
}
}
}
Install globally
npm install -g @provision-stack/mcp
provision-stack-mcp
Tools (12)
| Tool | Purpose |
|---|---|
generate_suggestions |
Get 4 tier options (Starter/MVP/Startup/Enterprise) with monthly costs |
get_pricing |
Detailed cost breakdown for individual cloud resources |
detect_region |
Detect configured AWS/GCP/Azure/Oracle region |
detect_providers |
Detect all configured cloud providers |
list_credentials |
Check cloud credential configuration |
deploy |
Provision infrastructure via the Execution API |
get_deployment_status |
Check deployment progress |
destroy |
Tear down a specific deployment |
list_deployments |
List all tracked deployments |
teardown_latest |
Destroy most recent active deployment |
get_balance |
Check account credit balance |
top_up |
Add credits (XRP or Stripe) |
Typical Flow
1. detect_region → Get your AWS region
2. generate_suggestions → Get 4 tier options with costs
3. Present options → Show costs, resources, tradeoffs
4. WAIT for user choice → Never proceed without explicit selection
5. deploy → Provision infrastructure
6. Report results → Deployment ID, resources, costs
Environment Variables
| Variable | Description | Default |
|---|---|---|
PROVISION_STACK_EXECUTION_API_URL |
API base URL | https://api.provision-stack.com |
PROVISION_STACK_API_TOKEN |
Bearer token | (none — read-only tools work without) |
AWS_REGION |
AWS region override | ~/.aws/config or us-east-1 |
AWS_PROFILE |
AWS profile name | default |
Architecture
This package is a thin client — it defines MCP tools and forwards calls to the hosted Execution API. All business logic (pattern matching, pricing, Terraform generation, verification) runs server-side.
Your AI Client → MCP stdio/HTTP → This Package → Execution API → Your AWS Account
The API endpoint requires authentication for write operations (deploy, destroy, top_up). Read operations (generate_suggestions, get_pricing, detect_region) work without a token.
Links
- API: https://api.provision-stack.com
- Website: https://provision-stack.com
- Docs: https://provision-stack.com/llms.txt
- Issues: https://github.com/TravisLinkey/provision-stack-mcp/issues
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.