Generate infrastructure code for a project through the Vercel API
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Stakpak MCP Server generate Docker infrastructure for my web app"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A MCP server that connects to Stakpak API.
Before using the MCP server, you'll need to obtain a Stakpak API key. You can get your API key by:
Visiting Stakpak's website
Logging into your account
Going to your profile and navigating to the API keys section
For detailed instructions, see the Stakpak API Key Management documentation.
To install in a project, add the MCP server to your claude_desktop_config.json:
{
"mcpServers": {
"stakpak": {
"command": "npx",
"args": ["@stakpak/mcp@latest", "--output=resource"],
"env": {
"STAKPAK_API_KEY": "<your-stakpak-api-key>"
}
}
}
}To install in a project, add the MCP server to your .cursor/mcp.json:
{
"mcpServers": {
"stakpak": {
"command": "npx",
"args": ["@stakpak/mcp@latest STAKPAK_API_KEY=<YOUR_API_KEY>"]
}
}
}To install globally, add this command to your Cursor settings:
npx @stakpak/mcp STAKPAK_API_KEY=<your-stakpak-api-key>Add the MCP server to your ~/.codeium/windsurf/mcp_config.json file:
{
"mcpServers": {
"stakpak": {
"command": "npx",
"args": ["@stakpak/mcp@latest"],
"env": {
"STAKPAK_API_KEY": "YOUR_API_KEY"
}
}
}
}Related MCP server: Stack AI MCP Server
This MCP server provides the following tools for interacting with the Vercel API:
generate_infrastructure_code - Generate infrastructure code for a project
To set up the development environment:
Clone the repository:
git clone https://github.com/stakpak/mcp.git
cd mcpInstall dependencies:
bun installBuild the project:
bun buildInstall the MCP server globally:
npx @modelcontextprotocol/inspector node <path-to-your-build-file> -e STAKPAK_API_KEY=<your-stakpak-api-key>Add the MCP server to your project:
The MCP server can be integrated with various IDEs:
Add the MCP server to your .cursor/mcp.json:
{
"mcpServers": {
"stakpak": {
"command": "node",
"args": [
"<path-to-your-build-file> STAKPAK_API_KEY=<your-stakpak-api-key>"
]
}
}
}Generates infrastructure code based on a natural language prompt and selected context
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Natural language description of what infrastructure code to generate | |
| provisioner | Yes | Target infrastructure platform to generate code for (e.g. Terraform for cloud resources, Kubernetes for container orchestration) | |
| selected_content | No | Array of code selections to use as context for generation | |
| resolve_validation_errors | No | Whether to attempt automatic fixes for any validation errors in the generated code |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does not mention whether the tool modifies any state, what output is returned, or how the selected context is used. It only states the action without revealing side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, front-loaded with the primary action and resource, with no wasted words. It is immediately understandable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has four parameters, including a complex selection array and a boolean flag, but the description does not explain expected behavior, output format, or how validation errors are handled. Given the absence of an output schema, the description is insufficient for full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds the notion that a prompt and selected context work together, which is useful, but it does not enrich parameter semantics beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Generates') and resource ('infrastructure code'), and adds clarifying context ('based on a natural language prompt and selected context'). It clearly distinguishes the tool's function even without sibling tool names.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, prerequisites, or typical scenarios. The description is a bare statement of function, leaving the agent without context for when selection is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.0.3generate_infrastructure_codeScored across 1 tool
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clearly defined and distinct.
The single tool name follows a clear verb_noun pattern (generate_infrastructure_code), and there are no other tools to cause inconsistency.
One tool feels thin for a server, but it is not extreme. The tool serves a specific function, making the count borderline rather than clearly inappropriate.
The tool only covers generation, missing complementary operations such as validation, listing existing code, or managing contexts. This leaves significant gaps in the expected workflow.
Unified API to query AWS, GCP, Azure and generate Terraform/CLI execution kits for AI agents.
Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current.
Designs, prices, and deploys AWS/GCP cloud infrastructure from plain-English requirements.
Check if a repo will deploy, plan a deploy to your own cloud, and see status, logs and redeploys.
