About NAP MCP Server
NAP MCP Server exposes NAP API operations for managing projects, applications, clients, and workflows. It also supports workflow export and import between projects and workflow creation from prompts.
Key features
- 01Create projects, applications, and clients
- 02Create and manage workflows
- 03Export workflows between projects
- 04Generate workflows from prompts
Use cases
- 01Set up a project with applications and clients
- 02Create workflows from prompts
- 03Move workflows between projects
MCP support
It provides NAP API endpoints as MCP tools and resources, and supports workflow creation through MCP prompts.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMENAP MCP Server
This is a Model Context Protocol (MCP) server implementation for the NAP API. It provides a standardized way to interact with NAP API endpoints through MCP tools and resources - through prompts
Features
- Create Project, Add Applications, Add Clients & Create Workflows through MCP.
- Export Workflows from a project & Add to different Project (Import/Export Workflows).
- Create Workflows for a project using Prompts.
Installation
- Clone the repository
- Install dependencies:
pnpm install
- Copy
.env.exampleto.envand update the configuration:
cp .env.example .env
- Update the environment variables in
.envwith your NAP API configuration.
Development
-
Navigate to File > Preferences > Cursor Settings

-
Navigate to MCP and create a new Server
-
In the config, Paste the following:
"nap-mcp-server": {
"command": "node",
"args": ["./nap-mcp-server/index.js"]
}

Note: The server contains path to the index.js file, so if any changes are made by dev, make sure to run npx tsc to compile the javascript code
Common Usage
Below Video Demonstrates how to develop using MCP:
-
Import/Export Project: --> Utilize the prompts mentioned in
prompt-replicate-workflows.txtand edit the prompt based on the your requirements. -
Make sure Agent mode is enabled (if not available, update cursor)

Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.