What runtime is required?
The server runs on Node.js. Install dependencies with `npm install`, then build and start with `npm run build` and `npm start`.
@johnneerdael
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"netskope-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-p",
"3000:3000",
"ghcr.io/johnneerdael/privateaccess-mcp:latest"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A comprehensive Model Context Protocol (MCP) server for managing Netskope Private Access (NPA) infrastructure through AI-powered automation. It provides 84 specialized tools across 10 categories for tasks such as publisher management, private app lifecycle, policy management, SCIM integration, and compliance auditing.
Set environment variables (NETSKOPE_BASE_URL, NETSKOPE_API_TOKEN), then install and run via npm (npm install, npm run build, npm start) or Docker. Connect your MCP client using a JSON config that points to the serverβs command or URL, optionally passing credentials as headers.
The server runs on Node.js. Install dependencies with `npm install`, then build and start with `npm run build` and `npm start`.
Supply `NETSKOPE_BASE_URL` and `NETSKOPE_API_TOKEN` as environment variables, or pass the token via an `Authorization` header and tenant URL via `X-Netskope-Tenant` header in the MCP client configuration.
It exposes a streamable HTTP endpoint at `/mcp` and a liveness endpoint at `/healthz`. A generic JSON client config can target a URL like `https://YOUR-MCP-HOST.example.com/mcp`.
Yes. The server includes built-in rate limiting, API quota management, retry logic with exponential backoff, and graceful degradation for partial failures.
Yes. Two Docker Compose files are provided: one for the prebuilt multi-arch image from GHCR, and one for building locally. You can also run a standalone container with `docker run` using the image `ghcr.io/johnneerdael/privateaccess-mcp:latest`.
Open-source MCP to use Blender with any LLM

Model Context Protocol Servers

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student β in a fraction of the time. What once took a week, now takes one free period.
Comments