Isilon

A practical MCP server that enables Claude and other clients to interact with Dell PowerScale OneFS via a generated tool set.
  • python

0

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You deploy an MCP server to connect your Dell PowerScale (Isilon) cluster with AI assistants. This server exposes a complete MCP API surface, handling authentication, tool generation from the OpenAPI spec, and multiple transport options so you can drive cluster operations from Claude, n8n, or your own client.

How to use

You interact with the Isilon MCP Server through a client that can talk either via standard input/output or via an HTTP/SSE endpoint. Use the stdio transport when you want a direct CLI or desktop integration, or use the HTTP/SSE transport to connect web-based tools like n8n.

With the stdio transport, you start the server locally and communicate through the process I/O. With the HTTP/SSE transport, you run a local HTTP server and point your client to the /sse endpoint to receive server-sent events and issue commands.

You can perform common storage management tasks such as listing SMB/NFS shares, inspecting cluster health, managing snapshots, and handling SyncIQ policies by invoking the generated MCP tools from your client. Tools are generated to cover the full scope of the OneFS API, so you have a consistent way to access authentication, protocols, quotas, events, and more.

How to install

Prerequisites you need before installing: Python 3.10 or higher, and access to a PowerScale cluster with the REST API enabled. You also need credentials with appropriate permissions.

Install from PyPI (recommended) via pip. If you want HTTP server support for n8n, install with the http extras.

# Install the package
pip install isilon-mcp-server

# Or install with HTTP server support for n8n
pip install "isilon-mcp-server[http]"

Install from source if you prefer to run from a checkout.

# Clone the repository
git clone https://github.com/sachdev27/isilon-mcp-server.git
cd isilon-mcp-server

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install the package
pip install -e .

# Or install with HTTP server support for n8n
pip install -e ".[http]"

Configuration

Create a local environment file to store your credentials and connection details. The example below shows the variables you typically set.

ISILON_HOST=your-powerscale-host
ISILON_USERNAME=admin
ISILON_PASSWORD=your-secure-password
ISILON_PORT=8080
ISILON_TLS_VERIFY=true

Running the server

Choose the transport that matches your workflow.

# StdIO transport for Claude Desktop use
# Using the CLI
isilon-mcp

# Or using Python module
python -m isilon_mcp.main

HTTP/SSE transport for web clients

Start the HTTP server locally and then connect your client to the SSE endpoint.

# Start HTTP server
python -m isilon_mcp.http_server

# With custom host/port
python -m isilon_mcp.http_server --host 0.0.0.0 --port 8000

Claude Desktop integration

Configure Claude Desktop to run the MCP server inside your environment. The following example shows how to reference the Python module you started above.

{
  "mcpServers": {
    "isilon": {
      "command": "/path/to/venv/bin/python",
      "args": ["-m", "isilon_mcp.main"],
      "cwd": "/path/to/isilon-mcp-server",
      "env": {
        "ISILON_HOST": "your-powerscale-host",
        "ISILON_USERNAME": "admin",
        "ISILON_PASSWORD": "your-password"
      }
    }
  }
}

n8n integration

For n8n, start the HTTP server and then add an MCP Client node pointing to the SSE endpoint.

# Start the HTTP server
python -m isilon_mcp.http_server --host 0.0.0.0 --port 8000

# Use in n8n
http://localhost:8000/sse

Example usage

After connecting, you can ask the system to list SMB shares, show cluster health, create NFS exports, fetch snapshots, inspect SyncIQ policies, or list users.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational