opnsense
Modular MCP server for OPNsense firewall management - 88 tools providing access to 2000+ methods through AI assistants
claude mcp add --transport stdio pixelworlds-opnsense-mcp-server npx -y @richard-stovall/opnsense-mcp-server \ --env OPNSENSE_URL="https://192.168.1.1" \ --env INCLUDE_PLUGINS="true" \ --env OPNSENSE_API_KEY="your-api-key" \ --env OPNSENSE_API_SECRET="your-api-secret" \ --env OPNSENSE_VERIFY_SSL="false"
How to use
This MCP server exposes 88 modular tools that map to OPNsense modules, enabling an AI assistant to manage your firewall through a type-safe interface. Each tool like firewall_manage or interfaces_manage represents a module and accepts a method parameter to specify the exact operation, e.g., to search for a firewall alias you would call the firewall_manage tool with method set to aliasSearchItem and provide the necessary parameters. The plugin system can extend capabilities with 64 additional plugin modules if enabled. To use, configure your MCP client (Claude Desktop, Cursor, or other MCP-compatible clients) to connect to the server using the provided URL, API key, and secret, and ensure SSL verification settings match your environment. Typical prompts include asking for system status via core_manage, listing aliases with firewall_manage, or retrieving network interfaces with interfaces_manage. When plugins are enabled, you can access additional capabilities such as Nginx management via plugin_nginx_manage or other plugin modules depending on your configuration.
How to install
Prerequisites:
- Node.js 18 or higher
- An OPNsense firewall with API access enabled
- An API key and API secret from OPNsense
Install from npm:
npm install -g @richard-stovall/opnsense-mcp-server
Configure the MCP server (example for Claude/Cursor integration):
{
"mcpServers": {
"opnsense": {
"command": "npx",
"args": ["-y", "@richard-stovall/opnsense-mcp-server"],
"env": {
"OPNSENSE_URL": "https://192.168.1.1",
"OPNSENSE_API_KEY": "your-api-key",
"OPNSENSE_API_SECRET": "your-api-secret",
"OPNSENSE_VERIFY_SSL": "false"
}
}
}
}
Alternative run (manual test):
node /path/to/opnsense-mcp-server/index.js \
--url https://YOUR-OPNSENSE-IP \
--api-key YOUR-API-KEY \
--api-secret YOUR-API-SECRET \
--no-verify-ssl
Test an available tool, e.g., core_manage to check system status by issuing a request with tool: "core_manage" and method: "systemStatus" in your MCP client.
Additional notes
Tips and notes:
- Environment variables: OPNSENSE_URL, OPNSENSE_API_KEY, OPNSENSE_API_SECRET are required; OPNSENSE_VERIFY_SSL can be set to false to disable SSL verification during development.
- To enable all 64 plugin tools, include the flag or env INCLUDE_PLUGINS=true when starting the server.
- If you encounter connection issues, verify that the OPNsense API is accessible from the host running the MCP server and that the API credentials have appropriate permissions.
- Check server logs for startup messages like the version and available module counts (e.g., Core tools: 24 modules, Plugin tools: 64 modules).
- You can run the MCP server locally for testing before integrating with Claude Desktop or Cursor.
Related MCP Servers
evernote
Evernote MCP server - allows LLMs that support MCP (like Claude Desktop) to query your notes in Evernote
taskflow
A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.
tally
MCP server for Tally.so - manage forms through AI with natural language commands and safety-first bulk operations
VixMCP.Ai.Bridge
.NET bindings for VMware VIX API with Model Context Protocol server for AI-driven virtual machine automation
dokploy
MCP server for the Dokploy API. 196 tools across 23 modules. Your AI agent can now deploy apps, manage databases, configure domains, and handle backups -- without you touching a dashboard.
openapi-sync
OpenAPI Sync MCP Server - Parse, validate, and generate code from OpenAPI specs