What environment variables are required?
OMADA_BASE_URL, OMADA_CLIENT_ID, OMADA_CLIENT_SECRET, and OMADA_OMADAC_ID are required. OMADA_SITE_ID is optional.
@gaspareduard
Basic information
Security-first MCP server for TP-Link Omada, with a stdio-first runtime, capability-gated tools, and OpenAPI-based network automation.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"safe-omada": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"OMADA_BASE_URL=https://your-omada-controller.local",
"-e",
"OMADA_CLIENT_ID=your-client-id",
"-e",
"OMADA_CLIENT_SECRET=your-client-secret",
"-e",
"OMADA_OMADAC_ID=your-omadac-id",
"-e",
"OMADA_SITE_ID=your-site-id",
"-e",
"OMADA_STRICT_SSL=true",
"ghcr.io/ailivesinterminal/omada-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 security-focused MCP server for TP-Link Omada Open API workflows. It provides a controlled, auditable interface to manage Omada controllers, sites, devices, and clients through MCP tools.
Configure environment variables (OMADA_BASE_URL, OMADA_CLIENT_ID, etc.) and run via Docker with Claude Desktop or directly. Alternatively, install locally with npm install, build, and start. The server communicates over stdio by default; HTTP is available only as an explicitly unsafe lab mode.
OMADA_BASE_URL, OMADA_CLIENT_ID, OMADA_CLIENT_SECRET, and OMADA_OMADAC_ID are required. OMADA_SITE_ID is optional.
The default profile is `safe-read`, which grants read-only operational visibility. Other profiles include `ops-write`, `admin`, and `compatibility`.
Tools like restoreController require `confirmDangerous: true`. Without it, the tool returns a warning instead of executing. This gate is effective in conversational AI sessions but does not prevent autonomous agents from bypassing it.
HTTP is not part of the supported production baseline. It only starts when both `MCP_SERVER_USE_HTTP=true` and `MCP_UNSAFE_ENABLE_HTTP=true` are set, and is intended only for local lab/debug scenarios.
Pull the image from `ghcr.io/gaspareduard/omada-mcp:latest`, then add a server entry in your Claude Desktop MCP config with the required environment variables and run command.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Hindsight: Agent Memory That Learns

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Comments