← Back to Skills Marketplace
f-liva

Ecovacs Mcp

by Federico Liva · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
257
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ecovacs-mcp
Description
Control Ecovacs robot vacuums (DEEBOT series) via the official Ecovacs MCP server — start/stop/pause cleaning, send the robot to its dock, check battery and...
README (SKILL.md)

Ecovacs Robot Vacuum Control

Control Ecovacs robot vacuums through the official Ecovacs MCP server. This is the first official MCP integration for robotic cleaning devices.

Prerequisites

  • API Key (ECO_API_KEY) from open.ecovacs.com
  • uvx (recommended) or python3 with ecovacs-robot-mcp installed
  • A robot registered in the Ecovacs mobile app, bound to the same account

MCP Server Configuration

The MCP server entry should look like this in your settings:

{
  "ecovacs_mcp": {
    "command": "uvx",
    "args": ["--from", "ecovacs-robot-mcp", "python", "-m", "ecovacs_robot_mcp"],
    "env": {
      "ECO_API_KEY": "YOUR_API_KEY",
      "ECO_API_URL": "https://open.ecovacs.com"
    }
  }
}

Regional endpoints:

  • International: https://open.ecovacs.com
  • China mainland: https://open.ecovacs.cn

MCP Tools Reference

The server exposes four tools. All device operations use a nickname parameter that supports fuzzy matching — you don't need the exact name.

get_device_list

Lists all robots bound to the account. No parameters. Always call this first to discover available robots and their nicknames.

start_cleaning

Controls cleaning operations.

Parameter Values Description
nickname string Robot name (fuzzy match)
act s Start cleaning
act p Pause cleaning
act r Resume cleaning
act h Stop cleaning

control_recharging

Controls dock/charging operations.

Parameter Values Description
nickname string Robot name (fuzzy match)
act go-start Return to charging dock
act stopGo Cancel return to dock

query_working_status

Returns real-time robot state. No input besides nickname. Returns three status fields:

  • cleanSt — Cleaning state (sweeping, mopping, paused, idle, mapping)
  • chargeSt — Charging state (returning to dock, docking, charging, idle)
  • stationSt — Dock station state (washing mop, drying, dust collection, idle)

Operating Guidance

  1. Always list devices first — call get_device_list before any operation to get the correct nickname. Cache the nickname for the session.
  2. Confirm actions — after starting or stopping cleaning, call query_working_status to verify the command took effect.
  3. Standard workflows:
    • Start cleaning: list devices → start_cleaning (act: s) → check status
    • Send home: control_recharging (act: go-start) → check status
    • Pause and resume: start_cleaning (act: p) → later (act: r)
  4. Natural language mapping:
    • "vacuum the house" / "clean the floor" / "start cleaning" → start_cleaning act: s
    • "send it back" / "dock" / "go home" / "charge" → control_recharging act: go-start
    • "stop" / "pause" → start_cleaning act: p or h
    • "what's it doing?" / "is it charging?" → query_working_status

Troubleshooting

  • No devices found — robot must be set up in the Ecovacs app and bound to the same account used for the API key
  • Authentication errors — verify ECO_API_KEY is correct and ECO_API_URL matches your region
  • Server won't start — ensure uvx is available (pip install uv), or install directly: pip install ecovacs-robot-mcp
Usage Guidance
This skill appears to do what it claims: it needs your Ecovacs API key and either uvx or the Python MCP package to call the official MCP server. Before installing, verify you trust the skill source (README/_meta reference a GitHub repo; confirm that repo is legitimate). If you proceed: provide a dedicated API key tied to the Ecovacs account you want the assistant to control, avoid placing other unrelated secrets in the same environment, and be aware the agent may autonomously invoke the skill when vacuum-related language appears (you may want to restrict or monitor autonomous actions). If you later remove the skill, rotate or revoke the API key. Minor metadata inconsistencies (package version and source labels) exist in the files — not inherently dangerous but worth checking the upstream repo for authenticity.
Capability Analysis
Type: OpenClaw Skill Name: ecovacs-mcp Version: 1.0.0 The skill is a standard integration for controlling Ecovacs robot vacuums via the official Ecovacs MCP server. It provides tools for device discovery, cleaning control, and status monitoring using the legitimate ecovacs-robot-mcp package and official API endpoints (open.ecovacs.com). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found across SKILL.md, skill.toml, or the documentation.
Capability Assessment
Purpose & Capability
Name/description, required env var (ECO_API_KEY), and required binaries (uvx or python3 + ecovacs-robot-mcp) are coherent with a skill that proxies commands to the official Ecovacs MCP server. The primary credential (ECO_API_KEY) is appropriate and expected for this integration.
Instruction Scope
SKILL.md stays within the stated scope (discover devices, call get_device_list, start/stop/pause, query status) and does not instruct reading unrelated files or exfiltrating data. One operational note: the doc repeatedly instructs the agent to 'use this skill whenever the user mentions their robot vacuum — even if they don't say "Ecovacs" explicitly', which is broad and could cause frequent autonomous invocation. Also it suggests caching nicknames for the session (normal but means device identifiers will be stored in session context).
Install Mechanism
This is an instruction-only skill with no install spec and no archives/downloads. It only recommends installing uvx or the ecovacs-robot-mcp Python package via pip; that is low-risk and expected.
Credentials
Only ECO_API_KEY is required/declared as the primary credential; that matches the described functionality. No unrelated secrets, config paths, or multiple external credentials are requested.
Persistence & Privilege
The skill is not marked always:true (good). It is set user-invocable: false but model invocation is allowed (disable-model-invocation: false), so the agent can autonomously invoke it; combined with the instruction to trigger on implicit mentions, this may lead to the skill being invoked whenever vacuum-related phrases appear. This is a design/behavioral choice rather than a direct security mismatch, but users should be aware.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ecovacs-mcp
  3. After installation, invoke the skill by name or use /ecovacs-mcp
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Ecovacs robot vacuum control via the official MCP server. - Adds support for controlling DEEBOT (Ecovacs) robots: start/stop/pause cleaning, send to dock, check battery/status, and list devices. - Integrates with the Ecovacs MCP server using an API key. - Uses fuzzy nickname matching for device selection. - Provides real-time status reports (cleaning, charging, station state). - Designed for seamless natural language triggers (e.g., “vacuum,” “send it home,” “is it charging?”).
Metadata
Slug ecovacs-mcp
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Ecovacs Mcp?

Control Ecovacs robot vacuums (DEEBOT series) via the official Ecovacs MCP server — start/stop/pause cleaning, send the robot to its dock, check battery and... It is an AI Agent Skill for Claude Code / OpenClaw, with 257 downloads so far.

How do I install Ecovacs Mcp?

Run "/install ecovacs-mcp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ecovacs Mcp free?

Yes, Ecovacs Mcp is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ecovacs Mcp support?

Ecovacs Mcp is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ecovacs Mcp?

It is built and maintained by Federico Liva (@f-liva); the current version is v1.0.0.

💬 Comments