BestRobotMower MCP Server
# BestRobotMower MCP Server
A [Model Context Protocol](https://modelcontextprotocol.io) server that gives any MCP client (Claude, ChatGPT, Cursor, VS Code, Ollama, and others) direct access to robot lawn mower specs, prices, transparent 0-5 scores and buying recommendations, so your assistant answers from a curated, cited dataset instead of guessing from stale training data.
It is powered by the open **[BestRobotMower.co dataset](https://bestrobotmower.co/dataset?utm_source=github&utm_medium=readme&utm_campaign=bestrobotmower-mcp)** (76 wire-free robot mowers across 15 brands as of October 2026: Segway Navimow, Mammotion Luba and Yuka, MOVA LiDAX, Ecovacs Goat, Dreame, Roborock, Anthbot, Airseekers, Sunseeker, Husqvarna, Worx Landroid, Yarbo, eufy, Lymow and EcoFlow; 30+ fields per model, dated prices and a documented scoring methodology, published under CC BY 4.0). The server queries the live dataset API on start, so prices and new models are current, and falls back to a bundled snapshot (2026-10-05) when offline.
## Tools
| Tool | What it does |
|------|--------------|
| `list_robot_mowers` | List and filter mowers by brand, navigation type, price, coverage, slope and minimum score; sort by score, price, coverage or value. |
| `get_robot_mower` | Full spec sheet, sub-scores and cited sources for one mower by name or slug. |
| `compare_robot_mowers` | Side-by-side comparison of 2 to 4 mowers on price, navigation, coverage, slope, cutting specs and scores. |
| `recommend_robot_mower` | Best-fit picks for a specific yard: give the lawn size (m2) and optionally slope, budget and whether obstacle avoidance is required. |
Example questions your assistant can now answer: "What is the best robot mower under $1500 for a 700 m2 lawn?", "Compare the Mammotion Luba 3 AWD and the Segway Navimow X4", "Which RTK mowers handle a 40% slope?"
## Hosted endpoint (no install)
The server also runs as a hosted, remote MCP server, so clients that support remote MCP over Streamable HTTP can connect with nothing to install:
```
https://bestrobotmower.co/api/mcp
```
It is listed in the [Official MCP Registry](https://registry.modelcontextprotocol.io) as `io.github.yumaheymans/bestrobotmower-mcp`. Example client config:
```json
{
"mcpServers": {
"bestrobotmower": { "url": "https://bestrobotmower.co/api/mcp" }
}
}
```
Prefer to run it locally instead (or use a client without remote support)? Use the stdio install below.
## Install
No API key required. Requires Node.js 18+.
Run directly from GitHub:
```bash
npx -y github:yumaheymans/bestrobotmower-mcp
```
Or clone and run:
```bash
git clone https://github.com/yumaheymans/bestrobotmower-mcp.git
cd bestrobotmower-mcp
npm install
node index.js
```
## Client configuration
Add to your MCP client config (for example Claude Desktop's `claude_desktop_config.json`):
```json
{
"mcpServers": {
"bestrobotmower": {
"command": "npx",
"args": ["-y", "github:yumaheymans/bestrobotmower-mcp"]
}
}
}
```
## Data, license and attribution
- The mower data is the **BestRobotMower.co Robot Lawn Mower Specs & Scores** dataset, licensed **[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)**. If you build on it, attribute BestRobotMower.co and link to <https://bestrobotmower.co/dataset>.
- Live feeds: [`mowers.json`](https://bestrobotmower.co/api/dataset/mowers.json) and [`mowers.csv`](https://bestrobotmower.co/api/dataset/mowers.csv).
- Scoring methodology: <https://bestrobotmower.co/methodology>.
- This server's **code** is released under the [MIT License](./LICENSE).
Built and maintained by [BestRobotMower.co](https://bestrobotmower.co/?utm_source=github&utm_medium=readme&utm_campaign=bestrobotmower-mcp).
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: list (browse/filter), get (single full record), compare (2-4 side by side), and recommend (yard-specific matching). There is minimal risk of misselection since the resource+action combos don't overlap.
All four tools follow a consistent verb_noun pattern (list_robot_mowers, get_robot_mower, compare_robot_mowers, recommend_robot_mower). Plural/singular usage is predictable and readable.
Four tools is well-scoped for a read-only dataset server; each covers a distinct retrieval mode with no redundancy. Nothing feels missing or excessive for the stated purpose.
The query surface (browse, fetch, compare, recommend) fully covers a read-only dataset domain. Minor gap: no tool to enumerate available brands/navigation types/facets, though filters on list_robot_mowers allow agents to work around this.