generate_lgtm_dogLABSCO SUMMARY
A one-call joke generator that actually finishes the job.
Nothing about this is load-bearing, and that is the point: it produces a usable PNG in a single call, with the text already scaled to the image, so there is no second step in an image editor. Pass an output path if you want it somewhere other than wherever the server happened to start.
What it is
A Node MCP server that pulls a random dog photo from the Dog CEO API, overlays LGTM on it, and saves the result as a PNG.
What you get
generate_lgtm_dog— one call, one finished image- A random dog photo per call, fetched from the Dog CEO API
- LGTM centred on the image in green with a white outline, sized to the photo rather than fixed
- An optional
outputPath; leave it out and the file is named automatically in the current directory
Requirements
npm install then npm run build, then point Claude Desktop at the built dist/index.js and restart the app fully so it picks up the server.
Setup effort
Build from source
USE CASES
01
Approving a pull request with style
Ask for an LGTM image and drop the generated PNG into the review comment.
02
Keeping the files organised
Pass an output path so images land in a folder you chose rather than the working directory.
03
Making a small batch
Call it several times — each call fetches a different dog.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/shin-usu/lgtm-dog-mcp
cd lgtm-dog-mcp
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"lgtm-dog": {
"command": "node",
"args": [
"<YOUR_PATH_TO_LGTM_DOG_MCP>/dist/index.js"
]
}
}
}
