get_lgtmLABSCO SUMMARY
Returns two forms so you never have to reformat.
The markdown covers a pull-request comment; the bare URL covers Slack, an issue template, or anywhere that renders images itself. That is the whole surface — one tool, no configuration, nothing to keep in sync.
What it is
A one-tool server that fetches a random LGTM image from the LGTM API and hands back both the markdown to paste and the direct image URL.
What you get
get_lgtmreturns a random LGTM image- The response includes ready-to-paste markdown for embedding the image, plus the direct URL for anywhere markdown is not what you need
Requirements
The npm package mcp-server-lgtm, version 0.1.0, which installs an mcp-server-lgtm command. Build it from source with npm install and npm run build, then point the client at build/index.js; there is also an automated Smithery install. No account, no key.
Setup effort
One command — npx -y @smithery/cli install @dongri/mcp-server-lgtm --client claude
USE CASES
01
Approving a pull request with something other than a thumbs-up
Ask for an image and paste the returned markdown straight into the review comment.
02
Posting the same approval outside a repo
Take the direct URL instead of the markdown when the destination renders its own images.
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.
Requires
npx on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
Build from source
TERMINAL
git clone https://github.com/dongri/mcp-server-lgtm
cd mcp-server-lgtm
npm install
npm run buildnpx
TERMINAL
npx -y @smithery/cli install @dongri/mcp-server-lgtm --client claudeMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"mcp-server-lgtm": {
"command": "<YOUR_PATH_TO_MCP_SERVER_LGTM>/build/index.js"
}
}
}
