Judgevet runs on your own machine — the client starts it, so there is no endpoint to ping. 2 282 installs a week from pypi. Last commit 10 Oct 2026.
Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
Today is the operative word: we check Judgevet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add judgevet -- uvx judgevet
{
"mcpServers": {
"judgevet": {
"args": [
"judgevet"
],
"command": "uvx"
}
}
}
[mcp_servers.judgevet]
command = "uvx"
args = ["judgevet"]
{
"mcpServers": {
"judgevet": {
"args": [
"judgevet"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"judgevet": {
"args": [
"judgevet"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
JEV_API__KEY (TypeSafe API key. Tool inputs are sent to TypeSafe for judgment.).
The author declared them in the registry entry; get the values from the project itself.
Lint questions for TypeSafe's Jev and OpenAI's Luna offline, or ask the model itself with your key.
Pare Search ג€” Structured code search operations (ripgrep + fd) as typed JSON.
Pare GitHub ג€” Structured GitHub operations (PRs, issues, actions) as typed JSON.
Evidence-oriented code questions, diff review and test selection via a Jev endpoint.
Structured interviewer for Claude Code — probing questions, decision tracking, evolving checkpoints.
Wraps Codex CLI as MCP tools: codex, review, query, search, structured, ping, listSessions.
Generate invoice, receipt, and report PDFs from structured JSON via a single API call.
SDMX Structure MCP — dataflow dimensions and code lists for any SDMX 2.1
Answers built from our own checks of this server.