Rubricscore runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 10 Nov 2026.
Grade essays and resumes, and judge texts with typed yes/no, choice and score questions.
Today is the operative word: we check Rubricscore 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 rubricscore -- npx -y @reneturcios/rubricscore
{
"mcpServers": {
"rubricscore": {
"command": "npx",
"args": [
"-y",
"@reneturcios/rubricscore"
]
}
}
}
[mcp_servers.rubricscore]
command = "npx"
args = ["-y", "@reneturcios/rubricscore"]
{
"mcpServers": {
"rubricscore": {
"command": "npx",
"args": [
"-y",
"@reneturcios/rubricscore"
]
}
}
}
{
"servers": {
"rubricscore": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/rubricscore"
]
}
}
}
Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
Evaluate state with typed choice, score, and probability questions.
Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.
Yes/no questions about local files, and relevant-file search, with TypeSafe Jev
Typed decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
Typed yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back.
Typed noul / choice / score judgments from a local Laya model, with token-budget preflight.
Answers built from our own checks of this server.