TypeSafe runs on your own machine — the client starts it, so there is no endpoint to ping. 501 installs a week from npm. Last commit 3 Nov 2026.
Get calibrated yes or no answers, choices and scores from TypeSafe's Jev, for one item or 1000 rows.
Today is the operative word: we check TypeSafe 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 typesafe -e 'TYPESAFE_API_KEY_FILE=<TYPESAFE_API_KEY_FILE>' -- npx -y @foreverworks/mcp-typesafe
{
"mcpServers": {
"typesafe": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}
[mcp_servers.typesafe]
command = "npx"
args = ["-y", "@foreverworks/mcp-typesafe"]
env = { TYPESAFE_API_KEY_FILE = "<TYPESAFE_API_KEY_FILE>" }
{
"mcpServers": {
"typesafe": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}
{
"servers": {
"typesafe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}
Put your own value in place of
<TYPESAFE_API_KEY_FILE> (Path of a file holding your TypeSafe API key).
The author’s registry entry marks it as required.
Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.
Typed yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back.
Typed decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU
Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.
Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
Answers built from our own checks of this server.