CalibratedDecisions.

Repo · SDKs & integrations

TypeSafe MCP

Expose typed judgments to MCP clients.

Open github.com ↗

From the repository

An mcp connector to evaluate anything fast and cheap. Give your AI agent direct access to typesafe ai's jev model and open weight models like laya

mcpmcp-tools

How builders describe it

TypeSafe MCP exposes Jev judgments to coding agents through a Go stdio MCP server, with an additional pi extension.
An MCP connector that gives your agent direct access to Jev.
A single-binary Go MCP server exposing one evaluate tool for noul, choice, and score questions, with one-command registration for Claude Code, Claude Desktop, and Codex.
If you haven't tried Jev yet, the quickest way to see how fast deterministic decisions feel is hooking it straight into your agent. This connector hands back typed judgments and raw probabilities your code can branch on instantly. You can wire it into Claude Code, Codex, or pi in seconds.

The decision Jev makes

Any Jev question: yes or no, a choice, or a score, from your own stack.

Where it fits

Official and community SDKs, MCP servers and integrations for calling Jev from the languages and tools you already use. All 625 sdks & integrations projects →

Related projects