Jev MCP — AI skill for Claude Code

jev-mcp

[](https://github.com/Afloat16/jev-mcp/actions/workflows/ci.yml) [](LICENSE) [](https://nodejs.org/) [](https://modelcontextprotocol.io/)

**Unofficial, community-maintained MCP server for TypeSafe AI Jev.**

[简体中文](README.zh-CN.md) · [One-click install](docs/INSTALLATION.md) · [Quick start](docs/QUICKSTART.md) · [Examples](examples/README.md) · [Security](SECURITY.md) · [FAQ](docs/FAQ.md)

`jev-mcp` exposes TypeSafe AI's Jev decision model as four conservative, read-only MCP tools for **bounded probabilistic decisions**.

It is intentionally designed as a **second-opinion layer**, not as a replacement for the active coding/reasoning model.

This project is not affiliated with, endorsed by, sponsored by, or an official product of TypeSafe AI or OpenAI.

Why this exists

Strong coding agents are good at open-ended reasoning, code generation, debugging, and repository-wide analysis. Jev is useful for a different class of problem: small, explicit decisions that benefit from a structured probability signal.

Typical examples:

• retry vs rollback vs change strategy;
• route to one of several known tools or subsystems;
• estimate low / medium / high / critical change risk;
• evaluate a yes/no gate against a threshold;
• repeat the same bounded decision many times in an automated workflow.

The design rule is simple:

deterministic evidence
        >
host-model repository-aware reasoning
        >
Jev probabilistic advice

A Jev result is **advisory**. It is never proof, never ground truth, and never authorization for destructive or irreversible work.

Architecture

flowchart LR
    U[User] --> H[Active host model / MCP client]
    E[Tests · compiler · runtime · static