User repository on GitHub
Unofficial conservative MCP server for TypeSafe AI Jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Agents & MCP
Jev MCP — Afloat16
Community Node.js MCP server exposing Jev as four read-only advisory tools for bounded probabilistic decisions, with the host model keeping final authority over every action.
- Stars
- 1
- Language
- TypeScript
- License
- MIT
- Published by
- Community
- Author
- Afloat16
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev MCP — jkudish.
About this project
Unofficial, community-maintained MCP server for TypeSafe AI Jev. 简体中文 · One-click install · Quick start · Examples · Security · FAQ. 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.
Quoted from the project's README. Read the full README.
Works forJev for Tool calling
Used inJev for Software & DevTools
- Languages
- TypeScript
Highlights
- Offers `jev_decide` (2-255 options), `jev_route`, `jev_risk_score`, and `jev_gate` over local stdio.
- Keeps the key in process env or a gitignored `.env`, never in MCP client config; sent state is billed API input.
- Installs via one-command script into `~/.jev-mcp/runtime` for Codex, Claude Code, Cursor, Gemini CLI, and more.
- Tags results as secondary advisory metadata; deterministic evidence always overrides the probability.
Watch out
Requires Node.js 20 or newer and a TypeSafe key; pre-1.0 with npm publishing intentionally disabled. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
Use it when the tool boundary itself matters: repeatability, structured output, orchestration, explicit thresholds, or shared agent workflows. High-volume application logic is cleaner as a direct SDK integration.
No. The digest is explicit that results are advisory only, never proof, ground truth, or authorization, and the tools edit no files, run no shell, deploy nothing, and switch no models.
The key lives only in `~/.jev-mcp/.env` while client configs carry no credential and are backed up first. Never commit `.env` or paste keys into docs, examples, issues, or logs.
Doctor, check, and inspect run with no API calls. A live tool invocation from MCP Inspector uses your own TypeSafe account and may consume provider credits.
Four read-only MCP tools: jev_decide for choosing among 2-255 explicit alternatives, jev_route for routing among known tools, jev_risk_score for an advisory low/medium/high/critical signal, and jev_gate for a yes/no probability against a threshold.
One-command installers cover Codex, Claude Code, Kimi Code, ZCode, Cursor, and Gemini CLI, plus Windsurf-compatible configs, generic .agents/mcp.json, and project-scoped VS Code/Copilot Agent configuration.
MIT, pre-1.0 with behavior that may evolve, Node.js 20 or newer, and local stdio transport with npm publishing intentionally disabled. One-click installs pin to the current release tag rather than main.
More Jev resources like this
2GitHub stars
Prompt-injection scanner that combines deterministic checks with focused Jev judgments and a configurable reasoning model, exposed over CLI, SDK, HTTPS, MCP, and editor plugins.
Jev Agents & MCP#community#github
Community
revsmoke/promptrejectormcpTypeScript
revsmoke/promptrejectormcpTypeScript1GitHub stars
OpenCode plugin that asks Jev once per prompt how much reasoning is needed, then maps minimal to xhigh effort onto the model's own variants without rewriting prompts.
Jev Agents & MCP#community#github
1GitHub stars
Pi extension that checks file-mutating tool calls against written rules in constraints.md, asking Jev which rule a change violates and offering rework with the rule text.
Jev Agents & MCP#community#github
Community
hcl-z/pi-jev-gateTypeScript
hcl-z/pi-jev-gateTypeScript0GitHub stars
MCP done-gate for coding agents: it diffs git reality, measures conventions deterministically, asks Jev eight quality questions, and returns a fix list.
Jev Agents & MCP#community#github
Community
BilalUchiha/vibecheck-mcpTypeScript
BilalUchiha/vibecheck-mcpTypeScript1.5kGitHub stars
Open-source platform that puts ACP-compatible agents such as Claude Code, Codex, and Pi inside the team's Slack, Telegram, Discord, and GitHub workflows, with reusable Jev decisions for routing, response gating, and reviewer selection.
Jev Agents & MCP#community#jevbest
488GitHub stars
A coding agent built on pi that hands its non-code decisions — what enters the context, whether a command is safe, whether the work is done — to a small judge model at 35 decision points per turn.
Jev Agents & MCP#community#jevbest
Community
qybaihe/muTypeScript
qybaihe/muTypeScriptFrom the Jev community
Posts from builders shipping with Jev right now.