S
shitianfang/jev-use
Hand steps that need no prose to a small judgment model
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
- Copy the command above
- Paste it as one entry under
mcpServersinclaude_desktop_config.json— local servers take command + args (example: clients) - Restart your client
Client config (built from the install command this repo gives)
{
"mcpServers": {
"shitianfang-jev-use": {
"command": "npx",
"args": ["-y", "jev-use"]
}
}
}Parsed from the README we fetched on 2026-11-05; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"shitianfang-jev-use": {
"command": "npx",
"args": ["-y", "jev-use"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio shitianfang-jev-use -- npx -y jev-use
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Source
- collected from the abordage/awesome-mcp list · type: MCP server
- Harvest history
- first seen 2026-11-05 · last seen 2026-11-14 · seen 10× · listed by 10 sources
- Score
- score 1,003 · 10 sources · mcp
- Install
npx -y jev-use
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
npx -y jev-use. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
first catalogued 2026-11-05；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.
# jev-use
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
English | 简体中文
The best way for Claude Code, Codex, and pi
to work with Jev:
hand the tasks that need no text output to Jev — faster steps, fewer
tokens, tasks done sooner and better.
It makes the LLM and Jev true collaborators: when content needs to be
written, the LLM takes over; when a step just needs a fast decision, Jev
executes it.
## Demos — real runs, 1× speed
Directions task: Jev clicks, the LLM types — 10 decisions (p50 274 ms) · 4 writes; Jev rejects a wrong route, the LLM rewrites
Context compaction — 200 messages judged in 7 calls, one LLM paragraph replaces the dropped pile; recall 3/3
Pong: ball speed = decision latency — 86 Jev decisions in 20 s vs 6 (haiku) and 3 (gemini) called the usual way; enum-constrain both and the gap is 3×
Gate every shell command — dangerous ones denied in ~230 ms with a reason, zero LLM tokens
Every demo is a rerunnable script in bench/examples/;
all numbers, methodology, variance and caveats:
bench/RESULTS.md · third-party measurements:
docs/evidence.md.
## Install
bash
npx -y jev-use install # wires Claude Code, Codex, and pi — whichever it finds
Set one key in the environment your agent runs in (JEVBACKEND=mock for
a keyless dry run):
| Provider | Env var |
| TypeSafe direct | TYPESAFEAPIKEY |
| OpenRouter | OPENROUTERAPIKEY |
| Vercel AI Gateway | AIGATEWAYAPIKEY |
npx -y jev-use doctor checks the wiring. Judged state goes to the
provider you configure; JEVBACKEND=mock stays local. Plugin form with
the routing skill and the PreToolUse gate:
harness/claude-code ·
harness/codex.
## Use as a library
npm i jev-use — zero runtime dependencies on the judgment path:
js
import { Jev, check, pick, rate } from "jev-use";
const jev = new Jev();
const { answers } = await jev.judge(state, {
next: pick("Next action?", { merge: "all green", rerun: "looks flaky", hold: "needs attention" }),
risk: rate("How risky?", ["routine", "worth a look", "incident"]),
passed: check("Did the run fully succeed?"),
});
// answers.next → { answer: "merge", confidence: 0.93, confidenceFrom: "reported", escalate: false }
Anything Jev can't or shouldn't decide comes back with escalate: true
and a typed reason. Tools, verdict shape, escalation contract, CLI:
docs/reference.md.
## Small enough to read
| File | Job |
| src/protocol.ts | Questions (check/pick/rate), verdicts, escalation reasons |
| src/dispatch.ts | Pre-call routing: what never reaches Jev |
| src/judge.ts | screen → backend → hand back what is unsure; gate |
The best way for Claude Code, Codex, and pi
to work with Jev:
hand the tasks that need no text output to Jev — faster steps, fewer
tokens, tasks done sooner and better.
It makes the LLM and Jev true collaborators: when content needs to be
written, the LLM takes over; when a step just needs a fast decision, Jev
executes it.
## Demos — real runs, 1× speed
Directions task: Jev clicks, the LLM types — 10 decisions (p50 274 ms) · 4 writes; Jev rejects a wrong route, the LLM rewrites
Context compaction — 200 messages judged in 7 calls, one LLM paragraph replaces the dropped pile; recall 3/3
Pong: ball speed = decision latency — 86 Jev decisions in 20 s vs 6 (haiku) and 3 (gemini) called the usual way; enum-constrain both and the gap is 3×
Gate every shell command — dangerous ones denied in ~230 ms with a reason, zero LLM tokens
Every demo is a rerunnable script in bench/examples/;
all numbers, methodology, variance and caveats:
bench/RESULTS.md · third-party measurements:
docs/evidence.md.
## Install
bash
npx -y jev-use install # wires Claude Code, Codex, and pi — whichever it finds
Set one key in the environment your agent runs in (JEVBACKEND=mock for
a keyless dry run):
| Provider | Env var |
| TypeSafe direct | TYPESAFEAPIKEY |
| OpenRouter | OPENROUTERAPIKEY |
| Vercel AI Gateway | AIGATEWAYAPIKEY |
npx -y jev-use doctor checks the wiring. Judged state goes to the
provider you configure; JEVBACKEND=mock stays local. Plugin form with
the routing skill and the PreToolUse gate:
harness/claude-code ·
harness/codex.
## Use as a library
npm i jev-use — zero runtime dependencies on the judgment path:
js
import { Jev, check, pick, rate } from "jev-use";
const jev = new Jev();
const { answers } = await jev.judge(state, {
next: pick("Next action?", { merge: "all green", rerun: "looks flaky", hold: "needs attention" }),
risk: rate("How risky?", ["routine", "worth a look", "incident"]),
passed: check("Did the run fully succeed?"),
});
// answers.next → { answer: "merge", confidence: 0.93, confidenceFrom: "reported", escalate: false }
Anything Jev can't or shouldn't decide comes back with escalate: true
and a typed reason. Tools, verdict shape, escalation contract, CLI:
docs/reference.md.
## Small enough to read
| File | Job |
| src/protocol.ts | Questions (check/pick/rate), verdicts, escalation reasons |
| src/dispatch.ts | Pre-call routing: what never reaches Jev |
| src/judge.ts | screen → backend → hand back what is unsure; gate |
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/shitianfang-jev-use/)
- Source
- awesome · https://github.com/shitianfang/jev-use
- Browse by field
- MCP servers
- Listed by
- 10 independent sources
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.