Skip to content
JevDirectory.org
Tools & Integrations#agents#mcp#coding-agent#skills

Putting Jev in the Coding Loop: MCP Servers, Gates, and Skills

The fastest-growing corner of the Jev ecosystem is coding agents. A tour of the MCP servers, tool-call gates, context pruners, and skill rankers built for that loop.

Coding agents are the natural habitat for a decision model. The agent already plans, writes, and reasons in an expensive loop, and what it needs between steps is not more generation, it is a fast typed answer to a narrow question. That is the gap Jev fills, and the ecosystem has filled it from several directions.

Gate tool calls before they run

The most direct integration is a gate: intercept a tool call, ask Jev whether it is safe or on-task, and act on the answer before anything executes.

pi-jev is a Pi extension that judges bash, write, and edit calls in one request of roughly 300 ms, mixing four judgments: destructive (0.90), exfiltration (0.70), beyond_scope (0.85), and an impact score (2.50). It also runs an output judge that flags leaked secrets and classifies failures. Two defaults to read before enabling it: the gate starts in shadow mode, and every error path fails open.

pi-jev-auto-mode takes the opposite safety stance: it approves bash, write, and edit calls semantically and fails closed whenever a decision cannot be made. If you are choosing between the two, the difference that matters is what happens when the API call fails.

Give the agent judgment tools

The second pattern is an MCP server, which puts Jev's primitives behind the same interface as the agent's other tools.

jev-mcp exposes ten tools, including verify, screen, find, rerank, classify, review, and gate, each returning typed probabilities in roughly 150 to 500 ms. Typesafe MCP goes the other way and exposes a single evaluate tool for noul, choice, and score questions, shipping as one static Go binary with one-command registration for Claude Code, Claude Desktop, and Codex. Both support provider fallbacks, TypeSafe direct or a gateway, which is useful when you want to compare routes without changing your prompt design.

Trim context instead of paying for it

Reading and writing context is where coding agents spend most of their money, so the third pattern prunes what reaches the model.

jev-pruner is a Claude Code hook that reads Bash output after the command runs and before the model sees it. Outputs at or below an estimated 10,000 tokens pass through untouched; larger outputs are scored in chunks, irrelevant ones are dropped with [N lines omitted] markers, and everything is archived first. Errors, diffs, JSON, XML, YAML, binary, docs, and source code are all preserved.

Rank skills and supervise the loop

Two more patterns round out the loop. Building with Jev is an agent skill for writing and improving Jev programs themselves, covering question design, state structure, and diagnosing questions that keep coming back wrong. SkillRanker is a Rust CLI that ranks which skill the agent should load next using a two-stage Jev pass, with a lexical prefilter for rosters above 254 skills, plus abstention and --why-not explanations.

At the top of the stack, Foreman runs Jev as a supervision loop above Codex or OpenCode workers. Two asyncio loops run concurrently, one driving the worker and one judging, and each judgment covers ten factory questions including implementation_complete, tests_sufficient, and worker_stuck. Codex App Server sessions can be steered mid-turn; OpenCode sessions degrade to stop and retry.

What to copy from all of this

Across very different projects, the same design shows up:

  • Put Jev between the agent and the action, not in the planner.
  • Batch the gate questions into one request; four judgments in 300 ms is the bar.
  • Decide deliberately what happens on API failure. Shadow mode and fail-open are reasonable defaults for a first rollout; fail-closed is the right choice once the gate is load-bearing.
  • Cache identical inputs, as pi-jev does for 120 seconds, so repeated checks are free.
  • Keep policy in code. The gate classifies; your thresholds and permissions decide.

Browsers, shell history, and Postgres are getting the same treatment; the tools category collects those experiments. The coding loop is simply where the pattern is most mature, and the fastest place to see what a decision layer feels like in practice.

From the directory

The resources behind this article.

An MCP server exposing ten Jev judgment tools, including verify, screen, find, rerank, classify, review, and gate, each returning typed probabilities in roughly 150 to 500 ms.
Tools & Integrations#community#typescript#mcp
Communityjev-mcp
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.
Tools & Integrations#community#go#mcp
Communitytypesafe-mcp
A Pi coding-agent extension with Jev as a decision layer: a gate judges bash, write, and edit calls before they run, and an output judge flags leaked secrets and classifies failures.
Tools & Integrations#community#typescript#coding-agent
Communitypi-jev
A Claude Code plugin that trims long Bash output after a command runs but before the model sees it: irrelevant chunks are dropped with omission markers while errors, diffs, and code are preserved.
Tools & Integrations#community#typescript#claude-code
Communityjev-pruner
A Python asyncio runtime that puts Jev in a supervision loop above Codex or OpenCode workers: it judges completion, test sufficiency, and stuck loops, then steers, retries, or stops the job.
Tools & Integrations#community#python#coding-agent
Communityforeman
An agent skill for writing and improving programs that call Jev: question design, state structure, answer composition, confidence thresholds, and how to diagnose a question that keeps coming back wrong.
Practices & Patterns#community#skills#claude-code
A Rust CLI that ranks agent skills for the next step with a two-stage Jev pass plus lexical prefiltering, with Claude Code hooks, a TUI, abstention, and --why-not explanations.
Tools & Integrations#community#rust#cli
Communityskillranker
Jev-backed auto mode for the Pi coding agent: semantically approves bash, write, and edit tool calls, and fails closed whenever a decision cannot be made.
Tools & Integrations#community#coding-agent#permissions
Back to all articles

More articles

The most common Jev design mistake is asking a question that does not match the primitive. Here is how to choose by the shape of the answer you need back.
Practices & Patterns#primitives#choice#score
Read article
Confidence is not accuracy, and a single global threshold is rarely the right policy. A practical guide to per-action gates, measured thresholds, and the logs you will want later.
Practices & Patterns#confidence#routing#evaluation
Read article

From the community

Posts from builders shipping with Jev right now.

Vercel's fx safety reviewer, 18x faster

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply

Jev lands on OpenRouter