What does jev-scout do?

An MCP stdio server exposing guarded_search, guarded_fetch and research_report. Every query, search result and fetched page is scored by Jev, and the decisions stay observable in a ledger and dashboard.

How does it use Jev per research step?

One Jev call judges each result for relevance, credibility and worth-fetching; another judges each fetched page for answered, content class and steering risk. The README cites per-decision cost around $0.0001 and 70-500 ms latency.

What do I need to run jev-scout?

Node, a Jev key, a search backend (SearXNG via Docker is the default and needs a JSON-format settings change) and the sibling jev-client repository cloned beside it, since jev-scout consumes it as a file: dependency.

Is jev-scout a research agent?

No. The README is explicit that there is no multi-hop planning, synthesis or answer-writing; it is a decision layer that annotates or optionally gates what an agent sees during research.

What does the dashboard show?

A live decision feed grouped by search with confidence and an explicit unscored badge when Jev could not be reached, a running cost/call ticker, and a per-domain credibility table.

How accurate are the Jev judgments?

The first live checkpoint reported relevance 88% and credibility 96% against a hand-labeled golden set, with methodology and caveats in the accuracy doc. It is one checkpoint, not an ongoing guarantee.

Jev directory

CommunityJev Agents & MCP

Jev Scout — kierandotai

An MCP stdio server that judges every research step: guarded_search, guarded_fetch and research_report score each query, result and fetched page with Jev for relevance, credibility and steering risk, with budgets, SSRF-guarded fetching and a live SSE dashboard.

See highlights Open github.com

Stars: 3
Language: TypeScript
Reading time: 2 min
Published by: Community
Author: kierandotai
Last verified: Oct 2026

kierandotai/jev-scout

User repository on GitHub

View on GitHub

Jev-scored observable web research for MCP agents — every query, result, and fetched page judged for relevance and credibility, with budgets, SSRF-guarded fetching, and a live dashboard

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity catalog-import cobanov mcp web-research

Works forJev for Verification Jev for Ranking Jev for Decision gating

Used inJev for Software & DevTools

Languages: TypeScript
Platforms: MCP
Capabilities: Open sourceRuns locallyRequires API key

Highlights

Judges every step: one Jev call per result for relevance, credibility and worth-fetching, and one per page for answered, content class and steering risk.
Decisions stream to a JSONL ledger and an SSE dashboard with a live decision feed, a cost/call ticker and a per-domain credibility table.
Rubrics validated on a hand-labeled golden set: relevance 88% and credibility 96% at the first live checkpoint, with miss analysis in docs/accuracy.
Not a research agent: no multi-hop planning, synthesis or answer-writing, just a thin decision layer that annotates or gates what an agent sees.
Consumes jev-client as a file: dependency for OpenRouter/TypeSafe wiring, defaulting to a local SearXNG backend that needs a JSON-format settings change.

Quickstart

bash

claude mcp add --scope project --transport stdio jev-scout -- node --experimental-strip-types /ABS/PATH/jev-scout/src/server-mcp.ts

Watch out

Grounded on the truncated README and GitHub metadata reviewed 2026-10-15; no repository license is listed and the README is cut mid-section. The accuracy figures come from the project's own first live checkpoint, and coverage is voluntary unless you deny an agent's built-in WebSearch and WebFetch tools.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Jev in front of the HeyGen MCP

X: Playwright CLI + Jev vs Playwright MCP

X: A local MCP server that cuts computer use from 23s to 0.8s. Cartwright built Cortex, a local MCP server where…

X: A side panel that drives any site's WebMCP tools

Other listings of this project

Forks and copies of this project in the directory. This entry is the canonical one.

jev-scout

A Rust CLI and stdio MCP server that grounds repository and crate discovery in live GitHub and crates.io metadata, then lets Jev score candidates so only verified, installable packages are returned.

Jev Tools & CLIs#community#rust#cli

Community

AkashPriyadarshii/jev-scoutRust

From the Jev guides

Original write-ups on what this entry is for.

MCP tool routing: Jev in front of the tool call

Oct 16, 2026

Tool menus can outgrow the context that reads them. The catalog's Jev-based routers and gates narrow the list: benchmarked tool search, per-tool scoring, fail-closed approvals, and WebMCP in the browser.

Jev Agents & MCP#mcp#tool-routing#agents

Read article

Approval policies for coding agents: hooks, guards, and gateways

Oct 16, 2026

How the Jev guard family turns coding-agent permissions into auto-approve, deny, or ask: hooks that enforce, guards that fail safe, and gateways that gate generation.

Jev Agents & MCP#coding-agents#guardrails#hooks