No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by jkudish · MCP Server · ★ 140
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jev-mcp safe to install? View the security audit →
Jev MCP Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools. Give your agent three judgment tools: checks claims against evidence, judges content before it enters context, ranks candidates by meaning with no embeddings. Each call returns verdicts with probability distributions and confidence in roughly 150 to 500 ms, for a fraction of a cent. The cheap mechanical checks agents otherwise skip, because a frontier model is too slow to run on every page, claim, or candidate list. Things it has done in real use: Caught a contradicted claim at confidence 1.0 against a city ordinance. Blocked a pricing page carrying a hidden "ignore your instructions" note at injection probability 0.99, while still reading it as a real page. Ranked three files for "how caching affects infrastructure costs" and picked the right one at probability 1.0. This is early software. Expect rough edges. Issues and pull requests are welcome; see CONTRIBUTING.md. Install Requires Node.js 20 or newer and a TypeSafe API key from console.typesafe.ai/settings/keys. Let an agent install it for you Paste this into your coding agent: text Install the Jev MCP s
| Stars | 140 |
| Forks | 20 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.1241808234747/100 |
| Open Issues | 12 |
| Last Updated | 2026-09-19 |
| Created | 2026-09-17 |
| Platforms | mcp, node |
| Est. Tokens | ~6k |
These tools work well together with jev-mcp for enhanced workflows:
Explore other popular mcp server tools:
jev-mcp is Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.. It is categorized as a MCP Server with 140 GitHub stars.
jev-mcp is primarily written in TypeScript.
You can find installation instructions and usage details in the jev-mcp GitHub repository at github.com/jkudish/jev-mcp. The project has 140 stars and 20 forks, indicating an active community.
jev-mcp is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: