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 PerryLink · MCP Server · ★ 102
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jevcore safe to install? View the security audit →
jevcore TypeSafe Jev for DeepSeek Harness and any other MCP host. Jev is not a chat model. It answers typed questions — (yes/no), , — and returns calibrated probabilities. It does not write prose, and asking it to is a category error. This project gives an agent exactly that surface, and nothing more. Offline by default. Egress disclosed. Nothing default-on. Three packages, one decision layer The adapters are thin on purpose. is four files: it d
| Stars | 102 |
| Forks | 0 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 65.7130340016689/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-24 |
| Created | 2026-09-20 |
| Platforms | mcp, node |
| Est. Tokens | ~19k |
Looking for a jevcore alternative? If you're comparing jevcore with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Composable mathematics tools for agents
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API e
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into sea
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher
Explore other popular mcp server tools:
jevcore is TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.. It is categorized as a MCP Server with 102 GitHub stars.
jevcore is primarily written in TypeScript. It covers topics such as ai-agents, cordis, decision-model.
You can find installation instructions and usage details in the jevcore GitHub repository at github.com/PerryLink/jevcore. The project has 102 stars and 0 forks, indicating an active community.
jevcore is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to jevcore on Agent Skills Hub include jacobian, memtrace-public, awesome-jev-use-cases. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: