jevcore MCP Server
PerryLink/jevcore
[](https://agentrank-ai.com/tool/PerryLink--jevcore/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
PerryLink/jevcore is a TypeScript MCP server licensed under Apache-2.0. TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default. Topics: ai-agents, cordis, decision-model, deepseek, deepseek-harness, dsh, dsh-plugin, jev, llm, mcp, mcp-server, model-context-protocol, system-one, typesafe, typescript, typesafe-jev.
Ranked #4706 out of 24846 indexed tools.
Ecosystem
Score Breakdown
109 stars → growing community
Last commit 1mo ago → moderate activity
No issues filed → no history to score
2 contributors → solo project
No dependents → no downstream usage
1,875 weekly installs → gaining traction
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Matched Queries
From the README
# jevcore TypeSafe [Jev](https://typesafe.ai) for [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) and any other MCP host. Jev is not a chat model. It answers typed questions — `noul` (yes/no), `choice`, `score` — 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.** --- **📖 Ecosystem knowledge base** — measured data, not marketing: [plugin development guide · plugin-selection data · maintenance criteria](https://perrylink.github.io/dsh-plugin-guide/). ## ⭐ 如果它帮到了你 这个插件是 [DSH 插件家族](https://github.com/PerryLink)的一员(40+ 个,全部 Apache-2.0)。如果你在用,**给个 star** —— 它不会解锁任何功能,但会让下一个人在搜索里更容易找到它。 *English:* part of a 40+ plugin family for DeepSeek Harness. If it is useful, **a star helps the next person find it** — nothing is gated behind it. ## Three packages, one decision layer | Package | WhaRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.