ejentum-mcp
用于 Ejentum API 的 MCP 服务器。在 4 个框架（推理、代码、反欺骗、记忆）中提供 8 种认知操作，支持动态和自适应模式。
MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive modes.
怎么安装
npx -y ejentum-mcp dsh plugin add ejentum-mcp git clone https://github.com/ejentum/ejentum-mcp ~/.claude/skills/ejentum-mcp 简介
ejentum-mcp MCP server that improves LLM reasoning on complex, multi-step, or multi-constraint tasks. Before the agent generates, it calls one of eight tools to retrieve a *cognitive operation*: a structured procedure (numbered steps with the failure pattern to refuse and a falsification test) paired with an executable reasoning topology (a DAG of those steps with decision gates, parallel branches, bounded loops, meta-cognitive exits, and escape paths). The agent reads both layers before producing its response. Eight tools split into two retrieval modes: **Dynamic** (4 tools: reasoning, code, …
推荐参考
信息
- 协议
- MIT
- 语言
- JavaScript
- GitHub 星标
- 16
- 月下载
- 356
- 最近更新
- 2026-06-11
- 创建于
- 2026-05-05
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:punkpeye/awesome-mcp-servers
- 主题标签
- agentic-ai, ai-reliability, anthropic, anti-deception, claude, code-review, cognitive-scaffold, ejentum, llm-tools, mcp, mcp-server, model-context-protocol, reasoning-harness, typescript
同类推荐
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight：会学习的 Agent 长期记忆系统，自动召回/保存、知识页、深度反思与按仓库隔离的记忆银行。
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 官方Firecrawl MCP服务器 - 为Cursor、Claude及任何其他LLM客户端添加强大的网页抓取和搜索功能。
dsh-mnemon
omdsh-dev/dsh-mnemon
由 Mnemon 驱动的 DeepSeek Harness（DSH）跨 Agent、本地优先的持久记忆插件。它可在支持 Mnemon 的 Agent 之间共享长期记忆，并提供运行时记忆、可检索项目档案、语义召回、知识图谱和 Sidebar UI。
get-shit-done
gsd-build/get-shit-done
由 TÂCHES 开发的轻量且强大的元提示、上下文工程和规格驱动开发系统，适用于 Claude Code。