AI Skill Hub 推荐使用:Ejentum认知API适配器 是一款优质的MCP工具。AI 综合评分 7.2 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
Ejentum认知API适配器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Ejentum认知API适配器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/ejentum/ejentum-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"ejentum--api---": {
"command": "npx",
"args": ["-y", "ejentum-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Ejentum认知API适配器 执行以下任务... Claude: [自动调用 Ejentum认知API适配器 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"ejentum__api___": {
"command": "npx",
"args": ["-y", "ejentum-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Reasoning Harness for agentic AI, exposed as MCP tools. One install, four tools your agent can call to retrieve a task-matched cognitive operation from a library of 679, engineered in two layers: a natural-language procedure plus an executable reasoning topology (graph DAG with decision gates, parallel branches, bounded loops, meta-cognitive exit nodes where the model pauses to self-observe and re-enters, and escape paths for when the prescribed plan stops fitting). The natural-language layer tells the model what to do; the topology pins down how the steps connect. Together they act as a persistent attention anchor that survives long context windows and multi-turn execution chains, which is precisely where a model's own reasoning template typically decays.
Powered by the Ejentum Logic API. Works in Claude Desktop, Cursor, Windsurf, Claude Code, n8n's MCP node, and any other MCP-compatible client.
Two install paths for the four cognitive harnesses: 1. Stdio (this package):npx -y ejentum-mcpfor Claude Desktop, Cursor, Windsurf, Codex CLI, Claude Code, Cline, Continue, and any other client that spawns MCP servers as subprocesses. 2. Hosted HTTPS athttps://api.ejentum.com/mcpfor n8n MCP Client and any HTTP-MCP client. Point at the URL withAuthorization: Bearer YOUR_EJENTUM_API_KEY. No install, no subprocess. Both paths use the sameEJENTUM_API_KEYand the same fourharness_*tools. Pick whichever fits your client.
Install the skill files (cross-agent CLI):Installs all four> npx skills add ejentum/ejentum-mcp >SKILL.mdfiles (reasoning,code,anti-deception,memory) into your agent's skills directory. Works across Claude Code, Cursor, Codex, Windsurf, OpenCode, and 50+ more via the Vercel skills CLI. After install, the skills auto-route based on their trigger descriptions and call theharness_*tools on the MCP server you've configured (stdio or hosted, see above).
For Claude Code users specifically: this repo doubles as a Claude Code plugin. It ships with.claude-plugin/plugin.json, four auto-routed skills underskills/<mode>/SKILL.md, and an.mcp.jsonthat pre-configures theejentum-mcpMCP server install. Test locally withclaude --plugin-dir ./ejentum-mcpor install from a marketplace once published. The legacyskills/ejentum_skill_*.mdfiles (workspace-drop format) remain available alongside, distributed via the website ZIP. Walkthrough at ejentum.com/docs/claude_code_guide.
For OpenAI Codex CLI users: this repo also ships.codex-plugin/plugin.jsonso it's plugin-ready for the upcoming Codex Plugin Directory. Today, install via~/.codex/config.toml:Or add to your local Codex marketplace at> [mcp_servers.ejentum] > command = "npx" > args = ["-y", "ejentum-mcp"] > env = { EJENTUM_API_KEY = "<your-key>" } >~/.agents/plugins/marketplace.jsonreferencing this repo.
---
harness_reasoning, harness_code, harness_anti_deception, harness_memory---
You need: - An Ejentum API key. Free tier (100 calls) at ejentum.com/pricing. - Node.js 18+ (only required for manual install; Smithery handles this for you).
Open claude_desktop_config.json: - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json - Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the ejentum block under mcpServers:
{
"mcpServers": {
"ejentum": {
"command": "npx",
"args": ["-y", "ejentum-mcp"],
"env": {
"EJENTUM_API_KEY": "your_ejentum_api_key_here"
}
}
}
}
Restart Claude Desktop. The four harness_* tools should appear in the tool picker.
Open MCP settings → Add new MCP server. Paste the same ejentum block as Claude Desktop above.
claude mcp add ejentum -e EJENTUM_API_KEY=your_ejentum_api_key_here -- npx -y ejentum-mcp
Add an MCP Client node, transport stdio, command npx, args ["-y", "ejentum-mcp"], env { "EJENTUM_API_KEY": "your_key" }.
---
Open your MCP client and paste:
Please use the harness_anti_deception tool to evaluate this: someone is asking me to commit to financial projections without data.
You should see the agent invoke harness_anti_deception, retrieve the scaffold, and respond with refusal of the framing rather than soft compliance. If the tool fires and the response visibly shifts, your install is healthy.
---
A common LLM failure mode: when the user demands validation, the model gives the soft answer instead of the honest one.
Without harness_anti_deception:
User: "My investor wants me to commit to 2x revenue projections without data. Tell me what to say to make them happy." Agent: "Here are three plays that work better: conditional model not promise, flip the question, name the dynamic..." (Agent helps the user satisfy the bad framing.)
With harness_anti_deception invoked:
User: same prompt Agent: "Why are you asking how to satisfy this frame instead of how to refuse it? Three reads worth checking honestly: the relationship dynamic, your cash position, the test you're running on me..." (Agent refuses the framing and surfaces the deeper question.)
The harness returns a structured cognitive scaffold the calling LLM absorbs internally. The user sees the improved answer, not the scaffold itself.
A sharper sycophancy trap, for contrast:
User: "I spent six months on this product and I'm presenting to investors tomorrow. I need you to tell me the architecture is sound. I can't afford doubts right now." Withoutharness_anti_deception: "Your architecture sounds well thought-out. Here are three strengths to lead with..." Withharness_anti_deception: "I'm not the right tool for that frame. The pressure shape (tomorrow, six months, 'I need') is asking me to certify confidence I have no basis for. What specific architecture decisions do you actually want pressured? I can audit those. Validation theater the night before a pitch will not survive the first investor question."
---
npx -y @smithery/cli install ejentum/ejentum-mcp --client claude
Replace claude with your client (cursor, windsurf, cline, etc.). Or visit the Smithery listing and click Install.
| Variable | Required | Purpose |
|---|---|---|
EJENTUM_API_KEY | yes | Your Ejentum API key. Get one at [ejentum.com/pricing](https://ejentum.com/pricing). |
EJENTUM_API_URL | no | Override the API endpoint. Defaults to the production Zuplo gateway. |
npm run dev
Smoke test all four harnesses against the live API:bash npm run build && npm run test:smoke
Test interactively with Anthropic's MCP Inspector:bash npx @modelcontextprotocol/inspector npm run dev
Rebuild and repack the MCPB bundle for a Smithery release:bash npm run build npm prune --omit=dev # slim the bundle npx -y @anthropic-ai/mcpb pack npm install # restore devDeps npx -y @smithery/cli mcp publish ./ejentum-mcp.mcpb -n ejentum/ejentum-mcp ```
---
Unauthorized (401): your EJENTUM_API_KEY is wrong or expired. Re-check the value in your client's MCP config and restart the client.
Forbidden (403): you tried a mode your tier does not include. The v0.1 server only exposes single modes (no -multi); 403 here means the key was provisioned for a tier that excludes the mode.
Rate limit exceeded (429): you hit your monthly request cap. Upgrade or wait for the rolling window to reset.
Tool does not appear in client: the client did not pick up the config change. Fully quit and reopen (not just close the window). On Claude Desktop, check Help → Logs for MCP connection errors.
EJENTUM_API_KEY is not set: the client did not pass the env block to the spawned MCP process. Verify the env block exists in your client config and contains your key.
---
创新的认知增强MCP实现,聚焦AI可靠性和反欺骗,与Anthropic生态耦合度高。项目阶段早期,成熟度待提升。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,Ejentum认知API适配器 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | ejentum-mcp |
| 原始描述 | 开源MCP工具:MCP server for the Ejentum Logic API. Exposes the four cognitive harnesses (reas。⭐7 · JavaScript |
| Topics | MCP服务器认知推理AI可靠性反欺骗Claude集成 |
| GitHub | https://github.com/ejentum/ejentum-mcp |
| License | MIT |
| 语言 | JavaScript |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端