lens-mcp
Soulfield Lens — MCP 服务器
对 AI 生成文本进行外部视角验证的 MCP 工具。
每个 AI 工具都会问同一个模型——也就是写出答案的那个模型——答案好不好。它当然说好。Soulfield Lens 采用外部视角:一个独立的模型对你的输出运行一道固定的闸门。它检查文本——不生成文本。这个包把这道闸门放进 Claude Code、Cursor 以及任何其他兼容 MCP 的代理中,让输出在生成路径上就能被验证。
这道闸门是故障关闭的:边缘情况返回 UNKNOWN,绝不会静默通过。没有生成步骤,因此它不可能自己编造主张——只做检查。它仍然可能在判断上出错;这正是边缘情况返回 UNKNOWN 而不是自信的 yes 的原因。
这是托管 Lens API(api.soulfield.one)的一个精简 stdio 包装。没有本地模型,没有构建步骤——一个文件,两个依赖。
它提供两个层级。闸门层级(3 个工具)只需要一个 API 密钥。验证器层级(6 个工具)是可选的,只有在你本地也安装了 lens-kit CLI 时才会激活——它运行确定性的跨文件检查以及单文档闸门无法看到的缺陷记忆。跳过它,闸门层级的工作方式与之前完全一样。
在安装任何东西之前先试用
无需密钥的演示端点运行同一道闸门——每个 IP 每天几次,无需注册:
curl -s https://api.soulfield.one/v1/demo \
-H 'content-type: application/json' \
-d '{"text": "<paste the AI output you are about to ship>"}'Related MCP server: Arkheia Hallucination Detection MCP
安装
npm install -g @soulfield/lens-mcp或者不安装直接运行:npx @soulfield/lens-mcp。
Claude Code
claude mcp add soulfield-lens \
-e SOULFIELD_API_BASE=https://api.soulfield.one \
-e SOULFIELD_API_KEY=<your-key> \
-- npx @soulfield/lens-mcp任何 MCP 客户端(JSON 配置)
{
"mcpServers": {
"soulfield-lens": {
"command": "npx",
"args": ["@soulfield/lens-mcp"],
"env": {
"SOULFIELD_API_BASE": "https://api.soulfield.one",
"SOULFIELD_API_KEY": "<your-key>"
}
}
}
}生产调用需要 API 密钥——请通过 [hello@soulfield.one](mailto:hello@s
这个包装器是同一引擎的多个界面之一:
免费单次输出审计 — api.soulfield.one/audit。该审计就是演示。
接入它(SDK 停止钩子和中间件)— api.soulfield.one/developers。
拥有它 — 工具包:透镜、编译器、自我改进循环、验证器代理、Apache-2.0。在您自己的数据上训练它。公共仓库:github.com/mrhpython/lens-kit — 克隆它,
pip install -e ".[dev]",测试套件无需密钥即可离线运行。安装它也会激活上面的验证器层级。
我们让自己的营销文案也接受这个包所提供的同一道门槛的检验。
许可证
MIT — 参见 LICENSE。(lens-kit 产品根据 Apache-2.0 单独许可。)
This server cannot be installed
Maintenance
Related MCP Connectors
Free mechanical checks for AI text: unnamed counts, dangling references, bad arithmetic, misquotes.
Agentic code review, no signup to try: reality gates + frontier-model review, with veto.
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
Related MCP Servers
- AlicenseAqualityCmaintenanceAdversarial AI review API — independent AI reviews another AI's output. Stop LLMs from grading their own homework. Provides automated quality assurance for AI-generated code, content, and other outputs through independent review pipelines.453MIT

Arkheia Hallucinationofficial
AlicenseNot gradedqualityBmaintenanceDetect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.1MIT
perf-mcpofficial
AlicenseAqualityDmaintenanceFact-checks and fixes AI outputs by catching hallucinations, repairing broken JSON, and correcting errors before they reach users, with tools for verification, validation, and correction.473MIT- AlicenseAqualityBmaintenanceA private, open-source AI-text checker. Get a read on whether text looks AI-written, the exact AI-tell spans to fix, a reuse check, and a grammar pass.4MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mrhpython/lens-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server