io.github.Perf-AI/perf-mcp

编码与调试

by perf-technology

用于核查并修复 AI 输出,支持 hallucination 检测、schema 校验与自动修复,提升结果可信度。

什么是 io.github.Perf-AI/perf-mcp

用于核查并修复 AI 输出,支持 hallucination 检测、schema 校验与自动修复,提升结果可信度。

README

perf-mcp

Fact-check and fix AI outputs. Catches hallucinations, repairs broken JSON, corrects errors — before they reach users.

Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible client.

Quick Start

Add to your MCP client config:

json
{
  "mcpServers": {
    "perf": {
      "command": "npx",
      "args": ["-y", "perf-mcp"],
      "env": {
        "PERF_API_KEY": "pk_live_xxx"
      }
    }
  }
}

Get your API key at dashboard.withperf.pro — 200 free verifications, no credit card.

Tools

perf_verify

Detect and repair hallucinations in LLM-generated text. Uses multi-channel verification (web search, NLI models, cross-reference) — not just another LLM check.

code
perf_verify({ content: "The Eiffel Tower was built in 1887." })
→ Corrected: "built in 1887" → "inaugurated in 1889" (89% confidence)

perf_validate

Validate LLM-generated JSON against a schema and auto-repair violations. Fixes malformed enums, wrong types, missing fields, hallucinated properties.

code
perf_validate({
  content: '{"name": "John", "age": "twenty"}',
  target_schema: { type: "object", properties: { name: { type: "string" }, age: { type: "number" } } }
})
→ Rejected: /age must be number

perf_correct

General-purpose output correction. Classifies the error type and applies the right fix — hallucination, schema violation, semantic inconsistency, or instruction drift.

code
perf_correct({ content: "The Great Wall was built in 1950.", correction_budget: "fast" })
→ Corrected: temporal_error + factual_error detected (87% confidence)

perf_chat

Route LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, and 20+ models based on task complexity. OpenAI-compatible format.

Setup by Client

Claude Code

Add to your project's .mcp.json:

json
{
  "mcpServers": {
    "perf": {
      "command": "npx",
      "args": ["-y", "perf-mcp"],
      "env": {
        "PERF_API_KEY": "pk_live_xxx"
      }
    }
  }
}

Cursor

Settings → MCP → Add Server:

json
{
  "mcpServers": {
    "perf": {
      "command": "npx",
      "args": ["-y", "perf-mcp"],
      "env": {
        "PERF_API_KEY": "pk_live_xxx"
      }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json
{
  "mcpServers": {
    "perf": {
      "command": "npx",
      "args": ["-y", "perf-mcp"],
      "env": {
        "PERF_API_KEY": "pk_live_xxx"
      }
    }
  }
}

Environment Variables

VariableRequiredDescription
PERF_API_KEYYesYour Perf API key (pk_live_xxx)
PERF_BASE_URLNoOverride API URL (for testing)

Pricing

PlanCreditsPrice
Free200 verifications$0 (never expires)
Pro1,000/mo$19/mo
Pay-as-you-goUnlimited$0.02/verification

1 tool call = 1 credit. Get started at dashboard.withperf.pro.

License

MIT

常见问题

io.github.Perf-AI/perf-mcp 是什么?

用于核查并修复 AI 输出,支持 hallucination 检测、schema 校验与自动修复,提升结果可信度。

相关 Skills

网页构建器

by anthropics

Universal
热门

面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。

在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。

编码与调试
未扫描176.4k

网页应用测试

by anthropics

Universal
热门

用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。

借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。

编码与调试
未扫描176.4k

前端设计

by anthropics

Universal
热门

面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。

想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。

编码与调试
未扫描176.4k

相关 MCP Server

GitHub

编辑精选

by GitHub

热门

GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。

这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。

编码与调试
89.7k

by Context7

热门

Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。

它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。

编码与调试
60.2k

by tldraw

热门

tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。

这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。

编码与调试
49.9k

评论