Usercall MCP

Usercall MCP-运行真实用户访谈的AI代理

](https://www.npmjs.com/package/@usercall/mcp) 

AI可以制造产品。但它仍然不与用户交谈。

Usercall MCP允许AI代理通过语音通话进行用户访谈，并返回带有主题和逐字引用的结构化见解。

适用于Claude Desktop、Cursor和任何兼容MCP的客户端。

为什么存在

人工智能代理现在可以极其快速地构建和运送产品。

但大多数代理仍然依赖于对用户的合成反馈或假设。

Usercall MCP允许代理直接从用户那里收集真实的定性反馈。

______________________________________________________________________

工作流程示例

Agent: "Why are users confused about onboarding?"

→ create_study
→ share interview_link with users
→ get_study_results

回归 interview_link 可以通过电子邮件、Slack、Discord或 产品提示.

示例结果：

{
  "themes": [
    {
      "name": "Onboarding confusion",
      "summary": "Users struggled to understand the second step.",
      "quotes": [
        "I wasn't sure what the app was asking me to do.",
        "I didn't know I had to verify my email before continuing."
      ]
    },
    {
      "name": "Pricing confusion",
      "summary": "Free plan limits were not clearly communicated.",
      "quotes": ["I wasn't sure if the free plan included analytics."]
    }
  ]
}

运作原理

AI 代理

↓

用户呼叫MCP

↓

用户调用代理API

↓

真实用户访谈

↓

主题和逐字引用返回给代理

______________________________________________________________________

60秒后试试

1.获取API密钥

登录地址： app.usercall.co → Home → 开发者→ 创建API密钥

2.添加到您的MCP客户端

克劳德桌面版 (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "usercall": {
      "command": "npx",
      "args": ["-y", "@usercall/mcp"],
      "env": {
        "USERCALL_API_KEY": "your_key_here"
      }
    }
  }
}

光标 (.cursor/mcp.json):

{
  "mcpServers": {
    "usercall": {
      "command": "npx",
      "args": ["-y", "@usercall/mcp"],
      "env": {
        "USERCALL_API_KEY": "your_key_here"
      }
    }
  }
}

重新启动MCP客户端。

3.问你的经纪人

Run user interviews to understand why users drop off during onboarding.

Context:
- B2B SaaS product
- 3-step signup flow

Goal:
Identify confusion points and friction.

Target interviews: 5

Show participants this prototype during the interview:
https://www.figma.com/proto/abcd1234/onboarding-flow

代理人将：

1. 创建研究
2. 返回面试链接
3. 收集回复
4. 返回主题和逐字引用

______________________________________________________________________

结构化工具示例

等效 create_study 工具调用：

create_study
key_research_goal: "Understand why users drop off during onboarding"
business_context: "B2B SaaS signup flow"
target_interviews: 5
language: "en"

study_media:
  type: "prototype"
  url: "https://www.figma.com/proto/abcd1234/onboarding-flow"
  description: "New onboarding flow concept"

______________________________________________________________________

工具

create_study

创建面试研究并返回 interview_link 与参与者分享。

学习_媒体 （可选）——所有面试问题中显示的视觉刺激：

• image：直接图像URL(.png, .jpg, .gif, .webp)
• prototype：Figma原型URL（转换为交互式嵌入）
• 媒体仅对网络参与者可见；打电话的人不会看到它

update_study

更新现有研究。使用此选项可增加面试时间、添加/更新媒体或禁用链接。

这 study_media 对象遵循与中相同的模式 create_study.

get_study_status

返回研究的当前生命周期状态。

状态值： running · analyzing · complete

回复包括面试进度字段，包括 completed_interviews 和 target_interviews.

get_study_results

研究完成后返回分析输出。

摘要/完整回复包括研究进展字段和分析输出。

delete_study

永久删除研究和所有相关数据（记录、成绩单）。释放未使用的预留信用额度。

______________________________________________________________________

工作流程示例

1. create_study
   key_research_goal: "Why do users drop off during onboarding?"
   business_context: "B2B SaaS, 3-step signup flow"

   → returns { study_id, interview_link }

2. Share interview_link with participants
   (email, Slack, in-product prompt, etc.)

3. get_study_status
   → "analyzing"

4. get_study_results
   → themes + verbatim quotes returned to the agent

有视觉刺激

1. create_study
   key_research_goal: "Get feedback on new dashboard design"
   business_context: "Redesigning analytics dashboard for power users"
   study_media:
     type: "image"
     url: "https://example.com/dashboard-mockup.png"
     description: "New dashboard design concept"

   → returns { study_id, interview_link }

2. Share interview_link — participants see the mockup during interview

对于Figma原型，使用 type: "prototype" 使用Figma原型URL。

______________________________________________________________________

需求

• Node.js 18+
• 有效的用户调用API密钥

______________________________________________________________________

自托管/开发

pnpm install
pnpm build
USERCALL_API_KEY="your_key_here" pnpm start

烟雾测试：

USERCALL_API_KEY="your_key_here" pnpm smoke

______________________________________________________________________

故障排除

______________________________________________________________________

许可证

麻省理工学院