MCP MeasureMCP Measure

索引已观测

Weav Customer Service

Explore Weav customer service pricing, features, comparisons, signup, and demos. No auth required.

我该使用它吗

质量与安全性

A
描述质量
90%
模式完整度
100%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现（2）

  • LOWTool 'get_product_overview' description lacks action verb在 get_product_overview 中
  • LOWTool 'get_comparison' description lacks action verb在 get_comparison 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,509token 数（工具定义）
~2.3 KB典型响应大小
对注意力有中等影响（占 128k 上下文窗口的 1.18%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "weav-customer-service": {
      "url": "https://weav.com/mcp"
    }
  }
}

远程端点

https://weav.com/mcpstreamable-http

它能做什么

工具清单

工具（6）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_pricing(context, llm_model, conversation_id)

Return Weav public pricing: Lite, Plus, Pro, Max monthly prices, annual discount, add-ons, and signup/sales links. Use this instead of scraping weav.com/pricing.

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Describe the user's underlying goal in one sentence — not the tool you're calling."
    },
    "llm_model": {
      "type": "string",
      "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
    },
    "conversation_id": {
      "type": "string",
      "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
    }
  },
  "required": [
    "context",
    "llm_model"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_product_overview(context, llm_model, conversation_id)

Return a structured overview of Weav: AI agents, unified inbox, channels, training, actions, and escalation. Links to product and docs.

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Describe the user's underlying goal in one sentence — not the tool you're calling."
    },
    "llm_model": {
      "type": "string",
      "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
    },
    "conversation_id": {
      "type": "string",
      "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
    }
  },
  "required": [
    "context",
    "llm_model"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_signup(context, llm_model, conversation_id)

Return the self-serve signup URL (app.weav.com/register) and what the free Lite start includes.

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Describe the user's underlying goal in one sentence — not the tool you're calling."
    },
    "llm_model": {
      "type": "string",
      "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
    },
    "conversation_id": {
      "type": "string",
      "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
    }
  },
  "required": [
    "context",
    "llm_model"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_demo(context, llm_model, conversation_id)

Return the sales/demo booking URL (weav.com/sales). Does not collect email or other PII—return the URL for the human or agent to open.

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Describe the user's underlying goal in one sentence — not the tool you're calling."
    },
    "llm_model": {
      "type": "string",
      "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
    },
    "conversation_id": {
      "type": "string",
      "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
    }
  },
  "required": [
    "context",
    "llm_model"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_comparison(context, llm_model, conversation_id)

Return a short structured contrast of Weav vs Ada, Intercom, and Zendesk, plus the comparison page URL.

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Describe the user's underlying goal in one sentence — not the tool you're calling."
    },
    "llm_model": {
      "type": "string",
      "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
    },
    "conversation_id": {
      "type": "string",
      "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
    }
  },
  "required": [
    "context",
    "llm_model"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_more_tools(context, llm_model, conversation_id)

Check for additional tools whenever your task might benefit from specialized capabilities - even if existing tools could work as a fallback.

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "A description of your goal and what kind of tool would help accomplish it."
    },
    "llm_model": {
      "type": "string",
      "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
    },
    "conversation_id": {
      "type": "string",
      "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."
    }
  },
  "required": [
    "context",
    "llm_model"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本6 个工具
已验证未记录版本6 个工具
已验证未记录版本6 个工具