Verbaterm Policy Intelligence

Judged, citation-checked policy corpus over MCP. Keyless public reads; API key for AI tools.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
80%
命名质量
97%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~613token 数(工具定义)
~548 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.48%)

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": {
    "verbaterm": {
      "url": "https://verbaterm.com/mcp"
    }
  }
}

远程端点

https://verbaterm.com/mcpstreamable-http

它能做什么

工具清单

工具(7)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_policies(q, category, limit)

Search Verbaterm's judged, citation-checked public policy corpus (companies, products, policy kinds). Returns derived review metadata — findings counts, scores, freshness — never raw policy text.

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Company or product name to search."
    },
    "category": {
      "type": "string",
      "description": "Optional audience category slug."
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 20, max 50)."
    }
  }
}
🟢list_policies

List published public-library policy reviews available in the corpus.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢get_policy_review(companySlug, productSlug, policyKind)

Get the full judged review for one published policy: findings with verbatim citation excerpts, scores, summary, and provenance. Cite the source URLs back to the user.

输入模式

{
  "type": "object",
  "properties": {
    "companySlug": {
      "type": "string"
    },
    "productSlug": {
      "type": "string"
    },
    "policyKind": {
      "type": "string",
      "description": "terms, privacy, cookies, data_processing, or other."
    }
  },
  "required": [
    "companySlug",
    "productSlug",
    "policyKind"
  ]
}
🟢start_private_review(policyText, documentTitle, policyKind)

Start a private Verbaterm review of pasted policy text (requires a Verbaterm API key; debits the caller's plan allowance, not API credits). Returns a sessionId to poll with get_private_review_progress.

输入模式

{
  "type": "object",
  "properties": {
    "policyText": {
      "type": "string",
      "description": "Full pasted policy text (min 80 chars)."
    },
    "documentTitle": {
      "type": "string"
    },
    "policyKind": {
      "type": "string",
      "description": "terms, privacy, cookies, data_processing, other, or auto."
    }
  },
  "required": [
    "policyText"
  ]
}
🟢get_private_review_progress(sessionId)

Poll progress of a private review started with start_private_review.

输入模式

{
  "type": "object",
  "properties": {
    "sessionId": {
      "type": "string"
    }
  },
  "required": [
    "sessionId"
  ]
}
🟢get_private_review_result(sessionId)

Get the completed private review (findings + citations) for a session started with start_private_review. Raw source text is not returned.

输入模式

{
  "type": "object",
  "properties": {
    "sessionId": {
      "type": "string"
    }
  },
  "required": [
    "sessionId"
  ]
}
⚪ask_question(question, reviewRef)

Ask a citation-grounded follow-up question about a public library review or a private session (requires a Verbaterm API key; debits the caller's plan Q&A allowance).

输入模式

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "description": "3–1000 characters."
    },
    "reviewRef": {
      "type": "object",
      "description": "{ kind: \"public_path\", companySlug, productSlug, policyKind } or { kind: \"private\", sessionId }."
    }
  },
  "required": [
    "question",
    "reviewRef"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本7 个工具
已验证未记录版本7 个工具