compliance-evidence

Dated, signed compliance-evidence packs: gov-fact-grounded claims + exclusion screens + trap-facts.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
82%
命名质量
90%
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

~501token 数(工具定义)
~557 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.39%)

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": {
    "compliance-evidence": {
      "url": "https://evidence.dropwatchhq.com/mcp"
    }
  }
}

远程端点

https://evidence.dropwatchhq.com/mcpstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪build_evidence_pack(tickers, entities, traps)

Build a dated, source-linked, SIGNED compliance-evidence pack for a regulated-AI deployer to file with their auditor. Grounds each ticker's claims against CURRENT public gov facts (contradiction-engine: SEC 10-K vs USAspending), screens each named entity against federal exclusion/sanctions (exclude-feed: OFAC/LEIE/SAM), and runs N trap-fact refusals (planted false facts refuted by live public data). Output is an EVIDENCE ARTIFACT with a hash-chain receipt — NOT a 'you are compliant' claim.

输入模式

{
  "type": "object",
  "properties": {
    "tickers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Public-company tickers whose disclosure claims to ground (max 10)."
    },
    "entities": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Named entities to screen: [{name, npi?, uei?, state?}] (max 20)."
    },
    "traps": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Optional custom trap-fact battery; omit to use the default battery."
    }
  }
}
⚪ground_claim(ticker)

Ground one public-company claim against CURRENT gov facts via the live contradiction-engine. Returns the dual-cited record if a verifiable 10-K-vs-USAspending contradiction exists, else an HONEST null ('checked, no contradiction at medium/high confidence as of T') — itself audit evidence.

输入模式

{
  "type": "object",
  "properties": {
    "ticker": {
      "type": "string"
    }
  },
  "required": [
    "ticker"
  ]
}
⚪screen_entity(name, npi, uei, state)

Screen a named entity across federal exclusion/sanctions lists (OFAC SDN, OFAC Consolidated, OIG LEIE; SAM where enabled) via the live exclude-feed. FCRA-safe KYB/sanctions screen, not a consumer report.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "npi": {
      "type": "string"
    },
    "uei": {
      "type": "string"
    },
    "state": {
      "type": "string"
    }
  },
  "required": [
    "name"
  ]
}
⚪verify_pack(id)

Verify a previously-issued pack's hash-chain receipt (proves the artifact is unaltered since generatedAt). Pass the pack id.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具
已验证未记录版本4 个工具
已验证未记录版本4 个工具