EthersFlow — Trust Gate for AI Agents

Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
98%
命名质量
100%
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

~291token 数(工具定义)
~3.2 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.23%)

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": {
    "ethersflow": {
      "command": "npx",
      "args": [
        "@ethersflow/mcp-server"
      ]
    }
  }
}

可运行的软件包

npm@ethersflow/mcp-server0.2.3stdio

远程端点

https://www.ethersflow.com/api/mcpstreamable-http

它能做什么

工具清单

工具(1)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪verify_agent_action(agent_action, reasoning_chain, context, agent_count, persona_preset, ...)

Gate and verify autonomous AI agent action decisions (e.g. trades, emails, claims, API calls) via EthersFlow Multi-Model Federated Adversarial Consensus before execution.

输入模式

{
  "type": "object",
  "properties": {
    "agent_action": {
      "type": "string",
      "description": "The proposed action the agent intends to take."
    },
    "reasoning_chain": {
      "type": "string",
      "description": "The agent's internal reasoning or context leading to this decision."
    },
    "context": {
      "type": "object",
      "description": "Structured contextual evidence, metadata, or source document references."
    },
    "agent_count": {
      "type": "number",
      "description": "Number of adversarial audit nodes (2 to 7, default 3)."
    },
    "persona_preset": {
      "type": "string",
      "enum": [
        "clinical_safety",
        "financial_compliance",
        "legal_citation",
        "cybersecurity_auditor",
        "general_adversarial"
      ]
    },
    "scope_hint": {
      "type": "string",
      "description": "Optional domain or task scope hint (e.g. 'clinical_safety', 'financial_compliance', 'legal_citation', 'cybersecurity_auditor')."
    },
    "policy_id": {
      "type": "string",
      "description": "Optional policy pack identifier to evaluate against."
    },
    "grounding_enabled": {
      "type": "boolean",
      "description": "Enable hybrid fact grounding verification."
    },
    "zero_retention": {
      "type": "boolean",
      "description": "Enforce zero data retention (ZDR)."
    }
  },
  "required": [
    "agent_action"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本1 个工具
需要认证未记录版本—