HumanMirror One

One MCP tool for verified AI-agent outcomes with success-only charging.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
88%
命名质量
80%
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

~338token 数(工具定义)
~4.1 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.26%)

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": {
    "one": {
      "url": "https://humanmirror.fr/api/one/mcp/"
    }
  }
}

远程端点

https://humanmirror.fr/api/one/mcp/streamable-http

它能做什么

工具清单

工具(1)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪humanmirror_do(intent, route_intent, dispatch_only, objective, outcome_type, ...)

One HumanMirror tool for verified outcomes and canonical intent routing. Provide intent to route free to the correct HumanMirror safety, commerce, payment or best-execution boundary. Provide outcome_type/input for a directly verified Outcome; 6 Nexus credits are kept only on verified success.

输入模式

{
  "type": "object",
  "properties": {
    "intent": {
      "type": "string",
      "description": "Optional routing intent, for example sanitize untrusted input, protect an agent purchase, issue execution evidence, use the zero-cost sink, diagnose a payment failure, or request best execution."
    },
    "route_intent": {
      "type": "string",
      "description": "Alias for intent when the caller wants canonical route discovery."
    },
    "dispatch_only": {
      "type": "boolean",
      "description": "When true, resolve the canonical HumanMirror route without charging Nexus credits."
    },
    "objective": {
      "type": "string",
      "description": "Natural-language measurable objective, for example: remove duplicate records and prove none remain."
    },
    "outcome_type": {
      "type": "string",
      "description": "Optional explicit Outcome type: clean_json, deduplicate_records, normalize_entity, data_quality_at_least, detect_anomalies, no_secrets, output_quality, schema_compatible, safe_preflight, execution_receipt."
    },
    "input": {
      "description": "JSON input for the requested result."
    },
    "criteria": {
      "type": "object",
      "description": "Optional measurable success thresholds."
    },
    "options": {
      "type": "object",
      "description": "Optional operation-specific settings."
    },
    "contract_id": {
      "type": "string",
      "description": "Optional Outcome contract ID returned by a dry run."
    },
    "dry_run": {
      "type": "boolean",
      "description": "When true, return a free quote and do not reserve or consume credits."
    }
  },
  "additionalProperties": false
}

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
已验证未记录版本1 个工具