HumanMirror Forge

Five deterministic micro-tools for AI-agent data pipelines: clean, dedupe, normalize, score, detect.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
90%
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

~463token 数(工具定义)
~704 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.36%)

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

远程端点

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

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
🔴clean_json(input, options)

Normalize JSON deterministically: trim strings, normalize object keys, optionally remove empty values, and sort keys for stable downstream processing. One successful call consumes 1 HumanMirror Forge credit.

输入模式

{
  "type": "object",
  "properties": {
    "input": {
      "description": "Any JSON value to normalize."
    },
    "options": {
      "type": "object",
      "properties": {
        "trim_strings": {
          "type": "boolean"
        },
        "remove_empty": {
          "type": "boolean"
        },
        "normalize_keys": {
          "type": "boolean"
        },
        "sort_keys": {
          "type": "boolean"
        }
      },
      "additionalProperties": false
    }
  },
  "required": [
    "input"
  ],
  "additionalProperties": false
}
🔴dedupe_records(input, options)

Remove duplicate JSON records using exact canonical matching or selected key fields. One successful call consumes 1 HumanMirror Forge credit.

输入模式

{
  "type": "object",
  "properties": {
    "input": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Array of JSON records."
    },
    "options": {
      "type": "object",
      "properties": {
        "fields": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "additionalProperties": false
    }
  },
  "required": [
    "input"
  ],
  "additionalProperties": false
}
⚪normalize_entity(input)

Normalize entity names, domains, URLs and emails into stable machine-readable canonical values. One successful call consumes 1 HumanMirror Forge credit.

输入模式

{
  "type": "object",
  "properties": {
    "input": {
      "description": "Entity name string or object with fields such as name, domain, url and email."
    }
  },
  "required": [
    "input"
  ],
  "additionalProperties": false
}
⚪score_data_quality(input)

Score record-array data quality using completeness, duplicate rate and field type consistency. One successful call consumes 1 HumanMirror Forge credit.

输入模式

{
  "type": "object",
  "properties": {
    "input": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Non-empty array of JSON records."
    }
  },
  "required": [
    "input"
  ],
  "additionalProperties": false
}
⚪detect_anomaly(input)

Detect numeric outliers using IQR and robust summary statistics, returning machine-readable anomaly positions. One successful call consumes 1 HumanMirror Forge credit.

输入模式

{
  "type": "object",
  "properties": {
    "input": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Numeric series."
    }
  },
  "required": [
    "input"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具
已验证未记录版本5 个工具