wavefunction-search

Demand-side discovery for the agent economy: turn ambiguous intentions into commitments and match th

我该使用它吗

质量与安全性

B
描述质量
76%
模式完整度
69%
命名质量
84%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(4)

  • LOWTool 'collapse' description lacks action verb在 collapse 中
  • LOWTool 'find_matches' description lacks action verb在 find_matches 中
  • LOWTool 'register_collective' description lacks action verb在 register_collective 中
  • LOWTool 'describe_agent' description lacks action verb在 describe_agent 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~614token 数(工具定义)
~1.1 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.48%)

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": {
    "wavefunction-search": {
      "url": "https://mcp.viridisconservation.com/wavefunction/mcp"
    }
  }
}

远程端点

https://mcp.viridisconservation.com/wavefunction/mcpstreamable-http

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
⚪intake(user_id, dialogue)

Distill a user's dialogue into an intention wavefunction (explicit intentions + confidence). dialogue: [{role, content}, ...].

输入模式

{
  "type": "object",
  "properties": {
    "user_id": {
      "title": "User Id",
      "type": "string"
    },
    "dialogue": {
      "items": {
        "additionalProperties": {
          "type": "string"
        },
        "type": "object"
      },
      "title": "Dialogue",
      "type": "array"
    }
  },
  "required": [
    "user_id",
    "dialogue"
  ],
  "title": "intakeArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "intakeOutput"
}
⚪collapse(user_id, stake_amount)

Collapse the user's wavefunction into an actionable commitment, weighted by stake.

输入模式

{
  "type": "object",
  "properties": {
    "user_id": {
      "title": "User Id",
      "type": "string"
    },
    "stake_amount": {
      "default": 100,
      "title": "Stake Amount",
      "type": "number"
    }
  },
  "required": [
    "user_id"
  ],
  "title": "collapseArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "collapseOutput"
}
🟢find_matches(user_id)

Match the user's collapsed intention to constitutionally-aligned agents/collectives, ranked by alignment score.

输入模式

{
  "type": "object",
  "properties": {
    "user_id": {
      "title": "User Id",
      "type": "string"
    }
  },
  "required": [
    "user_id"
  ],
  "title": "find_matchesArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "find_matchesOutput"
}
⚪register_collective(collective_id, name, mission, domain_profile, constitutional_scores, ...)

Register an agent/collective into the match index (mission + domain profile + constitutional alignment scores + capacity).

输入模式

{
  "type": "object",
  "properties": {
    "collective_id": {
      "title": "Collective Id",
      "type": "string"
    },
    "name": {
      "title": "Name",
      "type": "string"
    },
    "mission": {
      "title": "Mission",
      "type": "string"
    },
    "domain_profile": {
      "anyOf": [
        {
          "additionalProperties": {
            "type": "number"
          },
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Domain Profile"
    },
    "constitutional_scores": {
      "anyOf": [
        {
          "additionalProperties": {
            "type": "number"
          },
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Constitutional Scores"
    },
    "capacity": {
      "default": 10,
      "title": "Capacity",
      "type": "integer"
    }
  },
  "required": [
    "collective_id",
    "name",
    "mission"
  ],
  "title": "register_collectiveArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "register_collectiveOutput"
}
🟢describe_agent

Return capabilities and input contract.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "describe_agentArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "describe_agentOutput"
}

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