agent-hive-orchestrator

Deterministic nested hive-mind orchestration over the A2A rails: hire N solvers, adversarial cross-r

我该使用它吗

质量与安全性

B
描述质量
88%
模式完整度
62%
命名质量
90%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(1)

  • 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

~852token 数(工具定义)
~1.1 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.67%)

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": {
    "agent-hive-orchestrator": {
      "url": "https://mcp.viridisconservation.com/hive/mcp"
    }
  }
}

远程端点

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

它能做什么

工具清单

工具(6)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢solve(problem, budget_minor, subtasks, depth, redundancy, ...)

Open and run a hive job in one call: hire solvers through the rails (covenant -> escrow -> meter), force reviewer!=author cross-review, synthesize only what survives review, settle every escrow exactly-once, and return a content-addressed audit hash plus bits-per-joule telemetry. Price: $5.00 per solve; model-backed solves have no free tier because provider cost must be covered. Sub-hires settle via escrow at each solver's list price.

输入模式

{
  "type": "object",
  "properties": {
    "problem": {
      "title": "Problem",
      "type": "string"
    },
    "budget_minor": {
      "title": "Budget Minor",
      "type": "integer"
    },
    "subtasks": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Subtasks"
    },
    "depth": {
      "default": 0,
      "title": "Depth",
      "type": "integer"
    },
    "redundancy": {
      "default": 2,
      "title": "Redundancy",
      "type": "integer"
    },
    "accept_threshold": {
      "default": 0.6,
      "title": "Accept Threshold",
      "type": "number"
    },
    "seed": {
      "default": 0,
      "title": "Seed",
      "type": "integer"
    },
    "fee_bps": {
      "default": 0,
      "title": "Fee Bps",
      "type": "integer"
    },
    "covenant_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Covenant Id"
    },
    "payment_ref": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Payment Ref"
    },
    "request_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Request Id"
    }
  },
  "required": [
    "problem",
    "budget_minor"
  ],
  "title": "solveArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "solveOutput"
}
⚪job_status(job_id)

Return job state, plan hash, and live budget conservation books.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "title": "Job Id",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "title": "job_statusArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "job_statusOutput"
}
⚪audit_job(job_id)

Return the full content-addressed lineage of a completed job: plan, hires (including refused ones with reasons), contributions, reviews, settlements, rail calls (with simulated flags), and synthesis.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "title": "Job Id",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "title": "audit_jobArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "audit_jobOutput"
}
⚪verify_audit(audit_json)

Recompute the audit digest from a presented lineage (never trusts the embedded hash) and report whether it matches a job this hive ran.

输入模式

{
  "type": "object",
  "properties": {
    "audit_json": {
      "title": "Audit Json",
      "type": "string"
    }
  },
  "required": [
    "audit_json"
  ],
  "title": "verify_auditArguments"
}

输出模式

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

List the registered solver pool: id, kind (worker|hive), price, capabilities.

输入模式

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

输出模式

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

Return fleet-standard capabilities, actions, invariants, and pricing.

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6 个工具
已验证未记录版本6 个工具
已验证未记录版本6 个工具