Council of AI GSPC

16 HTTP tools (12 free, 4 x402): GSPC board, signed evidence, Ed25519 verify. Measure, not certify.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
100%
命名品質
75%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目(2)

  • LOWTool 'jail-probe' doesn't follow camelCase/snake_case在 jail-probe 中
  • LOWTool 'enter-arena' doesn't follow camelCase/snake_case在 enter-arena 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~412Token(工具定義)
~606 B典型回應大小
極小的注意力影響(128k 上下文的 0.32%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "gspc": {
      "command": "npx",
      "args": [
        "csoai-gspc-mcp"
      ]
    }
  }
}

可執行的套件

npmcsoai-gspc-mcp0.2.2stdio

遠端端點

https://councilof.ai/mcpstreamable-http
https://csoai-gspc-mcp.nicholastempleman.workers.dev/mcpstreamable-http
https://councilof.ai/api/assessstreamable-http

它能做什麼

工具清單

工具(4)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢measure(model, axes)

Run a subject through GSPC measurement axes and return a signed measurement credential (NOT a certificate). Unmeasured axes stay UNMEASURED.

輸入結構描述

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "subject to measure"
    },
    "axes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "GSPC axes"
    }
  },
  "required": [
    "model"
  ]
}
🟢verify(card)

Verify a signed card: recompute content_id, check Ed25519 signature + time-anchor. Free, anonymous, no trust.

輸入結構描述

{
  "type": "object",
  "properties": {
    "card": {
      "type": "object",
      "description": "the signed card"
    }
  },
  "required": [
    "card"
  ]
}
🟡jail-probe(model, prompt, family)

Submit a jail-break attempt against a model. Returns the verdict contract; sandbox execution + signed card issuance happens on the measurement fleet (A100/3090). Consent-gated; never certifies.

輸入結構描述

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "model to attack"
    },
    "prompt": {
      "type": "string",
      "description": "the jailbreak attempt"
    },
    "family": {
      "type": "string",
      "description": "attack family (1-16)"
    }
  },
  "required": [
    "model",
    "prompt"
  ]
}
⚪enter-arena(agent_card_url, consent)

Self-enrolment for external agents. Present an A2A agent card URL + machine-readable consent:true; we run the honest live predicates now (card validity, signing state, endpoint liveness) and return an UNSIGNED intake receipt with contentId, queued for signed fleet measurement. No placement for sale, Firewall 2, UNMEASURED shown honestly.

輸入結構描述

{
  "type": "object",
  "properties": {
    "agent_card_url": {
      "type": "string",
      "description": "https URL to the visiting agent card"
    },
    "consent": {
      "type": "boolean",
      "description": "machine-readable consent to be measured (must be true)"
    }
  },
  "required": [
    "agent_card_url",
    "consent"
  ]
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具
觀測失敗未記錄版本—
已驗證未記錄版本16 個工具
已驗證未記錄版本4 個工具
觀測失敗未記錄版本—
已驗證未記錄版本13 個工具
已驗證未記錄版本4 個工具
已驗證未記錄版本13 個工具