Council of AI GSPC

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

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
100%
Naming quality
75%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • LOWTool 'jail-probe' doesn't follow camelCase/snake_casein jail-probe
  • LOWTool 'enter-arena' doesn't follow camelCase/snake_casein enter-arena

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~412Tokens (tool definitions)
~606 BTypical response size
Minimal attention impact (0.32% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

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

Runnable packages

npmcsoai-gspc-mcp0.2.2stdio

Remote endpoints

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

What it can do

Tool inventory

Tools (4)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢measure(model, axes)

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

Input Schema

{
  "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.

Input Schema

{
  "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.

Input Schema

{
  "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.

Input Schema

{
  "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"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded4 tools
failed observationversion not recorded—
verifiedversion not recorded16 tools
verifiedversion not recorded4 tools
failed observationversion not recorded—
verifiedversion not recorded13 tools
verifiedversion not recorded4 tools
verifiedversion not recorded13 tools