← Index

io.github.nqzai/kakunin

io.github.nqzai/kakunin·v0.1.1·Monitoring & Logs
Quality Score
80
/100

X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.

§00  Trust verdict · v1 advisory ·  method
UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01  Install
Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "kakunin": {
      "command": "npx",
      "args": [
        "-y",
        "@kakunin/mcp"
      ],
      "env": {
        "KAKUNIN_API_KEY": "<your-kakunin_api_key>",
        "KAKUNIN_AGENT_ID": "<kakunin_agent_id>"
      }
    }
  }
}
Cursor (.cursor/mcp.json)
{
  "mcpServers": {
    "kakunin": {
      "command": "npx",
      "args": [
        "-y",
        "@kakunin/mcp"
      ],
      "env": {
        "KAKUNIN_API_KEY": "<your-kakunin_api_key>",
        "KAKUNIN_AGENT_ID": "<kakunin_agent_id>"
      }
    }
  }
}
Cline (cline_mcp_settings.json)
npx -y @kakunin/mcp
§02  Environment variables
KAKUNIN_API_KEY
requiredsecret

Kakunin API key (kkn_live_... or kkn_test_...). Obtain at https://kakunin.ai/dashboard.

KAKUNIN_AGENT_ID
required

ID of the agent this MCP server acts on behalf of (agt_...).

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
5
§04  Alternatives in Monitoring & Logs