ai.getvda/traced-claude-format-guard

AI 与模型 HTTP 只读/查询为主

能做什么：它校验 Claude 输出格式并在追踪下拦截不合规响应，可自检。

什么时候接：下游对格式敏感、需要给模型输出加一道闸时。

注意：校验规则与拦截动作以官方 README 为准。

可用工具

invokeProxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.
selftestFREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.

更新日期：2026-10-29（tools/list 实测）

配置到 Claude / Cursor

{
  "mcpServers": {
    "remote-ai-getvda-traced-claude-format-guard": {
      "type": "http",
      "url": "https://traced-llm-proxy-anthropic.getvda.ai/mcp"
    }
  }
}

来源

更新日期：2026-10-29

同分类其他 MCP

资料来自官方仓库与 MCP 接口探测，以官方最新文档为准；安装第三方 MCP server 前请自行评估安全风险。