WhiteBoxXAI

io.github.AgentaFlow由 GitHub 账号 AgentaFlow 发布v0.3.2更新于 Oct 29, 2026

AI observability, explainability and governance: drift, fairness, ISO 42001, risk register.

已验证Streamable HTTP可网页运行安全与监控数据与分析AI 与机器学习

概览

AI 生成的概览

WhiteBoxXAI 向 MCP 客户端提供 AI 可观测性、可解释性与治理工具，涵盖漂移、公平性、风险登记与 ISO 42001 证据。

可以做什么
  • 管理模型与预测：模型注册表、基于 Git 的模型差异对比、预测日志记录、模型性能指标
  • 检测数据漂移并审计偏差与公平性，支持异步生成 SHAP/LIME 解释
  • 解释大模型：注意力、词元重要性、敏感性、反事实分析与提示词调试
  • 监控大模型调用（词元、成本、延迟），以及 RAG 流水线监控与内容安全分析
  • 处理治理事务：ISO/IEC 42001 就绪度、合规证据、AI 风险登记与治理审查查询、提示词治理
  • 处理告警（规则、分诊上下文、智能分析、告警管理）与多智能体工作流追踪
适用场景
适合需要查看或汇报已部署 AI 模型与大模型应用状况的场景：检查漂移、公平性与性能，生成解释，查阅治理与合规证据，或对 WhiteBoxXAI 账户中的告警进行分诊。
运行要求
需要 WhiteBoxXAI 账户及在控制台（Settings > API Keys）生成的 API 密钥。本地 stdio 方式通过 pip 安装，配置 WHITEBOXXAI_MCP_API_KEY，可选 WHITEBOXXAI_MCP_API_BASE_URL；也可使用托管 Streamable HTTP 端点，在 Authorization 头中传入密钥或个人 JWT。需能访问 WhiteBoxXAI API。
安装前请注意
需要密钥（WHITEBOXXAI_MCP_API_KEY，或 Authorization / X-WhiteBox-API-Key 头），该密钥在显式撤销前长期有效。工具涉及日志记录、告警管理与治理记录，部分调用可能写入或更改账户数据。托管端点的支持与 SLA 取决于 Free/Business Cloud 套餐，部分工作流成本、瓶颈与时间线调用可能耗时约 30 秒。

安装

在 SourceWeft 中

  1. 打开 控制台中的 WhiteBoxXAI，将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.AgentaFlow%2Fwhiteboxxai-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "whiteboxxai": {
      "type": "http",
      "url": "https://api.whiteboxxai.com/mcp/",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

whiteboxxai-mcp

[PyPI version] [Python versions] [Test] [License: MIT]

An MCP (Model Context Protocol) server that exposes WhiteBoxXAI observability and explainability capabilities — model registry, Git-backed model diffing, prediction logging, drift detection, bias/fairness auditing, ISO/IEC 42001 readiness and compliance evidence, AI Risk Register / governance review queries, prompt governance, asynchronous SHAP/LIME explanation generation, LLM explainability (attention/token-importance/sensitivity/counterfactual analysis and prompt debugging), LLM call monitoring (token/cost/latency tracking), RAG pipeline monitoring, content safety analysis, alert rules and triage context, alert intelligence, alert management, multi-agent workflow tracking, and model performance metrics (197 tools across 18 domains) — to any MCP-compatible client (Claude Desktop, Claude Code, LangChain, custom agent harnesses, etc.). Supports MCP Apps (ui:// resources) with sandboxed interactive audit cards, stdio transport, and Streamable HTTP transport (hosted at https://api.whiteboxxai.com/mcp/).

See the integration docs for full setup, connection examples, the tool reference, and known v1 limitations. See examples/ for runnable LangChain, Semantic Kernel, and raw-MCP-client integrations.

Install

bash
pip install whiteboxxai-mcp

Run (stdio — local/self-hosted)

Configure a credential via environment variables, then run the console script. Stdio transport authenticates via WHITEBOXXAI_MCP_API_KEY:

bash
# An API key generated from the WhiteBoxXAI dashboard's Settings > API Keys tab.# Never expires on a fixed schedule -- only when explicitly revoked -- and doesn't require storing a password.export WHITEBOXXAI_MCP_API_BASE_URL="https://api.whiteboxxai.com"export WHITEBOXXAI_MCP_API_KEY="wbx_live_..."
whiteboxxai-mcp

Point your MCP client at this command (e.g. in Claude Desktop's mcpServers config, or Claude Code's .mcp.json).

For hosted Streamable HTTP (https://api.whiteboxxai.com/mcp/), pass your API key or personal JWT in the Authorization: Bearer <token> header.

Agent skills

To have a coding agent set this up and call the tools correctly, give it the whitebox-mcp-server skill (and whitebox-governance-rules). They are published at https://whiteboxxai.com/skills/index.md. The tool list they reference is pinned in tests/mcp_inspector_snapshot.json; a rename or removal of a tool shows up as a diff there.

Versioning & support

This package follows Semantic Versioning; see CHANGELOG.md for release history. Self-hosted stdio usage (above) is best-effort supported; the hosted /mcp/ HTTP endpoint is a product surface whose support/SLA follows the caller's underlying Free/Business Cloud plan.

Known v1 limitations

  • Auth: stdio uses WHITEBOXXAI_MCP_API_KEY — a scoped, revocable credential that isn't tied to a human account's password or session lifecycle. Hosted Streamable HTTP (https://api.whiteboxxai.com/mcp/) accepts an API key or personal JWT.
  • Alerts: covers core alert rules and triage context (whitebox_alerts_*), alert intelligence (whitebox_alert_intelligence_*, 20 tools), and alert management (whitebox_alert_management_*, 13 tools).
  • whitebox_agent_workflows_cost_breakdown/_bottlenecks/_timeline: these three can take up to ~30s — the backend blocks server-side on a Celery task before responding, and the SDK client uses an extended (40s) timeout for exactly these calls.
  • Scope: models, predictions, drift, bias/fairness, AI Risk Register / governance queries, prompts, compliance, explanations, LLM explainability, LLM call monitoring, RAG monitoring, content safety, alert intelligence, alert management, multi-agent workflows, and metrics all ship across 18 domains (197 tools total) over both stdio and hosted Streamable HTTP.

MCP Registry

The server is published to the official MCP Registry as io.github.AgentaFlow/whiteboxxai-mcp.

Development

bash
pip install -e ".[dev]"pytest tests/unit
# MCP Inspector tool-list regression check (needs Node.js); after an intentional# tool change, regenerate the committed snapshot with --writepython tests/check_mcp_inspector_snapshot.py

Releases are cut from GitHub releases; see RELEASING.md.

License

MIT -- see LICENSE.

来源：README.md，提交 f2ebcba

工具

0
该服务器需要 API 密钥等凭据，因此 SourceWeft 无法在没有凭据的情况下读取其工具，也未收录。

版本历史

1
  1. v0.3.2最新Oct 29, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分