AnomalyArmor
AnomalyArmor 智能体
用于 AnomalyArmor 数据可观测性的 AI 技能和 MCP 服务器。直接从 Claude Code、Cursor 或任何兼容 MCP 的 AI 工具中监控数据质量、检测模式漂移并管理警报。
版本: 0.6.0 | 工具: 52 个整合的 MCP 工具 | 技能: 14 个斜杠命令
快速入门
选项 1:Claude Code 插件(推荐)
# Install the plugin
claude plugin marketplace add anomalyarmor/agents
claude plugin install armor@anomalyarmor
# Or via skills.sh
npx skills add anomalyarmor/agents然后使用以下技能:
/armor:status- 检查数据健康状况/armor:alerts- 查看和管理警报/armor:recommend- 获取 AI 监控建议/armor:ask- 询问有关数据的问题
选项 2:MCP 服务器
添加到您的 MCP 配置中(Claude Code、Cursor 等):
{
"mcpServers": {
"armor": {
"command": "uvx",
"args": ["armor-mcp"]
}
}
}Related MCP server: aegis-dq
前置要求
AnomalyArmor 账户:在 anomalyarmor.ai 注册
API 密钥:在“设置 > API 密钥”中生成
配置:设置
ARMOR_API_KEY环境变量或创建~/.armor/config.yaml:
api_key: aa_live_your_key_here可用技能
技能 | 描述 | 示例 |
| 新用户引导 | "帮我完成设置" |
| 所有资产的健康状况摘要 | "我的数据健康吗?" |
| 连接新的数据源 | "连接我的 Snowflake 仓库" |
| 设置新鲜度和模式监控 | "监控 orders 表的新鲜度" |
| 查询和管理警报 | "昨天触发了哪些警报?" |
| 关于数据的自然语言问答 | "哪些表包含客户数据?" |
| 触发 AI 分析 | "分析 finance 模式" |
| 数据质量指标和有效性规则 | "为 customer_id 添加空值检查" |
| 监控覆盖率分析 | "哪些表没有监控?" |
| AI 驱动的监控建议 | "我应该监控什么?" |
| 资产标记和分类 | "将此表标记为 PII" |
| 根本原因分析 | "为什么此表数据陈旧?" |
| 数据血缘探索 | "什么表依赖于此表?" |
| 表分析和统计 | "分析 orders 表" |
MCP 工具(29 个整合工具)
工具遵循整合模式:每个域一个工具,通过 action 参数处理多种操作,在保持完整功能的同时减少上下文窗口的使用。
健康状况与简报
health_summary()- 所有资产的整体数据健康状况get_todays_briefing()- 包含警报、新鲜度和覆盖率缺口的每日 AI 简报
警报 (5 个工具)
get_alerts_summary()- 按严重程度和状态统计的警报数量list_alerts(status, severity, asset_id, from_date, to_date)- 带过滤器的警报查询list_inbox_alerts(status, limit)- 未解决的警报收件箱update_alert(alert_id, action, ...)- 确认、解决、暂缓或评论警报get_alert_trends(period)- 警报趋势随时间的变化get_alert_history(alert_id)- 特定警报的完整历史记录
警报规则 (3 个工具)
list_alert_rules(asset_id, is_active)- 列出已配置的规则create_alert_rule(asset_id, rule_type, ...)- 创建新的警报规则manage_alert_rule(rule_id, action, ...)- 更新、删除、启用/禁用或复制规则
资产 (3 个工具)
list_assets(source, asset_type, search)- 列出受监控的资产create_asset(name, source_type, connection_config)- 创建数据源manage_asset(asset_id, action, ...)- 更新、删除、测试连接或触发发现trigger_asset_discovery(asset_id)- 开始模式发现
新鲜度 (4 个工具)
get_freshness_summary()- 所有资产的新鲜度概览check_freshness(asset_id, table_path)- 检查特定表的新鲜度setup_freshness(asset_id, table_path, check_interval, ...)- 创建新鲜度计划list_freshness_schedules(asset_id)- 列出已配置的计划manage_freshness_schedule(schedule_id, action, ...)- 更新、删除、暂停/恢复计划
模式漂移 (5 个工具)
get_schema_summary()- 模式漂移概览list_schema_changes(asset_id, severity, from_date, to_date)- 列出检测到的更改create_schema_baseline(asset_id, description)- 创建基准enable_schema_monitoring(asset_id, schedule_type, notify_on)- 启用监控disable_schema_monitoring(asset_id)- 禁用监控get_schema_monitoring(asset_id)- 查看当前监控配置dry_run_schema(asset_id, schedule_type)- 在启用前测试模式监控
数据质量 (4 个工具)
get_metrics_summary(asset_id)/list_metrics(asset_id)- 查看指标create_metric(asset_id, metric_type, table_path, ...)- 创建行数、空值率或自定义指标manage_metric(metric_id, action, ...)- 更新、删除、捕获或查看快照get_validity_summary(asset_id)/list_validity_rules(asset_id)- 查看有效性规则create_validity_rule(asset_id, rule_type, table_path, ...)- 创建有效性规则manage_validity_rule(rule_id, action, ...)- 更新、删除、检查或查看结果
参照完整性 (2 个工具)
create_referential_check(asset_id, ...)- 创建跨表参照检查manage_referential(check_id, action, ...)- 列出、删除、运行或查看结果
目标位置 (4 个工具)
list_destinations(destination_type)- 列出警报目标(Slack、电子邮件、Webhook)setup_destination(destination_type, ...)- 创建 Slack 频道、电子邮件或 Webhook 目标manage_destination(destination_id, action, ...)- 更新、删除、测试、启用/禁用manage_rule_destinations(rule_id, action, ...)- 将目标链接/取消链接到警报规则
覆盖率与建议 (3 个工具)
get_coverage(asset_id)- 资产的覆盖率等级和评分manage_coverage(asset_id, action)- 获取后续步骤或应用推荐的监控recommend(asset_id, recommendation_type)- 关于新鲜度、指标、覆盖率或阈值的 AI 建议
智能 (2 个工具)
ask_question(asset, question)- 自然语言问答generate_intelligence(asset)- 触发 AI 知识库生成
目录 (4 个工具)
get_lineage(asset_id, depth, direction)- 数据血缘图job_status(job_id)- 检查异步作业状态create_tag(asset_id, name, object_path, ...)- 创建并分配标签list_tags(asset_id)/apply_tags(asset_id, ...)- 列出并应用标签
API 密钥
get_api_key_info()- 查看当前 API 密钥详情和权限
示例
检查数据健康状况
User: Is my data healthy?
Your data health status:
- Overall: WARNING
- 3 unresolved alerts (1 critical, 2 warning)
- 2 stale tables (orders, customers)
- 1 unacknowledged schema change
- Coverage: 65% (Tier 2: Protected)获取 AI 建议
User: What should I monitor on my Snowflake warehouse?
Based on your table patterns and update frequency:
1. orders (high traffic) - Add freshness check (hourly), row count metric
2. customers (PII) - Enable schema drift monitoring, add null checks
3. payments (financial) - Add freshness + row count + validity rules
Want me to set these up? I can configure all three in one go.每日简报
User: What happened overnight?
Your daily briefing:
- 2 new alerts: orders table stale (6h), schema change in users
- Coverage improved: finance schema now at Tier 3 (Verified)
- Recommendation: 4 tables still have no monitoring. Run /armor:recommend.根本原因分析
User: Why is the orders table stale?
Investigation results:
- Last update: 6 hours ago (expected: hourly)
- Upstream dependency: raw_orders was last updated 8 hours ago
- Likely cause: upstream ETL job failed or delayed
- Impact: 3 downstream dashboards affected故障排除
身份验证失败
Error: No API key configured解决方案:设置 ARMOR_API_KEY 环境变量或创建 ~/.armor/config.yaml
未找到 MCP 服务器
Error: MCP server 'armor' not found解决方案:
配置更改后重启您的 AI 工具
验证是否安装了 uvx:
uvx --version检查 MCP 配置语法
技能无法加载
解决方案:
验证插件是否已安装:
claude plugin list检查技能目录是否存在
重启 Claude Code
开发
请参阅 AGENTS.md 获取开发指南。
支持
问题反馈: GitHub Issues
电子邮件: support@anomalyarmor.ai
许可证
MIT 许可证 - 请参阅 LICENSE
This server cannot be deployed
Maintenance
Related MCP Connectors
- SpanlyOAuthcom.spanly
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Data + AI observability — monitor and troubleshoot production-grade agents and the context they use.
The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.
- SchemaOAuthai.schemalabs
The AI that understands raw data: Schema over your tables and databases, as MCP tools.
Related MCP Servers
AlicenseNot gradedqualityFmaintenanceOpen-source agentic schema layer. Define metrics once in YAML, query governed data from any warehouse (Snowflake, BigQuery, Databricks, PostgreSQL, DuckDB) via MCP.28Apache 2.0- AlicenseBqualityDmaintenanceAgentic data quality MCP server — runs structured validation rules against warehouses (DuckDB, BigQuery, Athena, Databricks, Postgres), diagnoses failures with LLM root cause analysis, and proposes SQL remediations. Full audit trail of every AI decision.64Apache 2.0
- FlicenseNot gradedqualityCmaintenanceOpen-source autonomous agent swarm of 15 MCP-native AI agents for data engineering — catalog, quality, incidents, schema evolution, governance, migration, observability, ML. 212+ tools, Apache 2.0. Works with Claude Code, Cursor, ChatGPT, and any MCP client.12-
- AlicenseNot gradedqualityCmaintenanceAI-driven MCP server that audits, profiles, detects schema drift, and auto-generates documentation for dbt projects, enabling natural language interaction with your dbt project's health.134MIT