oracle-eim-dq
Oracle EIM Data Quality
独立 MCP 服务器,用于针对本地部署的 Oracle 和 Oracle ATP 执行受治理的 EIM 数据质量检查。这不是 Oracle MCP 聊天机器人。
聊天机器人项目(oracle-mcp-chatbot)负责回答自然语言问题。本项目只从 EIM_APPS.EIM_DQ_RULES_LOOKUP 查询 ACTIVE 规则,运行已批准的只读聚合 SQL,并返回一份总监可直接使用的 Markdown 报告。
pip install --target .pydeps -r requirements-dev.txt
PYTHONPATH=.pydeps:src pytest
cp .env.example .env # add credentials
PYTHONPATH=.pydeps:src python -m oracle_mcp.server --profile both --check
PYTHONPATH=.pydeps:src python -m oracle_mcp.server --profile both规则工作流与报告约定:docs/data-quality-framework.md。
功能
能力 | 实现方式 |
与聊天机器人分离 | 独立仓库,独立 MCP 服务器名称 |
仅 ACTIVE 规则 | 目录筛选 |
检查点上下文 |
|
只读 | AST 守卫,并加上 |
指标 | 总数、失败数、通过率、失败率、严重程度 |
趋势 | 本地 JSONL 历史与上次运行的对比 |
Related MCP server: database-mcp
MCP 工具
list_active_dq_rulesexecute_data_quality_rule以及用于确认对象的同类只读 discovery/validate/execute 工具
Cursor MCP
让 Cursor 指向 mcp-clients/cursor-mcp.json(替换为绝对路径)。工作区中的 .cursor/mcp.json 应注册 oracle-eim-dq,并将 cwd 设置为该仓库,而不是 oracle-mcp-chatbot。
本地测试
在此仓库中运行以下命令:
# 1. Unit and security tests (no database required)
PYTHONPATH=.pydeps:src .pydeps/bin/pytest -q
# 2. Verify both Oracle connections
PYTHONPATH=.pydeps:src python3 -m oracle_mcp.server --profile both --check
# 3. Verify the MCP tool surface and read the live ACTIVE-rule catalog
PYTHONPATH=.pydeps:src python3 scripts/verify_dq.py预期的实际验证结果:
{
"status": "OK",
"server": "oracle-eim-dq",
"databases": ["ATP", "ONPREM"],
"dq_tools": ["execute_data_quality_rule", "list_active_dq_rules"]
}如果 active_rule_count 为 0,说明连接和 MCP 都工作正常,但受治理的目录中还没有 ACTIVE 规则。请在该只读应用之外注册并审批目录规则行,然后重新运行验证。
修改 .cursor/mcp.json 后,请重新加载 Cursor 的 MCP 服务器。在聊天中,先提出:列出当前活动的 EIM 数据质量规则。 在该调用返回 ACTIVE 规则 ID 之前,不要尝试执行任何规则。
This server cannot be deployed
Maintenance
Related MCP Connectors
Auto-discover validation rules from data — scan, profile, health-score. No rules to write.
CloudOracle - 14-tool multi-cloud compliance MCP: AWS, Azure, GCP posture, IAM, configs.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Paid remote MCP for governed database query review, SQL simulation, approvals, and audits.
Related MCP Servers
- 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 gradedqualityDmaintenanceAutomatically discovers database schema, performs data quality checks on tables and columns, and generates natural-language root cause analysis reports using Ollama LLM.-
- FlicenseNot gradedqualityBmaintenanceProvides governed MCP tools for validating, explaining, and remediating clinical supply chain data quality across Bronze, Silver, and Gold layers on Azure Databricks, with data contracts and an evaluation harness.-
- AlicenseAqualityBmaintenanceGenerates and deploys Cloudera Data Engineering (CDE) Airflow jobs from ODCS data contracts, validating live table data in CDW against schema and data-quality rules without WAP staging.13Apache 2.0