Query Engine MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Query Engine MCPWhat were the total sales last quarter by region?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Query Engine MCP
一个声明驱动、可机械证明的企业取数 MCP Server。它将 Agent 提出的业务语义意图解析为 canonical refs,由 Runtime 验证统计范围、筛选、粒度、关系、fanout、权限和物理 binding 后才执行受控查询。
该仓库只包含 MCP Server、运行所需的语义 Runtime、Zeekr instance pack 和 ask-data skill;不包含 pa-chatbi 应用、Agent SDK、.env、凭据、真实查询结果、trace/replay artifact 或预构建 Python 环境。
公开 MCP 工具
semantic_querylist_query_capabilitiesget_system_dateget_data_horizon
Agent 只能提出指标、维度、统计范围、时间、筛选与分析操作;不能提交 SQL/VQL、表、字段、join 或物理 binding。无法由已发布原子与证明推导的组合必须 fail-closed。
Related MCP server: DataHub MCP Server
本机启动
需要 Python 3.13 和 uv。先准备本机运行时:
./tools/bootstrap-runtime.sh操作方将已有的 Denodo 配置放在仓库外部的 dotenv 文件中,再注册给 Codex:
export QUERY_ENGINE_LOCAL_DOTENV_PATH=/absolute/path/to/operator.env
./tools/install-codex-mcp.sh新开一个 Codex task 后即可发现 MCP。业务问答使用 skills/ask-data/SKILL.md,它只调用 semantic_query,不会绕过 Runtime 写 SQL。
目录
docs/architecture/uose/uose-caliber-harness/ Runtime 与 MCP Server
docs/architecture/uose/instance-packs/ 客户语义包与物理 binding
docs/architecture/uose/semantic-domain-modules/ 通用业务域角色
skills/ask-data/ Agent 问数指引
tools/ 启动与 Codex 安装脚本
docs/migration-inputs/semantic-kernel-v2/ 已导入的 v2 迁移输入与采用决策Zeekr 特有口径、视图映射和值域留在其 instance pack;Core Runtime 不写客户字段,也不会为每个指标 × 维度组合预枚举 Shape。
验证
完成安装后,在新开的 Codex task 中确认能发现四个公开工具;再通过 get_data_horizon 完成不读业务行的启动检查。业务查询必须走 semantic_query,并由当前 instance pack 的声明和 physical binding 决定是否准入。
本仓库是本机 read-only MCP 的源码项目,不是远程托管的生产 MCP 服务。生产认证、多租户隔离、部署与发布验收需在独立生产环境完成。
外部 v2 阶段包的完整源文件保留在
docs/migration-inputs/semantic-kernel-v2/。
它们是可审计的迁移输入,不会被运行时导入或额外暴露为 MCP/HTTP 服务;采用规则见其中的
INTEGRATION_DECISIONS.md。
This server cannot be deployed
Maintenance
Related MCP Connectors
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
Runtime permission, approval, and audit layer for AI agent tool execution.
Agent-native security, trust, reliability, data and procurement tools for AI workflows.
List datasets, schemas, run APL queries, and use prompts for exploration, anomalies, and monitoring.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to understand and query your database safely by providing a semantic layer of metadata, with tools to search, explain, validate, and generate safe SQL.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, explore data lineage, understand business context, and generate SQL queries across an organization's data ecosystem.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceProvides a semantic intelligence layer for SQL Server databases, enabling AI agents to understand schema structure, relationships, and safely interact through policy-gated tools.3MIT
- AlicenseAqualityFmaintenanceA governed SQL gateway that exposes typed tools to AI agents, compiling safe read-only queries from a semantic layer while blocking PII before execution, supporting SQL Server, Postgres, and SQLite.9MIT