Query Engine MCP

Query Engine MCP

Enables agents to perform controlled enterprise data queries through semantic intent, with runtime validation of statistics, filters, granularity, permissions, and physical bindings. Exposes tools like semantic_query for safe, fail-closed access to data horizons and capabilities.

Category
Visit Server

README

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_query
  • list_query_capabilities
  • get_system_date
  • get_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。

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

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。

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured