U2 MCP Server

io.github.bpamiri由 GitHub 账号 bpamiri 发布v0.1.1更新于 Oct 27, 2026

Connect AI assistants to Rocket Universe/UniData MultiValue databases via MCP.

已验证STDIO仅桌面数据库知识与记忆

概览

AI 生成的概览

让 AI 助手连接 Rocket Universe/UniData MultiValue 数据库,用自然语言查询、读取和修改记录。

可以做什么
  • 连接、断开并查看与 Universe/UniData 服务器的连接
  • 列出文件,读取单条或多条记录,写入和删除记录,获取文件统计
  • 执行 RetrieVe/UniQuery 语句、TCL/ECL 命令和 SELECT 列表
  • 浏览字典:列出字典项、查看字段定义、描述文件结构
  • 调用已编目的 BASIC 子程序,并用开始、提交、回滚管理事务
  • 保存、列出、搜索和删除关于数据库的知识笔记,跨会话保留
适用场景
适合需要让助手操作 Pick/MultiValue 数据库的场景,例如探索文件结构、回答记录相关问题或执行查询,而无需手写 RetrieVe 语法。也适合希望集中部署连接并共享数据库结构知识的团队。
运行要求
本地 Python 3.10+ 进程,通过 pip 或 uvx 运行,uopy 包会作为依赖自动安装。需要能访问 Universe 或 UniData 服务器的网络,并设置环境变量 U2_HOST、U2_USER、U2_PASSWORD 和 U2_ACCOUNT,另有 U2_SERVICE、U2_PORT、U2_SSL 等可选配置。文档还介绍了 HTTP/SSE 模式和基于 OAuth 的部署方式。
安装前请注意
服务器通过 U2_PASSWORD、U2_IDP_CLIENT_SECRET 等环境变量保存数据库凭据。写入和删除工具、TCL 执行以及 BASIC 子程序调用都可能修改或删除数据;只读模式(U2_READ_ONLY)默认关闭,命令黑名单(U2_BLOCKED_COMMANDS)默认仅含少数命令,探索时应主动开启。保存的知识会写入本地 markdown 文件,HTTP 模式配合宽松的 CORS 设置会把数据库连接暴露到网络。

安装

在 SourceWeft 中

  1. 打开 控制台中的 U2 MCP Server,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

u2-mcp

[PyPI version] [License] [Python] [MCP]

Connect Claude to your Universe/UniData database using natural language.

u2-mcp is an MCP server that lets AI assistants like Claude query and interact with Rocket Universe and UniData MultiValue databases. Ask questions in plain English and get real answers from your data.

The first MCP server for the Pick/MultiValue database family.

What Can You Do With This?

Instead of writing RetrieVe queries, just ask Claude:

You AskClaude Does
"How many customers are in California?"Queries the database and tells you "1,247 customers"
"Show me order ORD001"Reads the record and displays all fields
"What files are available?"Lists all files in your account
"Describe the CUSTOMERS file"Shows field definitions from the dictionary

How It Works

┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐│  Claude Desktop │◄───►│     u2-mcp      │◄───►│ Universe/UniData││  (You ask here) │     │  (Translates)   │     │   (Your data)   │└─────────────────┘     └─────────────────┘     └─────────────────┘
  1. You ask Claude a question about your database
  2. Claude calls u2-mcp with the appropriate tool
  3. u2-mcp queries your Universe/UniData server
  4. Results come back through Claude in a readable format

New to MCP? See What is MCP? for a complete explanation.

Documentation

GuideDescription
What is MCP?Understanding MCP and how u2-mcp works
InstallationComplete installation guide
QuickstartGet running in 10 minutes
ConfigurationAll configuration options
Tools ReferenceDetailed tool documentation
Usage ExamplesCommon usage patterns
OAuth SetupClaude.ai integration with SSO

Features

  • Connection Management - Connect to Universe/UniData servers with connection pooling and SSL support
  • File Operations - Read, write, and delete records while preserving MultiValue semantics
  • Query Execution - Run RetrieVe/UniQuery statements with safety controls
  • Dictionary Access - Explore file structures and field definitions
  • BASIC Subroutine Calls - Execute cataloged BASIC programs
  • Transaction Support - Full transaction management with commit/rollback
  • AI-Optimized - Built-in query examples and syntax help for better LLM interactions

Installation

bash
pip install u2-mcp

Or using uvx for isolated execution:

bash
uvx u2-mcp

Quick Start

Prerequisites

  • Python 3.10+
  • Access to a Rocket Universe or UniData server
  • The uopy package (installed automatically as a dependency)

Configuration

Set environment variables for your database connection:

bash
export U2_HOST=server.example.comexport U2_USER=usernameexport U2_PASSWORD=passwordexport U2_ACCOUNT=MYACCOUNTexport U2_SERVICE=uvcs  # or 'udcs' for UniData

Claude Desktop Configuration

Add to your claude_desktop_config.json:

json
{  "mcpServers": {    "u2": {      "command": "uvx",      "args": ["u2-mcp"],      "env": {        "U2_HOST": "server.example.com",        "U2_USER": "user",        "U2_PASSWORD": "password",        "U2_ACCOUNT": "MYACCOUNT"      }    }  }}

Usage Examples

Once connected, you can use natural language to interact with your Universe database:

  • "List all customers in California"
  • "Read record CUST001 from the CUSTOMERS file"
  • "Show me the dictionary for the ORDERS file"
  • "Count all open invoices over $1000"

Available Tools

Connection Management

  • connect - Establish connection to Universe/UniData server
  • disconnect - Close connections
  • list_connections - Show active connections

File Operations

  • list_files - List available files in the account
  • read_record - Read a single record by ID
  • read_records - Read multiple records
  • write_record - Write/update a record
  • delete_record - Delete a record
  • get_file_info - Get file statistics

Query Execution

  • execute_query - Run RetrieVe/UniQuery statements
  • execute_tcl - Run TCL/ECL commands
  • get_select_list - Execute SELECT and return record IDs

Dictionary Access

  • list_dictionary - List dictionary items
  • get_field_definition - Get field details
  • describe_file - High-level file description

Advanced Features

  • call_subroutine - Call BASIC subroutines
  • begin_transaction / commit_transaction / rollback_transaction - Transaction management

Knowledge Persistence

  • save_knowledge - Save learned information about the database
  • list_knowledge - List all saved knowledge topics
  • get_knowledge_topic - Retrieve specific topic
  • search_knowledge - Search across saved knowledge
  • delete_knowledge - Remove a knowledge topic

Configuration Options

VariableDescriptionDefault
U2_HOSTServer hostname or IPRequired
U2_USERUsernameRequired
U2_PASSWORDPasswordRequired
U2_ACCOUNTAccount nameRequired
U2_SERVICEService type (uvcs or udcs)uvcs
U2_PORTServer port31438
U2_SSLEnable SSLfalse
U2_TIMEOUTConnection timeout (seconds)30
U2_READ_ONLYDisable write operationsfalse
U2_MAX_RECORDSMaximum SELECT results10000
U2_BLOCKED_COMMANDSComma-separated blocked TCL commandsDELETE.FILE,CLEAR.FILE
U2_KNOWLEDGE_PATHCustom path for knowledge file~/.u2-mcp/knowledge.md

Knowledge Persistence

The MCP server includes a knowledge persistence feature that allows Claude to save and recall learned information about your database across sessions. This eliminates repetitive discovery work and speeds up future interactions.

How It Works

When Claude discovers useful information about your database (file purposes, field meanings, working queries), it can save this knowledge using the save_knowledge tool. This information is stored in a markdown file and automatically available in future conversations via the u2://knowledge resource.

What Gets Saved

  • File descriptions - What each file contains (e.g., "AR-CUST is the customer master file")
  • Field mappings - Which fields contain what data (e.g., "Field 1 is customer name")
  • Query patterns - Queries that produced good results
  • Data formats - Date formats, code meanings, conversion notes
  • Relationships - How files relate to each other

Storage Location

Knowledge is stored in ~/.u2-mcp/knowledge.md by default. You can customize this location using the U2_KNOWLEDGE_PATH environment variable:

json
{  "env": {    "U2_KNOWLEDGE_PATH": "/path/to/custom/knowledge.md"  }}

Example Usage

After Claude discovers that AR-CUST contains customer records:

Claude: I found that AR-CUST is the customer master file. Let me save this for future reference.[Calls save_knowledge("AR-CUST file", "Customer master file. Key is customer number. Field 1=name, Field 2=address...")]

In the next conversation, Claude will already know this and won't need to rediscover it.

Centralized Deployment (HTTP/SSE Mode)

For team environments, you can run u2-mcp as a centralized HTTP server instead of local stdio mode. This allows:

  • Single database connection for the whole team
  • Shared knowledge base
  • Centralized credential management
  • Access from any MCP-compatible client

Running the HTTP Server

bash
# Basic HTTP server on default port 8080u2-mcp --http
# Custom host and portu2-mcp --http --host 0.0.0.0 --port 3000
# Or using environment variablesexport U2_HTTP_HOST=0.0.0.0export U2_HTTP_PORT=3000u2-mcp --http

Docker Deployment

dockerfile
FROM python:3.12-slim
RUN pip install u2-mcp
ENV U2_HOST=your-universe-serverENV U2_USER=usernameENV U2_PASSWORD=passwordENV U2_ACCOUNT=MYACCOUNTENV U2_HTTP_PORT=8080
EXPOSE 8080
CMD ["u2-mcp", "--http"]
bash
docker build -t u2-mcp-server .docker run -p 8080:8080 u2-mcp-server

HTTP Configuration Options

VariableDescriptionDefault
U2_HTTP_HOSTHost to bind HTTP server to0.0.0.0
U2_HTTP_PORTPort for HTTP server8080
U2_HTTP_CORS_ORIGINSAllowed CORS origins (comma-separated or *)*

Connecting Clients

The HTTP server exposes an SSE (Server-Sent Events) endpoint at /sse. MCP clients that support remote servers can connect to:

http://your-server:8080/sse

Note: As of late 2024, Claude Desktop only supports local stdio MCP servers. HTTP/SSE mode is for:

  • Custom MCP clients
  • Future Claude Desktop versions with remote server support
  • Integration with other AI tools that support MCP over HTTP

Claude.ai Integration (Streamable HTTP + OAuth)

Deploy u2-mcp as a Custom Connector in Claude.ai with enterprise authentication via your identity provider (Duo, Auth0, Okta, etc.).

Quick Setup

  1. Deploy u2-mcp with OAuth enabled:
bash
u2-mcp --streamable-http --host 0.0.0.0 --port 8080
  1. Configure OAuth in your .env:
bash
U2_AUTH_ENABLED=trueU2_AUTH_ISSUER_URL=https://u2-mcp.example.comU2_IDP_PROVIDER=duoU2_IDP_DISCOVERY_URL=https://sso-xxx.sso.duosecurity.com/oidc/CLIENT_ID/.well-known/openid-configurationU2_IDP_CLIENT_ID=your_client_idU2_IDP_CLIENT_SECRET=your_client_secret
  1. Add to Claude.ai: Go to Settings → Connectors → Add Custom Connector → Enter your URL

Users authenticate through your IdP and can then query your database directly from Claude.ai.

Supported Identity Providers

  • Cisco Duo - Enterprise MFA and SSO
  • Auth0 - Flexible identity platform
  • Any OIDC Provider - Okta, Azure AD, Google Workspace, Keycloak, etc.

See the OAuth Guide for detailed setup instructions.

Security

  • Credentials are never logged
  • Configurable command blocklist prevents dangerous operations
  • Optional read-only mode for safe exploration
  • Honors Universe's built-in security model

See SECURITY.md for reporting security vulnerabilities.

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Documentation

Getting Started

Reference

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Acknowledgments

  • Rocket Software for the uopy package
  • Anthropic for the Model Context Protocol specification
  • The MultiValue database community

来源:README.md,提交 f427768

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

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25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 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