U2 MCP Server

io.github.bpamiriPublished by GitHub account bpamiriv0.1.1Updated Oct 27, 2026

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

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

Connects an AI assistant to Rocket Universe/UniData MultiValue databases so it can query, read and modify records in plain language.

What you can do
  • Connect, disconnect and list connections to Universe/UniData servers
  • List files, read single or multiple records, write and delete records, get file statistics
  • Run RetrieVe/UniQuery statements, TCL/ECL commands and SELECT lists
  • Browse dictionaries: list items, get field definitions, describe files
  • Call cataloged BASIC subroutines and manage transactions with begin, commit and rollback
  • Save, list, search and delete notes about the database that persist across sessions
When to use it
Useful when an assistant needs to work with a Pick/MultiValue database — exploring file structures, answering questions about records, or running queries — without hand-writing RetrieVe syntax. Also suited to teams that want a shared, centrally deployed connection with saved schema knowledge.
Requirements
Local Python 3.10+ process, run via pip or uvx; the uopy package installs as a dependency. Needs network access to a Universe or UniData server and the environment variables U2_HOST, U2_USER, U2_PASSWORD and U2_ACCOUNT, plus optional U2_SERVICE, U2_PORT, U2_SSL and related settings. An HTTP/SSE mode and OAuth-based deployment are also documented.
Before you install
The server holds database credentials in environment variables such as U2_PASSWORD and U2_IDP_CLIENT_SECRET. Write and delete tools, TCL execution and BASIC subroutine calls can change or remove data; read-only mode (U2_READ_ONLY) and the command blocklist (U2_BLOCKED_COMMANDS) are off or limited by default, so enable them for exploration. Saved knowledge is written to a local markdown file, and HTTP mode with permissive CORS exposes the database connection to the network.

Installation

In SourceWeft

  1. Open U2 MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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

Source: README.md at commit f427768

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts