Skip to main content

A Model Context Protocol (MCP) server for MigratorXpress, enabling database migration between heterogeneous database systems.

Project description

MigratorXpress MCP Server

A Model Context Protocol (MCP) server for MigratorXpress, enabling database migration between heterogeneous database systems through AI assistants.

MigratorXpress supports migrating from Oracle, PostgreSQL, SQL Server, and Netezza to PostgreSQL or SQL Server targets.

Installation

pip install -e .

Or install dependencies directly:

pip install -r requirements.txt

Configuration

Environment Variables

Variable Default Description
MIGRATORXPRESS_PATH ./MigratorXpress Path to MigratorXpress binary
MIGRATORXPRESS_TIMEOUT 3600 Command execution timeout in seconds
MIGRATORXPRESS_LOG_DIR ./logs Directory for execution logs
LOG_LEVEL INFO Server logging level

Copy .env.example to .env and adjust values:

cp .env.example .env

Claude Code Configuration

Add to your Claude Code MCP settings:

{
  "mcpServers": {
    "migratorxpress": {
      "command": "python",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/migratorxpress-mcp",
      "env": {
        "MIGRATORXPRESS_PATH": "/path/to/MigratorXpress"
      }
    }
  }
}

Tools

1. preview_command

Build and preview a MigratorXpress CLI command without executing it. License text is automatically masked in the display output.

Required parameters: auth_file, source_db_auth_id, source_db_name, target_db_auth_id, target_db_name, migration_db_auth_id

2. execute_command

Execute a previously previewed command. Requires confirmation: true as a safety mechanism.

3. validate_auth_file

Validate that an authentication file exists, is valid JSON, and optionally check for specific auth_id entries.

4. list_capabilities

List supported source/target databases, tasks, migration DB modes, load modes, and FK modes.

5. suggest_workflow

Given a source database type, target database type, and optional constraint flag, suggest the full sequence of migration tasks with example commands.

6. get_version

Report MigratorXpress version and capabilities.

Workflow Example

A typical migration from Oracle to PostgreSQL:

Step 1: translate  — Translate Oracle DDL to PostgreSQL-compatible DDL
Step 2: create     — Create target tables from translated DDL
Step 3: transfer   — Transfer data from source to target
Step 4: diff       — Verify row counts match between source and target
Step 5: copy_pk    — Copy primary key constraints
        copy_ak    — Copy alternate key (unique) constraints
        copy_fk    — Copy foreign key constraints

Or run all steps in a single invocation with --task_list all.

Development

Running Tests

pip install -e ".[dev]"
python -m pytest tests/ -v

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

migratorxpress_mcp-0.1.0.tar.gz (22.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

migratorxpress_mcp-0.1.0-py3-none-any.whl (19.1 kB view details)

Uploaded Python 3

File details

Details for the file migratorxpress_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: migratorxpress_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 22.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for migratorxpress_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 3fbc7cf56dc12941702f234ecfd4e5025e7d2191c2fe5d4718105a9fc517ceb3
MD5 d3c32094a142a3565cb86d216130fc9e
BLAKE2b-256 80c5f57a03c5e31507ad5fab5694a24c28fe0f409b2ac9e3339f62e3fcbe2346

See more details on using hashes here.

File details

Details for the file migratorxpress_mcp-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for migratorxpress_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d77d8841bb4fc93298726c2ef87859980ffed862f7bd60727257075af61c685d
MD5 e17504d2e1b391b8001a0546cc34e02c
BLAKE2b-256 6f9f6aa193a319a3e27d1c32c827e420a3e13d8ff5f0d5d95804d2fe70b22444

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page