MCP Server
The Delphix MCP server enables AI assistants to interact with Data Control Tower (DCT) through natural language using the Model Context Protocol (MCP). Supported AI clients include Claude Desktop, Cursor, and VS Code Copilot.
After configuring the MCP Server, you can ask questions about your test data management environment. For example:
-
I need to provision an Oracle and PostgreSQL VDB and place them in the same VDB Group.
-
Add the Team: Alpha tag to all VDBs that were provisioned in the last hour.
-
Run a refresh from parent against all VDBs that haven't been refreshed in the last week.
-
List the PostgreSQL VDBs that have not been refreshed in the last 30 days.
-
How much storage is Delphix saving me in TBs? Dollars?
-
Which top five compliance jobs are most likely to fail? Why?
-
List all VDBS that occupy more space than their parent dataset.
-
Search for dSources with the largest snapshot sizes.
Use this quick start guide to configure the MCP server. For comprehensive instructions, see the MCP Server repository.
Prerequisites
-
Data Control Tower (DCT) instance with API access.
-
Personal DCT API Key
-
See Select a toolset for your persona for information about the permissions associated with each persona. You do not need the full set of permissions to run a given toolset.
-
-
MCP-compatible client. For example, Claude Desktop, Windsurf, or Cursor.
-
Bring Your Own LLM (BYO-LLM) configured via the MCP-compatible client.
-
The Delphix MCP Server does not interface with the DCT internal LLM.
-
-
Python 3.11+ or Bash for local server execution.
Installation
Refer to the installation instructions in the MCP Server GitHub repository.
Configure an MCP client - quick start
You must configure the MCP client before it can send requests to DCT through the MCP server. No separate installation is required as uvx manages dependencies automatically.
-
Open the configuration file for your MCP-compatible AI client.
-
Add the following MCP server definition:
{
"mcpServers": {
"delphix-dct": {
"command": "uvx",
"args": ["--from", "git+https://github.com/delphix/dxi-mcp-server.git", "dct-mcp-server"],
"env": {
"DCT_API_KEY": "your-api-key-here",
"DCT_BASE_URL": "https://your-dct-host.company.com",
"DCT_TOOLSET": "self_service"
}
}
}
}
Select a toolset for your persona
Some LLM clients, including Claude Desktop, do not support automatic (auto) toolset selection. If your LLM client does not support this feature, select a specific toolset instead.
| DCT_TOOLSET value | Tools | Intended Users |
|---|---|---|
|
self_service (default) |
7 |
Developers and QA: Day-to-day VDB operations |
|
self_service_provision |
14 |
Senior developers: Self-service plus VDB provisioning |
|
continuous_data_admin |
17 |
DBAs (Database administrator): Full data lifecycle, dSource linking, exports |
|
platform_admin |
13 |
Platform admins: Engines, IAM, replication, system config |
|
reporting_insights |
13 |
Managers and auditors: Read-only reporting |
|
auto |
5 meta-tools |
Any user: runtime toolset discovery and switching |
Configure key environment variables
|
Variable |
Required |
Default |
Description |
|---|---|---|---|
|
DCT_API_KEY |
Yes |
— |
DCT API key. Do not prefix with 'apk' |
|
DCT_BASE_URL |
Yes |
— |
DCT instance URL. Do not append '/dct' |
|
DCT_TOOLSET |
No |
self_service |
Toolset to load (see Select a toolset for your persona) |
|
DCT_VERIFY_SSL |
No |
true |
Set false in non production |
|
DCT_TIMEOUT |
No |
30 |
Request timeout in seconds |
Videos
Limitations
-
The Delphix MCP Server is limited to Continuous Data and general platform create, read, update, and delete (CRUD) operations. Limited Continuous Compliance information, such as job execution and state, is also available for monitoring.
-
The Delphix MCP Server is not part of the Data Control Tower deployment package. It requires a separate installation and configuration.
-
The Delphix MCP Server is a preview release and must not be used in production.
Support
The Delphix MCP Server is an open-source community project provided under the MIT License.
If you make modifications or improvements to the source code, submit a pull request for review.
For any questions, bugs, or feature requests, create an issue. Delphix Support does not assist with open-source community projects.