A Model Context Protocol (MCP) server acts as a proxy between an external service that provides context, data, or capabilities to a Large Language Model (LLM) or AI application. MCP servers connect AI applications to external systems such as databases and web services, translating their responses into a format that the AI application can understand.
Server Setup
You must enable MCP servers and set up authentication before use. For more information about using Google and Google Cloud remote MCP servers, see Google Cloud MCP servers overview .
MCP server for interacting with Knowledge Catalog (formerly known as Dataplex).
Server Endpoints
An MCP service endpoint is the network address and communication interface (usually a URL) of the MCP server that an AI application (the Host for the MCP client) uses to establish a secure, standardized connection. It is the point of contact for the LLM to request context, call a tool, or access a resource. Google MCP endpoints can be global or regional.
The dataplex.googleapis.com MCP server has the following MCP endpoint:
- https://dataplex.googleapis.com/mcp
MCP Tools
An MCP tool is a function or executable capability that an MCP server exposes to a LLM or AI application to perform an action in the real world.
The dataplex.googleapis.com MCP server has the following tools:
Initiates the creation of a Data Product.
- The tool returns a long-running operation. Use the
get_operationtool to poll its status until the operation completes. - The data product creation operation can take several minutes. Use a command line tool to pause for 5 seconds before rechecking the status.
- After you use the
create_data_producttool to create a data product, you can use theupdate_data_producttool to add access groups and labels in case provided by the user else do not call theupdate_data_producttool and just call theget_data_producttool to get the data product details.
update_mask
parameter specifies which fields of the data product to update. For example, to update only the description
field, set update_mask
to description
. To update multiple fields at once, separate the field names with commas. For example, description,labels
updates both the description
and labels
fields. * The tool returns a long-running operation. Use the get_operation
tool to poll its status until the operation completes. * The data product update operation can take several minutes. Use a command line tool to pause for 5 seconds before rechecking the status. * After you use the update_data_product
tool, use the get_data_product
tool to retrieve the current values of the data product fields.Initiates the creation of a Data Asset.
- The tool returns a long-running operation. Use the
get_operationtool to poll its status until the operation completes. - In case access group configs are provided, the access group name provided is the key and the role provided is the value.
- The data asset creation operation can take several minutes. Use a command line tool to pause for 5 seconds before rechecking the status.
- After you use the
create_data_assettool to create a data product, use theget_data_assettool to get the data asset details.
update_mask
parameter specifies which fields of the data product to update. For example, to update only the description
field, set update_mask
to description
. To update multiple fields at once, separate the field names with commas. For example, access_group_configs,labels
updates both the access_group_configs
and labels
fields. * The tool returns a long-running operation. Use the get_operation
tool to poll its status until the operation completes. * In case access group configs are provided, the access group name provided is the key and the role provided is the value. * The data product update operation can take several minutes. Use a command line tool to pause for 5 seconds before rechecking the status. * After you use the update_data_asset
tool, use the get_data_asset
tool to retrieve the current values of the data product fields.name
: The name of the operation to get. * name
should be the name returned by the tool that initiated the operation. * name
should be in the format of projects/{project}/locations/{location}/operations/{operation}
Returns* response
: The response of the operation. * error
: The error returned by the operation if any.Get MCP tool specifications
To get the MCP tool specifications for all tools in an MCP server, use the tools/list
method. The following example demonstrates how to use curl
to list all tools and their specifications currently available within the MCP server.
| Curl Request |
|---|
curl --location 'https://dataplex.googleapis.com/mcp' \ --header 'content-type: application/json' \ --header 'accept: application/json, text/event-stream' \ --data '{ "method": "tools/list", "jsonrpc": "2.0", "id": 1 }' |

