MCP Reference: datamigration

Database Migration MCP service

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.

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 Database Migration API MCP server has the following global MCP endpoint:

  • https://datamigration.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.

Tools

The datamigration MCP server has the following tools:

MCP Tools
list_static_ips

When you migrate a database into Google Cloud using DMS, Google needs a way to securely connect to your source database to read the data. If you choose the Static-IP connectivity method to connect to your source database, you will need to allow incoming traffic from DMS's specific, trusted IPs. This tool lists the IP addresses (matching the provided resource name) that should be allowlisted by the customer.

  • The resource name parameter is in the form projects/{project name}/locations/{location}, for example: projects/my-project/locations/us-central1.
list_migration_jobs

Lists the migration jobs of the provided parent with optional filters.

  • Parent parameter is in the form projects/{project name}/locations/{location}, for example: projects/my-project/locations/us-central1.
  • You can use any, some or all of the additional parameters to filter the results.
  • You can specify in the 'pageSize' parameter the maximum number of migration jobs to return. The tool may return fewer than this value. If more jobs are available, a 'nextPageToken' value is returned and you can use it in the next call to retrieve the next page of results. If unspecified, at most 50 migration jobs will be returned. The maximum value is 100; values above 100 are coerced to 100.
  • If no 'nextPageToken' is returned, there are no more migration jobs to retrieve.
  • Not all the details of the migration jobs are returned.
  • To get the full details of a specific job use the 'get_migration_job' tool.

For example: { create_time_after: 2025-10-02T10:15:33Z create_time_before: 2025-10-03T00:00:00Z display_name: hr running: true page_size: 80 } will return up to 80 migration jobs that were created on or after 2025-10-02T10:15:33 UTC and before 2025-10-03T00:00:00 UTC and have hr in their display name and are currently running. If there are more than 80 such jobs, a nextPageToken value (like CgtteS1qb2IxM) will be returned and you can use it in the next call to retrieve the next page of results.
get_operation

Gets the status of a long-running operation.

Usage

Some tools (for example, start_migration_job) return a long-running operation. You can use this tool to get the status of the operation. It can be called repeatedly until the operation is complete.

Parameters

  • 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

  • An Operation object that contains the status of the operation.
  • If the operation is not complete, the response will be empty. Use a command line tool to pause for 10 seconds before rechecking the status.
  • If the operation is complete, the response will contain either:
    • A response field that contains the result of the operation and indicates that it was successful.
    • A error field that indicates any errors that occurred during the operation.
get_migration_job

Get details of the migration job specified by the provided resource name parameter.

  • The resource name parameter is in the form: projects/{project name}/locations/{location}/migrationJobs/{migration job name}, for example: projects/my-project/locations/us-central1/migrationJobs/my-migration-job.
start_migration_job

Starts an already created migration job, specified by the provided resource name parameter.

  • The resource name parameter is in the form: projects/{project name}/locations/{location}/migrationJobs/{migration job name}, for example: projects/my-project/locations/us-central1/migrationJobs/my-migration-job.
  • Use the optional 'skipValidation' parameter to specify whether to start the migration job without running prior configuration verification. The default is 'false'.
  • This tool returns a long-running operation. Use the 'get_operation' tool with the returned operation name to poll its status until it completes. Operation may take several minutes; use a command line tool to pause for 10 seconds before rechecking the status as needed.
stop_migration_job

Stops an already started migration job, specified by the provided resource name parameter.

  • The resource name parameter is in the form: projects/{project name}/locations/{location}/migrationJobs/{migration job name}, for example: projects/my-project/locations/us-central1/migrationJobs/my-migration-job.
  • This tool returns a long-running operation. Use the 'get_operation' tool with the returned operation name to poll its status until it completes. Operation may take several minutes; use a command line tool to pause for 10 seconds before rechecking the status as needed.
resume_migration_job

Resume a migration job that is currently stopped and is resumable (was stopped during CDC phase). Migration job is specified by the provided resource name parameter.

  • The resource name parameter is in the form: projects/{project name}/locations/{location}/migrationJobs/{migration job name}, for example: projects/my-project/locations/us-central1/migrationJobs/my-migration-job.
  • Use the optional 'skipValidation' parameter to specify whether to resume the migration job without running prior configuration verification. The default is 'false'.
  • This tool returns a long-running operation. Use the 'get_operation' tool with the returned operation name to poll its status until it completes. Operation may take several minutes; use a command line tool to pause for 10 seconds before rechecking the status as needed.
delete_migration_job

Deletes a migration job, specified by the provided resource name parameter.

  • The resource name parameter is in the form: projects/{project name}/locations/{location}/migrationJobs/{migration job name}, for example: projects/my-project/locations/us-central1/migrationJobs/my-migration-job.
  • This tool returns a long-running operation. Use the 'get_operation' tool with the returned operation name to poll its status until it completes. Operation may take several minutes; use a command line tool to pause for 10 seconds before rechecking the status as needed.

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://datamigration.googleapis.com/mcp' \
--header 'content-type: application/json' \
--header 'accept: application/json, text/event-stream' \
--data '{
    "method": "tools/list",
    "jsonrpc": "2.0",
    "id": 1
}'