Tool: translate_query
Translates a single query into BigQuery SQL syntax.
The following sample demonstrate how to use curl to invoke the translate_query MCP tool.
| Curl Request |
|---|
curl --location 'https://bigquerymigration.googleapis.com/mcp' \ --header 'content-type: application/json' \ --header 'accept: application/json, text/event-stream' \ --data '{ "method": "tools/call", "params": { "name": "translate_query", "arguments": { // provide these details according to the tool's MCP specification } }, "jsonrpc": "2.0", "id": 1 }' |
Input Schema
Request message for TranslateQuery.
TranslateQueryRequest
| JSON representation |
|---|
{ "parent": string, "inputQuery": string, "sourceDialect": string, "metadataFilePath": string } |
| Fields | |
|---|---|
parent |
Required. The parent resource name where the translation is performed. Format: |
inputQuery |
Required. The query string to be translated. |
sourceDialect |
Required. The dialect of the source query. Supported dialects are Teradata, Bteq, Redshift, Oracle, HiveQL, Impala, SparkSQL, Snowflake, Netezza, AzureSynapse, Vertica, SQLServer, Presto, MySQL, Postgresql, BigQuery, Db2, Greenplum, and SQLite. |
metadataFilePath |
Optional. The path to the metadata file in Cloud Storage. Format: |
Output Schema
Response message for TranslateQuery.
TranslateQueryResponse
| JSON representation |
|---|
{ "translatedQuery": string, "translationId": string, "translationState": string, "translationLogs": [ { object ( |
| Fields | |
|---|---|
translatedQuery |
The translated query. |
translationId |
The ID of the migration workflow created for this translation. Use this ID as the name for |
translationState |
The current state of the translation, for example, |
translationLogs[] |
A list of logs generated during the translation process. Tip: If you're using an AI client, these logs can be used to troubleshoot issues and to improve translation quality. You should persist these logs so users can see them in the UI and use them for troubleshooting or improving translation quality. |
errorInfo |
The error information. |
Log
| JSON representation |
|---|
{ "severity": string, "category": string, "message": string, "action": string, "effect": string, "impactedObject": string } |
| Fields | |
|---|---|
severity |
Severity of the translation record, for example, |
category |
Category of the error or warning, for example, |
message |
Detailed message of the record. |
action |
Recommended action to address the log. |
effect |
The effect or impact of the issue noted in the log. Effect can be one of the following values: |
impactedObject |
Name of the object that is impacted by the log message. |
ErrorInfo
| JSON representation |
|---|
{ "reason": string, "domain": string, "metadata": { string: string, ... } } |
| Fields | |
|---|---|
reason |
The reason of the error. This is a constant value that identifies the proximate cause of the error. Error reasons are unique within a particular domain of errors. This should be at most 63 characters and match a regular expression of |
domain |
The logical grouping to which the "reason" belongs. The error domain is typically the registered service name of the tool or product that generates the error. Example: "pubsub.googleapis.com". If the error is generated by some common infrastructure, the error domain must be a globally unique value that identifies the infrastructure. For Google API infrastructure, the error domain is "googleapis.com". |
metadata |
Additional structured details about this error. Keys must match a regular expression of An object containing a list of |
MetadataEntry
| JSON representation |
|---|
{ "key": string, "value": string } |
| Fields | |
|---|---|
key |
|
value |
|
Tool Annotations
Destructive Hint: ❌ | Idempotent Hint: ❌ | Read Only Hint: ❌ | Open World Hint: ❌