Integration · Developer tools

Connect Claude & ChatGPT to Google Vertex AI

Let your AI work with your own Google Cloud project in Vertex AI. It can send prompts to Gemini and other Google models, count tokens before a request, create text embeddings and run predictions on models you have deployed to an endpoint. It can also create RAG corpora and import files into them, manage context caches, and follow batch prediction and tuning jobs.

Connect Google Vertex AI free

Free plan, no credit card. Takes about a minute.

Try asking

“Ask gemini-2.5-flash in our project to summarize this contract.”
The AI sends the text to the model in your Vertex AI project and region and returns the model's answer.
“How many tokens does this prompt use?”
It counts the tokens for the model you name before anything is generated.
“Make an embedding of this product description.”
It creates a text embedding with a Google embedding model and returns the vector.

What your AI can do

Generate and embed

Send prompts to Gemini and other Google models, count tokens, create embeddings and run predictions on deployed endpoints.

RAG corpora and caches

Create RAG corpora, import or upload files, list their files, and create, update or delete context caches.

Jobs and endpoints

List endpoints, deploy and undeploy models, and create, follow, cancel or delete batch prediction and tuning jobs.

“Create a RAG corpus called Support docs and import our files from Cloud Storage.”
It creates the corpus, then starts an import of the files and gives you the operation to follow.
“Which context caches do we have, and when do they expire?”
It lists the context caches in the project with their model and expiry time.
“Did our tuning job finish?”
It lists tuning jobs in the project and reads the state of the one you pick.

92 tools for Google Vertex AI

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

cancel_operationDeletesCancel a operation (operations id). Destructive action; may require approval. API summary: Starts asynchronous cancellation on a long-running operation.
cancel_operation_aiplatform_projects_locations_endpoints_operatiDeletesCancel a operation (operations id). Destructive action; may require approval. API summary: Starts asynchronous cancellation on a long-running operation.
cancel_operation_aiplatform_projects_locations_tuning_jobs_operaDeletesCancel a operation (operations id). Destructive action; may require approval. API summary: Starts asynchronous cancellation on a long-running operation.
cancel_operation_cancelDeletesCancel a operation (operations id). Destructive action; may require approval. API summary: Starts asynchronous cancellation on a long-running operation.
cancel_projectDeletesCancel a project (tuning jobs id). Destructive action; may require approval. API summary: Cancels a tuning job.
cancel_project_cancelMoves moneyCancel a project (batch prediction jobs id). Financial or irreversible action; may require approval. API summary: Cancels a BatchPredictionJob.
count_tokensDeletesCount how many tokens a prompt uses for a Google model before sending it. Pass `publishers_id`, `models_id` and `contents`.
create_cached_contentChanges dataCreate a context cache for a Gemini model with `model`, `contents` and optional `system_instruction`, plus a `ttl` or `expire_time`. Caches are billed for storage while they exist.
create_compactChanges dataCreate a new compact. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
create_completionChanges dataCreate a new completion. API summary: Exposes an OpenAI-compatible endpoint for chat completions.
create_completion_aiplatform_projects_locations_endpoints_openapChanges dataCreate a new completion. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
create_compute_tokenDeletesCreate a new compute token. Destructive action; may require approval. API summary: Return a list of tokens based on the input text.
create_compute_token_aiplatform_projects_locations_endpoints_comDeletesCreate a new compute token. Destructive action; may require approval. API summary: Return a list of tokens based on the input text.
create_deploy_modelChanges dataCreate a new deploy model. API summary: Deploys a Model into this Endpoint, creating a DeployedModel within it.
create_direct_predictChanges dataCreate a new direct predict. API summary: Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.
create_direct_raw_predictChanges dataCreate a new direct raw predict. API summary: Perform an unary online prediction request to a gRPC model server for custom containers.
create_embeddingChanges dataCreate a new embedding. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
create_explainChanges dataCreate a new explain. API summary: Perform an online explanation.
create_generate_content_aiplatform_projects_locations_endpoints_Changes dataCreate a new generate content. API summary: Generate content with multimodal inputs.
create_inferenceChanges dataCreate a new inference. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
create_location_endpointChanges dataCreate a new endpoint for a location. Search endpoints first to avoid duplicates. API summary: Creates an Endpoint.
create_location_projectChanges dataCreate a new project for a location. Search projects first to avoid duplicates. API summary: Creates a tuning job.
create_location_project_aiplatform_projects_locations_batch_predVisible to othersCreate a new project for a location. Search projects first to avoid duplicates. Has effects visible outside this system. API summary: Creates a BatchPredictionJob.
create_location_tuning_jobs_rebase_tuned_modelChanges dataCreate a new tuning jobs rebase tuned model for a location. API summary: Rebase a tuned model.
create_mutate_deployed_modelChanges dataCreate a new mutate deployed model. API summary: Updates an existing deployed model.
create_predict_aiplatform_projects_locations_endpoints_predictChanges dataCreate a new predict.
create_predict_long_runningChanges dataCreate a new predict long running.
create_predict_long_running_aiplatform_projects_locations_endpoiChanges dataCreate a new predict long running.
create_rag_corpora_document_aiplatform_projects_locations_rag_coChanges dataCreate a new document for a rag corpora. API summary: Import files from Google Cloud Storage or Google Drive into a RagCorpus.
create_rag_corpusChanges dataCreate a new RAG corpus with a `display_name` and optional `description`. Returns a long-running operation.
create_raw_predictChanges dataCreate a new raw predict. API summary: Perform an online prediction with an arbitrary HTTP payload.
create_raw_predict_aiplatform_projects_locations_endpoints_raw_pChanges dataCreate a new raw predict. API summary: Perform an online prediction with an arbitrary HTTP payload.
create_responseChanges dataCreate a new response. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
create_response_aiplatform_projects_locations_endpoints_openapi_Changes dataCreate a new response. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
create_server_streaming_predictChanges dataCreate a new server streaming predict. API summary: Perform a server-side streaming online prediction request for Vertex LLM streaming.
create_server_streaming_predict_aiplatform_projects_locations_enChanges dataCreate a new server streaming predict. API summary: Perform a server-side streaming online prediction request for Vertex LLM streaming.
create_stream_generate_contentChanges dataCreate a new stream generate content. API summary: Generate content with multimodal inputs with streaming support.
create_stream_generate_content_aiplatform_projects_locations_endChanges dataCreate a new stream generate content. API summary: Generate content with multimodal inputs with streaming support.
create_stream_raw_predictChanges dataCreate a new stream raw predict. API summary: Perform a streaming online prediction with an arbitrary HTTP payload.
create_stream_raw_predict_aiplatform_projects_locations_endpointChanges dataCreate a new stream raw predict. API summary: Perform a streaming online prediction with an arbitrary HTTP payload.
create_undeploy_modelChanges dataCreate a new undeploy model. API summary: Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.
create_updateChanges dataCreate a new update. API summary: Updates an Endpoint with a long running operation.
create_waitChanges dataCreate a new wait. API summary: Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.
create_wait_aiplatform_projects_locations_endpoints_operations_wChanges dataCreate a new wait. API summary: Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.
create_wait_aiplatform_projects_locations_rag_corpora_rag_files_Changes dataCreate a new wait. API summary: Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.
create_wait_aiplatform_projects_locations_tuning_jobs_operationsChanges dataCreate a new wait. API summary: Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.
delete_cached_contentDeletesPermanently delete a context cache by `cached_contents_id`.
delete_endpoint_operationDeletesPermanently delete a operation by operations id. Destructive action; may require approval. API summary: Deletes a long-running operation.
delete_endpoint_responseDeletesPermanently delete a response by responses id. Destructive action; may require approval. API summary: Deletes the response from the endpoint.
delete_location_endpointDeletesPermanently delete a endpoint by endpoints id. Destructive action; may require approval. API summary: Deletes an Endpoint.
delete_location_projectMoves moneyPermanently delete a project by batch prediction jobs id. Financial or irreversible action; may require approval. API summary: Deletes a BatchPredictionJob.
delete_location_rag_corporaDeletesPermanently delete a rag corpora by rag corpora id. Destructive action; may require approval. API summary: Deletes a RagCorpus.
delete_project_operationDeletesPermanently delete a operation by operations id. Destructive action; may require approval. API summary: Deletes a long-running operation.
delete_rag_corpora_operationDeletesPermanently delete a operation by operations id. Destructive action; may require approval. API summary: Deletes a long-running operation.
delete_rag_fileDeletesPermanently remove one file from a RAG corpus by `rag_corpora_id` and `rag_files_id`.
delete_rag_file_operationDeletesPermanently delete a operation by operations id. Destructive action; may require approval. API summary: Deletes a long-running operation.
delete_responseDeletesPermanently delete a response by responses id. Destructive action; may require approval. API summary: Deletes the response from the endpoint.
embed_contentChanges dataCreate a text embedding with a Google embedding model. Pass `publishers_id` (google), the model name in `models_id` and `content` with the text parts; optional `task_type`.
generate_content_on_endpointChanges dataGenerate a response from a model deployed on your own endpoint (for example a tuned Gemini model). Pass `endpoints_id` and `contents`; optional `system_instruction` and `generation_config`.
get_batch_prediction_jobGet one batch prediction job by `batch_prediction_jobs_id`, including its state and output location.
get_cached_contentGet one context cache by `cached_contents_id`, including its model and expiry time.
get_endpointGet one endpoint by `endpoints_id`, including its deployed models and traffic split.
get_endpoint_operationGet one operation for a endpoint by operations id. API summary: Gets the latest state of a long-running operation.
get_endpoint_predict_operationChanges dataGet one endpoint by endpoints id. API summary: Fetch an asynchronous online prediction operation.
get_endpoint_responseGet one response for a endpoint by responses id. API summary: Gets the response from the endpoint.
get_location_project_aiplatform_projects_locations_batch_predictGet one project for a location by batch prediction jobs id. API summary: Gets a BatchPredictionJob.
get_model_predict_operationChanges dataGet one model by models id. API summary: Fetch an asynchronous online prediction operation.
get_project_operationGet one operation for a project by operations id. API summary: Gets the latest state of a long-running operation.
get_rag_corpusGet one RAG corpus by `rag_corpora_id`, including its status and settings.
get_rag_corpus_operationCheck the progress of a RAG corpus operation (such as a file import) by `rag_corpora_id` and `operations_id`.
get_rag_fileGet one file in a RAG corpus by `rag_corpora_id` and `rag_files_id`.
get_rag_file_operationGet one operation for a rag file by operations id. API summary: Gets the latest state of a long-running operation.
get_responseGet one response by responses id. API summary: Gets the response from the endpoint.
import_rag_filesChanges dataImport files into a RAG corpus by `rag_corpora_id` from Cloud Storage, Google Drive, Slack, Jira or SharePoint, set in `import_rag_files_config`. Returns an operation to check with get_rag_corpus_operation.
list_batch_prediction_jobsList batch prediction jobs in the project, with an optional `filter`.
list_cached_contentsList context caches (saved prompt content reused across Gemini requests) in the project.
list_endpointsList the project's Vertex AI endpoints (deployed models), with optional `filter` and `order_by`.
list_rag_corporaList the project's RAG corpora (document collections used for retrieval).
list_rag_filesList the files in a RAG corpus by `rag_corpora_id`.
predict_on_endpointChanges dataRun an online prediction on a model deployed to your endpoint by `endpoints_id`, with `instances` and optional `parameters`.
search_endpoint_operationsSearch operations for a endpoint by return partial success or filter. Use this to find existing operations before creating a new operation. Results are paginated. API summary: Lists operations that match the specified filter in the request.
search_location_projects_aiplatform_projects_locations_batch_preSearch projects for a location by read mask or filter. Use this to find existing projects before creating a new project. Results are paginated. API summary: Lists BatchPredictionJobs in a Location.
search_project_operationsSearch operations for a project by filter or return partial success. Use this to find existing operations before creating a new operation. Results are paginated. API summary: Lists operations that match the specified filter in the request.
search_rag_corpora_operationsSearch operations for a rag corpora by return partial success or filter. Use this to find existing operations before creating a new operation. Results are paginated. API summary: Lists operations that match the specified filter in the request.
search_rag_file_operationsSearch operations for a rag file by filter or return partial success. Use this to find existing operations before creating a new operation. Results are paginated. API summary: Lists operations that match the specified filter in the request.
submit_endpoint_tokensDeletesCount a endpoint (endpoints id). Destructive action; may require approval. API summary: Perform a token counting.
update_deployed_model_invokeChanges dataUpdate an existing invoke identified by invoke id. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
update_endpoint_invokeChanges dataUpdate an existing invoke identified by invoke id. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.
update_location_cached_contentChanges dataUpdate an existing cached content identified by cached contents id. Only the fields you pass are changed. API summary: Updates cached content configurations.
update_location_endpointChanges dataUpdate an existing endpoint identified by endpoints id. Only the fields you pass are changed. API summary: Updates an Endpoint.
update_location_rag_corporaChanges dataUpdate an existing rag corpora identified by rag corpora id. Only the fields you pass are changed. API summary: Updates a RagCorpus.
update_model_invokeChanges dataUpdate an existing invoke identified by invoke id. API summary: Forwards arbitrary HTTP requests for both streaming and non-streaming cases.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Google Vertex AI from the app list.
2
Paste your key
Paste the OAuth client ID and client secret from your own Google Cloud project, plus your project ID and Vertex AI region (for example us-central1), then sign in with Google once. In the Google Cloud console create a project with billing and enable the Vertex AI API. Set up the OAuth consent screen, then under Credentials create an OAuth client ID of type Web application with the redirect URI https://heymyapps.com/oauth/callback.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Google Vertex AI?

It can generate content with Gemini and other Google models, count tokens, create embeddings and run predictions on deployed endpoints. It can create and manage RAG corpora and their files, context caches, endpoints, batch prediction jobs and tuning jobs, and cancel or delete them if you switch those tools on.

Does the AI see my Google Vertex AI credentials?

No. Your Google Vertex AI credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with generating content and reading jobs. Deleting a RAG corpus, a cache or an endpoint is permanent, and cancelling or deleting a batch prediction job cannot be undone, so those actions can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

Google Vertex AI connects with OAuth, and this OAuth connection needs the HeyMyApps Pro plan. HeyMyApps also has a free plan with no credit card, but it does not include this connection. Paid plans bill per completed task. You also need your own Google Cloud project with the Vertex AI API enabled.

Which project and region does the AI use?

It uses the Google Cloud project ID and region you enter when you connect, for example us-central1 or europe-west4. Models, caches, corpora and jobs are created and read in that project and region, and any Vertex AI usage is billed to your own Google Cloud account.