Skip to content
Changelog

Report a bug

Gemini integration: operations for AI agents

Gemini connects to Type.com as an integration. This page lists the 94 operations documented for Claude and Codex in Type.com: 41 read, 40 write, 13 destructive.

About Gemini

Comprehensive Gemini integration supporting Veo 3 video generation, Gemini Flash text generation (Nano Banana), chat completions, and multimodal AI capabilities via the Google Gemini API.

Categories: Developer Tools & IT

How to connect Gemini to Type.com

Connect
No credential configured in the catalog
Access
Organization connection: one shared account for the workspace.
MCP
Selected AI media-generation operations are not available through Type’s MCP server. Other operations remain available through MCP, subject to your connection’s permissions. These MCP restrictions do not apply within Type.

To add the connection, follow the steps in Space connections.

Documented operations

94 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

94 operations listed.

  • Read

    Get File Search Store

    Gets information about a specific FileSearchStore.

  • Read

    Get Tuned Model

    Gets information about a specific TunedModel.

  • Read

    Get Environment Files Http By Environment

    Retrieves file metadata or directory contents from an environment's snapshot. To download file contents directly, pass ?alt=media or use the files.download helper.

  • Read

    Get Environment

    Gets an environment.

  • Read

    Get Permission

    Gets information about a specific Permission.

  • Read

    Get Environment Files Http

    Retrieves file metadata or directory contents from an environment's snapshot. To download file contents directly, pass ?alt=media or use the files.download helper.

  • Read

    Count Tokens

    Runs a model's tokenizer on input Content and returns the token count. Refer to the tokens guide to learn more about tokens.

  • Read

    List Documents

    Lists all Documents in a Corpus.

  • Read

    Count Message Tokens

    Runs a model's tokenizer on a string and returns the token count.

  • Read

    Get Operation By Generated File And Operation

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Read

    List Models

    Lists the Models available through the Gemini API.

  • Read

    Get Operation By Generate Content Batch

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Read

    List Operations By

    Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.

  • Read

    List Environments

    Lists environments.

  • Read

    Get Cached Content

    Reads CachedContent resource.

  • Read

    List Operations

    Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.

  • Read

    List Files

    Lists the metadata for Files owned by the requesting project.

  • Read

    Get Generated File

    Gets a generated file. When calling this method via REST, only the metadata of the generated file is returned. To retrieve the file content via REST, add alt=media as a query parameter.

  • Read

    List Environments Http

    Lists environments.

  • Read

    List Generated Files

    Lists the generated files owned by the requesting project.

  • Read

    Get Environment Http

    Gets an environment.

  • Read

    List Permissions By Corpus

    Lists permissions for the specific resource.

  • Read

    Download Media

    Downloads media from a FileSearchStore.

  • Read

    Get Model

    Gets information about a specific Model such as its version number, token limits, parameters and other metadata. Refer to the Gemini models guide for detailed model information.

  • Read

    Get File

    Gets the metadata for the given File.

  • Read

    Get Operation By File Search Stores Id And Operations Id

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Read

    Count Text Tokens

    Runs a model's tokenizer on a text and returns the token count.

  • Read

    Get Operation

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Read

    Get Document

    Gets information about a specific Document.

  • Read

    List Operations By Model

    Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.

  • Read

    List Cached Contents

    Lists CachedContents.

  • Read

    Get Operation By Corpus And Operation

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Read

    List Corpora

    Lists all Corpora owned by the user.

  • Read

    Get Operation By File Search Store And Operation

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Read

    Get Permission By Corpus And Permission

    Gets information about a specific Permission.

  • Read

    List Tuned Models

    Lists created tuned models.

  • Read

    Get Corpus

    Gets information about a specific Corpus.

  • Read

    List File Search Stores

    Lists all FileSearchStores owned by the user.

  • Read

    List Permissions

    Lists permissions for the specific resource.

  • Read

    Download File

    Download the File.

  • Read

    Get Operation By Model And Operation

    Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

  • Write

    Update Tuned Model

    Updates a tuned model.

  • Write

    Generate Text

    Generates a response from the model given an input message.

  • Write

    Update Permission

    Updates the permission.

  • Write

    Import File

    Imports a File from File Service to a FileSearchStore.

  • Write

    Batch Embed Contents

    Generates multiple embedding vectors from the input Content which consists of a batch of strings represented as EmbedContentRequest objects.

  • Write

    Embed Content

    Generates a text embedding vector from the input Content using the specified Gemini Embedding model.

  • Write

    Stream Generate Content

    Generates a streamed response from the model given an input GenerateContentRequest.

  • Write

    Predict

    Performs a prediction request.

  • Write

    Create Token

    Creates a token that can be used to constrain the behavior of a BidiGenerateContent session.

  • Write

    Generate Text By Tuned Model

    Generates a response from the model given an input message.

  • Write

    Upload To File Search Store

    Uploads data to a FileSearchStore, preprocesses and chunks before storing it in a FileSearchStore Document.

  • Write

    Generate Content By Tuned Model

    Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. Refer to the model guide and tuning guide for details.

  • Write

    Batch Embed Text

    Generates multiple embeddings from the model given input text in a synchronous call.

  • Write

    Async Batch Embed Content By Tuned Model

    Enqueues a batch of EmbedContent requests for batch processing. We have a BatchEmbedContents handler in GenerativeService, but it was synchronized. So we name this one to be Async to avoid confusion.

  • Write

    Transfer Ownership

    Transfers ownership of the tuned model. This is the only way to change ownership of the tuned model. The current owner will be downgraded to writer role.

  • Write

    Async Batch Embed Content

    Enqueues a batch of EmbedContent requests for batch processing. We have a BatchEmbedContents handler in GenerativeService, but it was synchronized. So we name this one to be Async to avoid confusion.

  • Write

    Generate Content

    Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. Refer to the model guide and tuning guide for details.

  • Write

    Embed Text

    Generates an embedding from the model given an input message.

  • Write

    Generate Message

    Generates a response from the model given an input MessagePrompt.

  • Write

    Update Cached Content

    Updates CachedContent resource (only expiration is updatable).

  • Write

    Create File

    Creates a File.

  • Write

    Create Environment

    Creates an environment.

  • Write

    Stream Generate Content By Tuned Model

    Generates a streamed response from the model given an input GenerateContentRequest.

  • Write

    Create Environment Http

    Creates an environment.

  • Write

    Create Permission By Corpus

    Create a permission to a specific resource.

  • Write

    Generate Answer

    Generates a grounded answer from the model given an input GenerateAnswerRequest.

  • Write

    Stream Generate Content By Dynamic Id

    Generates a streamed response from the model given an input GenerateContentRequest.

  • Write

    Batch Generate Content

    Enqueues a batch of GenerateContent requests for batch processing.

  • Write

    Batch Generate Content By Tuned Model

    Enqueues a batch of GenerateContent requests for batch processing.

  • Write

    Update Embed Content Batch

    Updates a batch of EmbedContent requests for batch processing.

  • Write

    Predict Long Running

    Same as Predict but returns an LRO.

  • Write

    Update Generate Content Batch

    Updates a batch of GenerateContent requests for batch processing.

  • Write

    Create Cached Content

    Creates CachedContent resource.

  • Write

    Register Files

    Registers a Google Cloud Storage files with FileService. The user is expected to provide Google Cloud Storage URIs and will receive a File resource for each URI in return. Note that the files are not copied, just registered with File API.

  • Write

    Create Corpus

    Creates an empty Corpus.

  • Write

    Generate Content By Dynamic Id

    Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. Refer to the model guide and tuning guide for details.

  • Write

    Update Permission By Corpus And Permission

    Updates the permission.

  • Write

    Create Tuned Model

    Creates a tuned model. Check intermediate tuning progress (if any) through the [google.longrunning.Operations] service. Access status and results through the Operations service. Example: GET /v1/tunedModels/az2mb0bpw6i/operations/000-111-222

  • Write

    Create File Search Store

    Creates an empty FileSearchStore.

  • Write

    Create Permission

    Create a permission to a specific resource.

  • Destructive

    Cancel Operation

    Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.

  • Destructive

    Delete File Search Store

    Deletes a FileSearchStore.

  • Destructive

    Delete Tuned Model

    Deletes a tuned model.

  • Destructive

    Delete Permission

    Deletes the permission.

  • Destructive

    Upload Environment File Http

    Uploads (creates or updates) a file in an environment's workspace.

  • Destructive

    Delete Operation

    Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.

  • Destructive

    Delete Cached Content

    Deletes CachedContent resource.

  • Destructive

    Delete Environment Http

    Deletes an environment.

  • Destructive

    Delete File

    Deletes the File.

  • Destructive

    Delete Document

    Deletes a Document.

  • Destructive

    Delete Permission By Corpus And Permission

    Deletes the permission.

  • Destructive

    Delete Corpus

    Deletes a Corpus.

  • Destructive

    Delete Environment

    Deletes an environment.

See How connections work for access and permissions, or browse all integrations.