Integration · Developer tools
Connect Claude & ChatGPT to Google AI Studio
Ask your AI to get a second answer from Gemini, or to check how many tokens a long prompt uses. With your Gemini API key it can list models, send prompts to a Gemini model, count tokens and create embeddings. It can also manage uploaded files, context caches, File Search stores and batch jobs for your key.
Free plan, no credit card. Takes about a minute.
Try asking
“Which Gemini models can my key use, and what are their token limits?”
The AI lists the models available to your key with token limits and supported methods.
“Ask gemini-2.5-flash to summarize this text in three bullet points.”
It sends the prompt to the model and returns the reply. This uses your Gemini API quota.
“How many tokens is this document for gemini-2.5-flash?”
It counts the tokens for that model without generating anything.
What your AI can do
Models and prompts
List models, send prompts with an optional system instruction, count tokens and create embeddings.
Files and File Search
List, read and delete uploaded files, create File Search stores and import files so Gemini can search them.
Caches and batches
Create, read and delete context caches, and follow or cancel batch jobs.
“Create an embedding for this product description.”
It sends the text to an embedding model and returns the embedding vector.
“Which files have I uploaded? Delete the ones I no longer need.”
It lists the files in the Files API and deletes the ones you choose. A deleted file cannot be restored.
“Is my batch job finished?”
It lists your batch jobs and shows the progress and output location of the one you ask about.
18 tools for Google AI Studio (Gemini)
These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.
cancel_batchDeletesCancel a running batch job by batches_id.count_tokensDeletesCount how many tokens a prompt uses for a model: models_id and contents. Does not generate anything.create_cached_contentChanges dataCache large prompt content for reuse: model, contents, optional system_instruction and ttl (e.g. '3600s'). Cached storage is billed.delete_cached_contentDeletesDelete a context cache by cached_contents_id.delete_fileDeletesDelete an uploaded file by files_id. This cannot be undone.embed_contentChanges dataTurn text into an embedding vector with an embedding model: models_id and content = {parts: [{text}]}; optional task_type.generate_contentChanges dataSend a prompt to a Gemini model and get its reply. Pass models_id and contents = [{role: 'user', parts: [{text}]}]; optional system_instruction, generation_config and tools. Uses paid API quota.get_batchGet one batch job by batches_id, with progress and output location.get_cached_contentGet one context cache by cached_contents_id.get_fileGet one uploaded file by files_id, with its URI, type, size and state.get_modelGet details of one model by models_id (e.g. gemini-2.5-flash).import_file_to_storeChanges dataImport an uploaded file (file_name, e.g. files/abc-123) into a File Search store by file_search_stores_id so Gemini can search it.list_batchesList batch jobs and their status.list_cached_contentsList context caches (saved prompt content reused across requests).list_file_search_storesList File Search stores (document collections Gemini can search).list_filesList files uploaded to the Gemini Files API (they expire after a short time).list_modelsList the Gemini models available to your API key, with token limits and supported methods.list_store_documentsList the documents in a File Search store by file_search_stores_id.
Set up in three steps
- 1
Pick the app
Create a free PipMCP account and choose Google AI Studio (Gemini) from the app list.
- 2
Paste your key
Paste a Gemini API key. In Google AI Studio open Get API key, click Create API key and copy it.
- 3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
- Click your name, then Settings › Connectors › Add custom connector.
- Paste your link as the Remote MCP server URL.
- Switch it on from the + menu in a chat.
Questions
What can the AI do in Google AI Studio?
It can list and read Gemini models, send prompts and get replies, count tokens and create embeddings. It can list, read and delete uploaded files, create and delete context caches, create File Search stores, list their documents and import files into them, and list, read and cancel batch jobs.
Does the AI see my Google AI Studio credentials?
No. Your Google AI Studio 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, for example token counting and model lists but not prompts. Prompts use your API quota, caches are billed for storage, and deleting a file or cache cannot be undone, so those tools 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 PipMCP 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?
PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Gemini API key.
Who pays for the Gemini requests?
Requests run on your own Gemini API key, so any usage and charges are between you and Google, the same as when you call the API yourself. Context caches are also billed for storage while they exist. PipMCP is an independent service and is not affiliated with Google.
Related integrations
Let your AI work in Google AI Studio (Gemini) today.
Start free. Your key stays encrypted, and you decide what the AI may do.
Connect Google AI Studio (Gemini) freePipMCP is not affiliated with Google AI Studio (Gemini). Product names are trademarks of their owners.