Skip to directory

Gemini Enterprise Agent Platform MCP

Google Cloud

Streamable HTTP56 documented tools0

About Gemini Enterprise Agent Platform MCP

Google Cloud managed MCP server for Gemini Enterprise Agent Platform. Exact tool names and accessible operations depend on the published server reference and configured Google Cloud permissions.

Connection and setup
Hosting
Google-managed remote
Transport
Streamable HTTP
Endpoint
https://aiplatform.googleapis.com/mcp/generate
Authentication
Google Cloud authentication: OAuth 2.0 using Application Default Credentials (ADC) in supported Google clients, or a client OAuth ID/secret or bearer token in compatible third-party clients. The principal needs mcp.tools.call plus the underlying product permissions; API key authentication is only available for services that explicitly support it.

Requirements

  • A Google Cloud project and access to the target product/resource.
  • Enable this MCP service and its underlying Google Cloud API as required by the product guide.
  • An MCP client that supports Streamable HTTP.
  • An identity with the MCP Tool User role (roles/mcp.toolUser) or equivalent mcp.tools.call permission, plus permissions for the underlying product operations.

Setup steps

  1. Choose the correct global or regional endpoint for your data location; this catalog lists the documented endpoint.
  2. In the Google Cloud project, enable the MCP service and the underlying product API if the product guide requires it.
  3. Authenticate the client with Google Cloud ADC (simplest with Antigravity/Gemini CLI) or configure OAuth 2.0 credentials in a compatible client.
  4. Grant the connecting identity roles/mcp.toolUser and only the product IAM roles needed for the intended operations.
  5. Add aiplatform.googleapis.com to the client as a Streamable HTTP MCP server and complete sign-in.
  6. Refresh the client tool list and check that the tools match the product reference; availability may depend on permissions and selected toolset.
Tools 56

56 tools combine multiple Agent Platform toolsets for endpoints, prompts, models, tuning, prediction/generation, RAG and Colab notebooks/schedules. CRUD and notebook operations can change deployed model/agent resources and incur charges; prediction/generation may process sensitive prompts/data. Toolsets are split across separate endpoint URLs; verify selected endpoint/toolset and IAM.

  • create_endpoint
    01
  • get_endpoint
    02
  • list_endpoints
    03
  • update_endpoint
    04
  • delete_endpoint
    05
  • create_prompt
    06
  • get_prompt
    07
  • list_prompts
    08
  • update_prompt
    09
  • delete_prompt
    10
  • upload_model
    11
  • list_models
    12
  • get_model
    13
  • update_model
    14
  • delete_model
    15
  • get_operation
    16
  • evaluate_instances
    17
  • list_tuning_jobs
    18
  • get_tuning_job
    19
  • cancel_tuning_job
    20
  • predict
    21
  • raw_predict
    22
  • generate_content
    23
  • count_tokens
    24
  • embed_content
    25
  • retrieve_contexts
    26
  • augment_prompt
    27
  • corroborate_content
    28
  • ask_contexts
    29
  • create_rag_corpus
    30
  • list_rag_corpora
    31
  • delete_rag_corpus
    32
  • import_rag_files
    33
  • colab_enterprise_create_notebook_runtime_template
    34
  • colab_enterprise_get_notebook_runtime_template
    35
  • colab_enterprise_list_notebook_runtime_templates
    36
  • colab_enterprise_delete_notebook_runtime_template
    37
  • colab_enterprise_update_notebook_runtime_template
    38
  • colab_enterprise_create_notebook_runtime
    39
  • colab_enterprise_get_notebook_runtime
    40
  • colab_enterprise_list_notebook_runtimes
    41
  • colab_enterprise_delete_notebook_runtime
    42
  • colab_enterprise_upgrade_notebook_runtime
    43
  • colab_enterprise_start_notebook_runtime
    44
  • colab_enterprise_stop_notebook_runtime
    45
  • notebook_execution_create_job
    46
  • notebook_execution_get_job
    47
  • notebook_execution_list_jobs
    48
  • notebook_execution_delete_job
    49
  • create_notebook_execution_schedule
    50
  • delete_notebook_execution_schedule
    51
  • get_notebook_execution_schedule
    52
  • list_notebook_execution_schedules
    53
  • pause_notebook_execution_schedule
    54
  • resume_notebook_execution_schedule
    55
  • update_notebook_execution_schedule
    56
Original sources
  • official setup guide

    Google Cloud describes remote MCP client setup, Streamable HTTP transport, supported authentication options, and ADC setup.

  • official authentication guide

    Google documents supported identity types and authorization requirements for Google Cloud MCP calls.

  • official source

    Official Google Cloud primary MCP documentation checked 2026-10-28.

  • official source

    Official Google Cloud primary MCP documentation checked 2026-10-28.

Documentation checked 2026-10-28. Connection has not been runtime tested.