npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

vertex-ai-mcp

v1.6.0

Published

MCP server for Google Vertex AI — 180+ tools covering datasets, endpoints, models, indexes, featurestores, pipelines, tensorboards, and more

Downloads

1,748

Readme

vertex-ai-mcp

MCP server for Google Vertex AI with 197 tools covering Imagen image generation, Gemini text generation, embeddings, datasets, endpoints, models, indexes, featurestores, pipelines, tensorboards, metadata, and more.

Installation

Using npx (recommended)

{
  "mcpServers": {
    "vertex-ai": {
      "command": "npx",
      "args": ["-y", "vertex-ai-mcp"],
      "env": {
        "GOOGLE_PROJECT_ID": "your-project-id",
        "GOOGLE_LOCATION": "us-central1"
      }
    }
  }
}

Local installation

npm install -g vertex-ai-mcp

Authentication

Recommended: Service account key file (required for all features including model discovery):

  1. Go to GCP Console → IAM → Service Accounts
  2. Create a service account with the Vertex AI User role
  3. Download the JSON key file
  4. Set the env var:
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"

Or in your MCP config:

{
  "mcpServers": {
    "vertex-ai": {
      "command": "npx",
      "args": ["-y", "vertex-ai-mcp"],
      "env": {
        "GOOGLE_PROJECT_ID": "your-project-id",
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account-key.json"
      }
    }
  }
}

Alternative methods (work for project-scoped endpoints but NOT model discovery):

  • gcloud auth application-default login — works for most tools but not vertex_list_publisher_models / vertex_get_publisher_model
  • Automatic on GCE, Cloud Run, GKE (metadata server)

Environment Variables

| Variable | Required | Default | Description | |----------|----------|---------|-------------| | GOOGLE_PROJECT_ID | Yes | - | Your Google Cloud project ID | | GOOGLE_LOCATION | No | us-central1 | Vertex AI region |

Tools (197)

Generative AI — Imagen, Gemini, Veo, Embeddings (16)

Model Discovery — Call vertex_list_publisher_models first if unsure which model to use. Returns all available models (Gemini, Imagen, Veo, embeddings, TTS, Lyria) from the live API. vertex_list_publisher_models, vertex_get_publisher_model

Imagen (Image Generation) vertex_generate_image, vertex_edit_image, vertex_upscale_image

Gemini (Text Generation) vertex_generate_content, vertex_stream_generate_content, vertex_count_tokens

Veo (Video Generation) vertex_generate_video

Embeddings vertex_embed_text, vertex_embed_multimodal

Cached Content vertex_create_cached_content, vertex_get_cached_content, vertex_list_cached_contents, vertex_update_cached_content, vertex_delete_cached_content

Local File Support

Generative AI tools accept local file paths as an alternative to base64-encoded data:

  • vertex_generate_content / vertex_stream_generate_content / vertex_count_tokens — pass a prompt string and filePaths array instead of building the full contents array
  • vertex_edit_image — pass imagePath / maskPath instead of base64
  • vertex_upscale_image — pass imagePath instead of base64
  • vertex_embed_multimodal — pass imagePath instead of base64
  • vertex_generate_video — pass imagePath instead of base64

Supported formats: PNG, JPEG, GIF, WebP, BMP, TIFF, PDF, MP4, MOV, AVI, MKV, WebM, MP3, WAV, FLAC, OGG, AAC, TXT, HTML, CSS, JS, JSON, CSV, XML.

Datasets (8)

vertex_create_dataset, vertex_get_dataset, vertex_list_datasets, vertex_delete_dataset, vertex_update_dataset, vertex_import_data, vertex_export_data, vertex_search_data_items

Endpoints (12)

vertex_create_endpoint, vertex_get_endpoint, vertex_list_endpoints, vertex_delete_endpoint, vertex_update_endpoint, vertex_deploy_model, vertex_undeploy_model, vertex_mutate_deployed_model, vertex_predict, vertex_raw_predict, vertex_explain, vertex_server_streaming_predict

Models (12)

vertex_upload_model, vertex_get_model, vertex_list_models, vertex_delete_model, vertex_update_model, vertex_delete_model_version, vertex_list_model_versions, vertex_merge_version_aliases, vertex_export_model, vertex_copy_model, vertex_get_model_evaluation, vertex_list_model_evaluations

Jobs (15)

vertex_create_custom_job, vertex_get_custom_job, vertex_list_custom_jobs, vertex_delete_custom_job, vertex_cancel_custom_job, vertex_create_batch_prediction_job, vertex_get_batch_prediction_job, vertex_list_batch_prediction_jobs, vertex_delete_batch_prediction_job, vertex_cancel_batch_prediction_job, vertex_create_hyperparameter_tuning_job, vertex_get_hyperparameter_tuning_job, vertex_list_hyperparameter_tuning_jobs, vertex_delete_hyperparameter_tuning_job, vertex_cancel_hyperparameter_tuning_job

Pipelines (10)

vertex_create_training_pipeline, vertex_get_training_pipeline, vertex_list_training_pipelines, vertex_delete_training_pipeline, vertex_cancel_training_pipeline, vertex_create_pipeline_job, vertex_get_pipeline_job, vertex_list_pipeline_jobs, vertex_delete_pipeline_job, vertex_cancel_pipeline_job

Indexes (13)

vertex_create_index, vertex_get_index, vertex_list_indexes, vertex_delete_index, vertex_update_index, vertex_upsert_datapoints, vertex_remove_datapoints, vertex_create_index_endpoint, vertex_get_index_endpoint, vertex_list_index_endpoints, vertex_delete_index_endpoint, vertex_deploy_index, vertex_undeploy_index

Featurestores (22)

vertex_create_featurestore, vertex_get_featurestore, vertex_list_featurestores, vertex_delete_featurestore, vertex_update_featurestore, vertex_search_features, vertex_batch_read_feature_values, vertex_create_entity_type, vertex_get_entity_type, vertex_list_entity_types, vertex_delete_entity_type, vertex_update_entity_type, vertex_read_feature_values, vertex_import_feature_values, vertex_export_feature_values, vertex_delete_feature_values, vertex_create_feature, vertex_get_feature, vertex_list_features, vertex_delete_feature, vertex_update_feature, vertex_batch_create_features

Feature Online Stores (13)

vertex_create_feature_online_store, vertex_get_feature_online_store, vertex_list_feature_online_stores, vertex_delete_feature_online_store, vertex_update_feature_online_store, vertex_create_feature_view, vertex_get_feature_view, vertex_list_feature_views, vertex_delete_feature_view, vertex_update_feature_view, vertex_fetch_feature_values, vertex_search_nearest_entities, vertex_sync_feature_view

Tensorboards (23)

vertex_create_tensorboard, vertex_get_tensorboard, vertex_list_tensorboards, vertex_delete_tensorboard, vertex_update_tensorboard, vertex_read_tensorboard_size, vertex_read_tensorboard_usage, vertex_batch_read_tensorboard_time_series_data, vertex_create_tensorboard_experiment, vertex_get_tensorboard_experiment, vertex_list_tensorboard_experiments, vertex_delete_tensorboard_experiment, vertex_write_tensorboard_experiment_data, vertex_create_tensorboard_run, vertex_get_tensorboard_run, vertex_list_tensorboard_runs, vertex_delete_tensorboard_run, vertex_write_tensorboard_run_data, vertex_create_tensorboard_time_series, vertex_get_tensorboard_time_series, vertex_list_tensorboard_time_series, vertex_delete_tensorboard_time_series, vertex_read_tensorboard_time_series_data

Metadata (18)

vertex_create_metadata_store, vertex_get_metadata_store, vertex_list_metadata_stores, vertex_delete_metadata_store, vertex_create_artifact, vertex_get_artifact, vertex_list_artifacts, vertex_update_artifact, vertex_purge_artifacts, vertex_create_context, vertex_get_context, vertex_list_contexts, vertex_update_context, vertex_purge_contexts, vertex_create_execution, vertex_get_execution, vertex_list_executions, vertex_update_execution

Schedules (7)

vertex_create_schedule, vertex_get_schedule, vertex_list_schedules, vertex_delete_schedule, vertex_update_schedule, vertex_pause_schedule, vertex_resume_schedule

Operations (5)

vertex_get_operation, vertex_list_operations, vertex_cancel_operation, vertex_delete_operation, vertex_wait_operation

Deployment Resource Pools (6)

vertex_create_deployment_resource_pool, vertex_get_deployment_resource_pool, vertex_list_deployment_resource_pools, vertex_delete_deployment_resource_pool, vertex_update_deployment_resource_pool, vertex_query_deployed_models

Tuning (5)

vertex_create_tuning_job, vertex_get_tuning_job, vertex_list_tuning_jobs, vertex_cancel_tuning_job, vertex_rebase_tuned_model

NAS Jobs (7)

vertex_create_nas_job, vertex_get_nas_job, vertex_list_nas_jobs, vertex_delete_nas_job, vertex_cancel_nas_job, vertex_get_nas_trial_detail, vertex_list_nas_trial_details

Specialist Pools (5)

vertex_create_specialist_pool, vertex_get_specialist_pool, vertex_list_specialist_pools, vertex_delete_specialist_pool, vertex_update_specialist_pool

Development

npm install
npm run build
npm test

License

MIT