io.github.nagarjunr/data-connectors-gcp-bucket — MCP Server for GCP Cloud Storage

This read-only MCP server provides access to Google Cloud Storage by listing objects in a specified bucket. It is designed as a data connector for working with bucket contents within developer workflows, including AI-agent and data-pipeline contexts.

🛠️ Key Features

Read-only MCP server
GCP Cloud Storage integration
Lists objects in a bucket

🚀 Use Cases

Data connectors for pipelines
Retrieving object listings from GCP buckets
Supporting RAG and LLM data access patterns

⚡ Developer Benefits

Connector-focused capability for GCP Cloud Storage
Useful in AI-agents and data-pipeline implementations

⚠️ Limitations

Only supports listing objects in a bucket (no write/update operations indicated)

Topics

ai-agents, connector, data-connectors, data-pipeline, google-cloud-storage, llm, onedrive, postgresql, python, rag, s3, sharepoint

Tools

Tool

Description

list_objects(prefix: str | None = None) -> list[str]

List object names in the configured bucket, optionally filtered by prefix

read_object_text(remote_path: str, max_bytes: int = 1_000_000) -> str

Read an object's content as UTF-8 text. Refuses (raises) objects larger than max_bytes rather than truncating.

get_signed_url(remote_path: str, expires_in_seconds: int = 300) -> str

Time-limited, read-only URL — for content beyond read_object_text's inline cap. Requires GOOGLE_APPLICATION_CREDENTIALS to point at a real service account key file (signing needs a private key, not metadata-server ADC).

upload()/download() are write/local-filesystem-shaped and aren't exposed.

The client is cached at module scope rather than rebuilt per call — GCPBucketClient's constructor makes a real network call (an SSL capability probe) plus Application Default Credentials resolution, and neither changes within a running server process.

Tested against a real fake-gcs-server container, not mocks.

Variable

Required

Notes

GCP_BUCKET_NAME

yes

GCS bucket name

GOOGLE_APPLICATION_CREDENTIALS

yes

Path to a service account JSON key (read-only storage role recommended). Read by the underlying google-auth library via Application Default Credentials, not by this server directly.

Use with an MCP client

json

{
  "mcpServers": {
    "gcp-bucket": {
      "command": "uvx",
      "args": ["--from", "data-connectors-ai[gcp,mcp]", "data-connectors-gcp-bucket-mcp"],
      "env": {
        "GCP_BUCKET_NAME": "your-bucket",
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json"
      }
    }
  }
}

Install

Configuration

Environment variables

GCP_BUCKET_NAMErequired

GCS bucket name

GOOGLE_APPLICATION_CREDENTIALSrequired

Path to a GCP service account JSON key (read-only storage role recommended)

Arguments

--fromdefault data-connectors-ai[gcp,mcp]==0.1.5

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "data-connectors-gcp-bucket": {
      "command": "uvx",
      "args": [
        "data-connectors-ai",
        "--from",
        "data-connectors-ai[gcp,mcp]==0.1.5",
        "data-connectors-gcp-bucket-mcp"
      ],
      "env": {
        "GCP_BUCKET_NAME": "<YOUR_GCP_BUCKET_NAME>",
        "GOOGLE_APPLICATION_CREDENTIALS": "<YOUR_GOOGLE_APPLICATION_CREDENTIALS>"
      }
    }
  }
}

GCP Bucket Connector

io.github.nagarjunr/data-connectors-gcp-bucket — MCP Server for GCP Cloud Storage

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

Topics

GCP Bucket MCP Server

Tools

Environment Variables

Run locally

Use with an MCP client

Registry

Install

Configuration