What it does

Lists buckets and objects and pulls metadata for a given path. Useful when the question is 'what is actually in this bucket' rather than 'download it'. Content reads should go through a normal client — routing megabytes through a model is slow and expensive in both directions.

Install

Terminal

npx -y @google-cloud/storage-mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "gcs": {
      "command": "npx",
      "args": [
        "-y",
        "@google-cloud/storage-mcp"
      ]
    }
  }
}

Use it for

Browsing buckets and reading object metadata without a console

Skip it if

Large file transfers through a context window

When to use it

Reach for this when the task needs gcp inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Cloud Storage MCP