Skip to content
MCP server

Vkcloud S3 MCP Ai Cli

MCP server and CLI for VK Cloud Hotbox and Icebox storage in Claude Code and Cursor

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted, Linux
Runs
Locally
Version
0.1.1
Listing updated
today

Similar MCP servers

About Vkcloud S3 MCP Ai Cli

Vkcloud S3 MCP Ai Cli is an open-source MCP server for cloud and infrastructure. It runs locally on your machine and is started by your AI client.

VK Cloud's object storage comes in Hotbox and Icebox flavours, and this server lets an agent check their metadata and fetch objects. It covers two pools: Moscow ru-msk (the default) and Kazakhstan kz-ast. Bucket tagging is disabled in this profile.

The README's example picks the pool of an existing bucket, reads an object's metadata with stat, totals a prefix with du and creates a short presigned link to hand over an archive. Larger transfers use multipart uploads or presigned URLs, and anything that changes data stays off until you enable write, delete or admin levels.

The vkcloud-s3 binary is also a command-line client, and it can write MCP entries for Cursor, Claude Desktop, Codex and Claude Code. The authors say the profile and the cloud API still need live verification.

Install

Run in a terminal

claude mcp add vkcloud-s3-mcp-ai-cli --env VKCLOUD_S3_ACCESS_KEY_ID='<VKCLOUD_S3_ACCESS_KEY_ID>' --env VKCLOUD_S3_SECRET_ACCESS_KEY='<VKCLOUD_S3_SECRET_ACCESS_KEY>' -- docker run -i --rm -e VKCLOUD_S3_ACCESS_KEY_ID -e VKCLOUD_S3_SECRET_ACCESS_KEY ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1

Add to claude_desktop_config.json

{
  "mcpServers": {
    "vkcloud-s3-mcp-ai-cli": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "VKCLOUD_S3_ACCESS_KEY_ID",
        "-e",
        "VKCLOUD_S3_SECRET_ACCESS_KEY",
        "ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1"
      ],
      "env": {
        "VKCLOUD_S3_ACCESS_KEY_ID": "<VKCLOUD_S3_ACCESS_KEY_ID>",
        "VKCLOUD_S3_SECRET_ACCESS_KEY": "<VKCLOUD_S3_SECRET_ACCESS_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "vkcloud-s3-mcp-ai-cli": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "VKCLOUD_S3_ACCESS_KEY_ID",
        "-e",
        "VKCLOUD_S3_SECRET_ACCESS_KEY",
        "ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1"
      ],
      "env": {
        "VKCLOUD_S3_ACCESS_KEY_ID": "<VKCLOUD_S3_ACCESS_KEY_ID>",
        "VKCLOUD_S3_SECRET_ACCESS_KEY": "<VKCLOUD_S3_SECRET_ACCESS_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "vkcloud-s3-mcp-ai-cli": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "VKCLOUD_S3_ACCESS_KEY_ID",
        "-e",
        "VKCLOUD_S3_SECRET_ACCESS_KEY",
        "ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1"
      ],
      "env": {
        "VKCLOUD_S3_ACCESS_KEY_ID": "<VKCLOUD_S3_ACCESS_KEY_ID>",
        "VKCLOUD_S3_SECRET_ACCESS_KEY": "<VKCLOUD_S3_SECRET_ACCESS_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "vkcloud-s3-mcp-ai-cli": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "VKCLOUD_S3_ACCESS_KEY_ID",
        "-e",
        "VKCLOUD_S3_SECRET_ACCESS_KEY",
        "ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1"
      ],
      "env": {
        "VKCLOUD_S3_ACCESS_KEY_ID": "<VKCLOUD_S3_ACCESS_KEY_ID>",
        "VKCLOUD_S3_SECRET_ACCESS_KEY": "<VKCLOUD_S3_SECRET_ACCESS_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "vkcloud-s3-mcp-ai-cli": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "VKCLOUD_S3_ACCESS_KEY_ID",
        "-e",
        "VKCLOUD_S3_SECRET_ACCESS_KEY",
        "ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1"
      ],
      "env": {
        "VKCLOUD_S3_ACCESS_KEY_ID": "<VKCLOUD_S3_ACCESS_KEY_ID>",
        "VKCLOUD_S3_SECRET_ACCESS_KEY": "<VKCLOUD_S3_SECRET_ACCESS_KEY>"
      }
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Configuration

  • VKCLOUD_S3_ACCESS_KEY_IDS3 access key ID
  • VKCLOUD_S3_SECRET_ACCESS_KEYS3 secret access key
  • VKCLOUD_S3_POOLSigning pool
  • VKCLOUD_S3_ENDPOINTOptional endpoint override
  • VKCLOUD_S3_ALLOW_INSECURESet 1 only for explicit HTTP test endpoints
  • VKCLOUD_S3_ALLOWIndependent write,delete,admin levels; read only by default
  • VKCLOUD_S3_DESTRUCTIVE_POLICY
  • VKCLOUD_S3_ALLOWED_BUCKETSComma-separated bucket scope
  • VKCLOUD_S3_ALLOWED_PREFIXESComma-separated bucket/prefix/ scope
  • VKCLOUD_S3_FILE_ROOTOptional confined local file root
  • VKCLOUD_S3_AUDIT_FILEOptional private append-only audit output

Tools this server provides (34)

Taken from the project documentation; the running server may differ.

s3_list_buckets
Lists the buckets the credentials can see.
s3_list_objects
Lists objects under a prefix, up to 1000 per page.
s3_head_object
Returns an object's metadata.
s3_get_object
Reads an object inline, up to 262144 bytes.
s3_preview_object
Returns a short preview of an object, up to 65536 bytes.
s3_presign_get
Creates a presigned download URL.
s3_list_object_versions
Lists versions of objects.
s3_list_multipart_uploads
Lists multipart uploads in progress.
s3_list_parts
Lists the parts of a multipart upload.
s3_get_bucket_config
Reads a bucket's configuration.
s3_largest_objects
Finds the largest objects under a prefix within a bounded scan.
s3_prefix_usage
Reports aggregated usage per prefix in pages.
s3_unfinished_uploads
Finds abandoned multipart uploads.
s3_download_file
Downloads an object to the confined local file root.
s3_get_object_tagging
Reads an object's tags.
s3_put_object
Writes an object inline.
s3_create_folder
Creates a folder marker.
s3_copy_object
Copies an object.
s3_presign_put
Creates a presigned upload URL.
s3_multipart_create
Starts a multipart upload.
s3_multipart_presign_part
Presigns one part of a multipart upload.
s3_multipart_complete
Completes a multipart upload.
s3_upload_file
Uploads a file from the confined local file root.
s3_put_object_tagging
Writes an object's tags.
s3_delete_object
Deletes one object.
s3_delete_objects
Deletes several objects.
s3_multipart_abort
Aborts a multipart upload.
s3_create_bucket
Creates a bucket.
s3_put_bucket_versioning
Sets bucket versioning.
s3_put_bucket_cors
Sets bucket CORS rules.
s3_put_bucket_policy
Sets a bucket policy.
s3_delete_bucket_policy
Removes a bucket policy.
s3_put_object_lock_configuration
Sets the Object Lock configuration.
s3_delete_bucket
Deletes a bucket.

What it does

Two regional pools
Switches between the Moscow ru-msk and Kazakhstan kz-ast pools.
Hotbox and Icebox metadata
Reads object details for both storage flavours.
Short presigned links
Creates time-limited download links for existing archives.
Prefix size totals
Reports bounded usage figures for a prefix.
Layered permissions
Read-only by default, with write, delete and admin enabled one at a time.
Built-in client installer
Adds MCP configuration for several coding clients.

Good for

  • Check which pool holds a bucket and inspect an object
  • Share a stored backup through a presigned link
  • Measure how much a daily-backup prefix holds
  • Restore an archive from VK Cloud to disk
  • Keep an agent in read-only mode on production data

Pricing

Open source

Free software; VK Cloud storage is billed separately

Vkcloud S3 MCP Ai Cli FAQ

Which pools are included?

ru-msk (Moscow, the default) and kz-ast (Kazakhstan).

Does it support bucket tagging?

No; bucket tagging is disabled in this profile.

Can it change data?

Only after you enable write, delete or admin levels; read is the default.

How does it handle credentials?

Flags win over environment variables, which win over a credentials file created with 0600 permissions.

Is Vkcloud S3 MCP Ai Cli free?

Yes. Vkcloud S3 MCP Ai Cli is open source, so you can use and self-host it for free.

How do I add Vkcloud S3 MCP Ai Cli to Claude Code?

Run this command in your terminal: claude mcp add vkcloud-s3-mcp-ai-cli --env VKCLOUD_S3_ACCESS_KEY_ID='<VKCLOUD_S3_ACCESS_KEY_ID>' --env VKCLOUD_S3_SECRET_ACCESS_KEY='<VKCLOUD_S3_SECRET_ACCESS_KEY>' -- docker run -i --rm -e VKCLOUD_S3_ACCESS_KEY_ID -e VKCLOUD_S3_SECRET_ACCESS_KEY ghcr.io/stufently/vkcloud-s3-mcp-ai-cli:0.1.1

What are the best alternatives to Vkcloud S3 MCP Ai Cli?

The closest alternatives to Vkcloud S3 MCP Ai Cli are REA, Context7, Chrome DevTools MCP, Codebase Memory and GitHub.

Where this comes from

  • Description: written from the project's README.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers