Beget S3 MCP Ai Cli
Read-only-by-default MCP access to Beget S3 buckets for inspection and backup recovery
- Platforms
- CLI, self-hosted
- Runs
- Locally
- Version
- 0.1.1
- Listing updated
- 4 days ago
Similar MCP servers
About Beget S3 MCP Ai Cli
Beget S3 MCP Ai Cli is an MCP server for cloud and infrastructure. It runs locally on your machine and is started by your AI client.
Aimed at Russian-hosted storage, this Go server and CLI connect Claude Code, Cursor and Codex to a bucket you already created in the Beget panel. It starts read-only and each level (write, delete, admin) is switched on separately with BEGET_S3_ALLOW, bucket and prefix allow-lists narrow the scope, destructive actions follow a confirm, elicit, block or allow policy, and an optional append-only audit file records activity.
The README notes the Beget profile is conservative: bucket creation, presigned URLs and bucket API calls are disabled, so those are done in the console. Read tools include listing buckets and objects, previews, largest objects, prefix usage and unfinished uploads, while write and delete tools cover put, copy, multipart and removal. Inline reads are capped at 262,144 bytes, with larger files going through a confined local file root.
The README is mainly in Russian with an English section, and the author says the profile still needs live verification.
Install
Run in a terminal
claude mcp add beget-s3-mcp-ai-cli --env BEGET_S3_ACCESS_KEY_ID='<BEGET_S3_ACCESS_KEY_ID>' --env BEGET_S3_SECRET_ACCESS_KEY='<BEGET_S3_SECRET_ACCESS_KEY>' -- docker run -i --rm -e BEGET_S3_ACCESS_KEY_ID -e BEGET_S3_SECRET_ACCESS_KEY ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1Add to claude_desktop_config.json
{
"mcpServers": {
"beget-s3-mcp-ai-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"BEGET_S3_ACCESS_KEY_ID",
"-e",
"BEGET_S3_SECRET_ACCESS_KEY",
"ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1"
],
"env": {
"BEGET_S3_ACCESS_KEY_ID": "<BEGET_S3_ACCESS_KEY_ID>",
"BEGET_S3_SECRET_ACCESS_KEY": "<BEGET_S3_SECRET_ACCESS_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"beget-s3-mcp-ai-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"BEGET_S3_ACCESS_KEY_ID",
"-e",
"BEGET_S3_SECRET_ACCESS_KEY",
"ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1"
],
"env": {
"BEGET_S3_ACCESS_KEY_ID": "<BEGET_S3_ACCESS_KEY_ID>",
"BEGET_S3_SECRET_ACCESS_KEY": "<BEGET_S3_SECRET_ACCESS_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"beget-s3-mcp-ai-cli": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"BEGET_S3_ACCESS_KEY_ID",
"-e",
"BEGET_S3_SECRET_ACCESS_KEY",
"ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1"
],
"env": {
"BEGET_S3_ACCESS_KEY_ID": "<BEGET_S3_ACCESS_KEY_ID>",
"BEGET_S3_SECRET_ACCESS_KEY": "<BEGET_S3_SECRET_ACCESS_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"beget-s3-mcp-ai-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"BEGET_S3_ACCESS_KEY_ID",
"-e",
"BEGET_S3_SECRET_ACCESS_KEY",
"ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1"
],
"env": {
"BEGET_S3_ACCESS_KEY_ID": "<BEGET_S3_ACCESS_KEY_ID>",
"BEGET_S3_SECRET_ACCESS_KEY": "<BEGET_S3_SECRET_ACCESS_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"beget-s3-mcp-ai-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"BEGET_S3_ACCESS_KEY_ID",
"-e",
"BEGET_S3_SECRET_ACCESS_KEY",
"ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1"
],
"env": {
"BEGET_S3_ACCESS_KEY_ID": "<BEGET_S3_ACCESS_KEY_ID>",
"BEGET_S3_SECRET_ACCESS_KEY": "<BEGET_S3_SECRET_ACCESS_KEY>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
BEGET_S3_ACCESS_KEY_IDS3 access key IDBEGET_S3_SECRET_ACCESS_KEYS3 secret access keyBEGET_S3_POOLSigning poolBEGET_S3_ENDPOINTOptional endpoint overrideBEGET_S3_ALLOW_INSECURESet 1 only for explicit HTTP test endpointsBEGET_S3_ALLOWIndependent write,delete,admin levels; read only by defaultBEGET_S3_DESTRUCTIVE_POLICYBEGET_S3_ALLOWED_BUCKETSComma-separated bucket scopeBEGET_S3_ALLOWED_PREFIXESComma-separated bucket/prefix/ scopeBEGET_S3_FILE_ROOTOptional confined local file rootBEGET_S3_AUDIT_FILEOptional private append-only audit output
Tools this server provides (12)
Taken from the project documentation; the running server may differ.
- s3_list_buckets
- Lists buckets.
- s3_list_objects
- Lists objects.
- s3_head_object
- Reads object metadata.
- s3_get_object
- Reads an object inline.
- s3_preview_object
- Previews an object.
- s3_largest_objects
- Finds the largest objects.
- s3_prefix_usage
- Reports usage per prefix.
- s3_put_object
- Writes an object.
- s3_copy_object
- Copies an object.
- s3_delete_object
- Deletes an object.
- s3_download_file
- Downloads to the file root.
- s3_upload_file
- Uploads from the file root.
What it does
- Read-only default
- Writes, deletes and admin actions must be enabled separately.
- Scoped access
- Restrict by bucket and by bucket/prefix lists.
- Destructive-action policy
- Choose confirm, elicit, block or allow.
- Storage analytics
- Find largest objects and per-prefix usage.
- Large file handling
- Use a confined file root and multipart for big transfers.
- Audit log
- Optionally writes a private append-only log.
Good for
- Inspect a backup bucket without risk of changes
- Restore a file from a daily archive
- Find what is using space in a prefix
- Install the same access into Cursor or Codex configs
Beget S3 MCP Ai Cli FAQ
Does it write to my bucket by default?
No. It is read-only unless write, delete or admin levels are enabled.
Can it create buckets or presigned links?
No. In this profile those are disabled; create buckets in the Beget panel.
How is it packaged?
As a Docker image ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1 and a binary release.
How are credentials handled?
Through environment variables or a 0600 credentials file; secrets are not written into client configs.
How do I add Beget S3 MCP Ai Cli to Claude Code?
Run this command in your terminal: claude mcp add beget-s3-mcp-ai-cli --env BEGET_S3_ACCESS_KEY_ID='<BEGET_S3_ACCESS_KEY_ID>' --env BEGET_S3_SECRET_ACCESS_KEY='<BEGET_S3_SECRET_ACCESS_KEY>' -- docker run -i --rm -e BEGET_S3_ACCESS_KEY_ID -e BEGET_S3_SECRET_ACCESS_KEY ghcr.io/stufently/beget-s3-mcp-ai-cli:0.1.1
What are the best alternatives to Beget S3 MCP Ai Cli?
The closest alternatives to Beget S3 MCP Ai Cli are Cloudru S3 MCP Ai Cli, Mws S3 MCP Ai Cli, Vkcloud S3 MCP Ai Cli, STRG.com s3-compatible object storage for people and agents and Techbeaver Cloud.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.