bucket-helper-mcp
Provides MCP tools for AWS S3 and S3-compatible storage, enabling file upload, download, listing, deletion, and temporary remote file staging via natural language.
README
Bucket Helper
Bucket Helper belongs to a collection of libraries called AI Helpers developed for building Artificial Intelligence.
Utility functions for AWS S3 and any S3-compatible object storage โ MinIO, Backblaze B2 S3 API, DigitalOcean Spaces, Cloudflare R2, Wasabi, and friends. Built on boto3. Same shape as sftp-helper: a credentials() loader, the usual CRUD (upload / download / delete / exists / list_prefix), and a remote_tempfile context manager for stage-and-share flows.
Installation
Prerequisites โ Python 3.10โ3.13 and git, cross-platform:
- ๐ macOS (Homebrew):
brew install python git - ๐ง Ubuntu/Debian:
sudo apt update && sudo apt install -y python3 python3-pip git - ๐ช Windows (PowerShell):
winget install Python.Python.3.12 Git.Git
Then install the package:
pip install --force-reinstall --no-cache-dir git+https://github.com/warith-harchaoui/bucket-helper.git@v0.2.2
Optional extras โ pick what you need:
# argparse CLI is always available. Add the click twin:
pip install 'bucket-helper[cli] @ git+https://github.com/warith-harchaoui/bucket-helper.git@v0.2.2'
# HTTP server (FastAPI + uvicorn + python-multipart):
pip install 'bucket-helper[api] @ git+https://github.com/warith-harchaoui/bucket-helper.git@v0.2.2'
# MCP tools (fastapi-mcp) โ requires the [api] plumbing:
pip install 'bucket-helper[api,mcp] @ git+https://github.com/warith-harchaoui/bucket-helper.git@v0.2.2'
Configuration
A ready-to-fill template is committed at s3_config.json.example. Copy it to s3_config.json and edit in place โ real *config.json files are gitignored so you cannot accidentally commit secrets:
cp s3_config.json.example s3_config.json
# then edit s3_config.json with your AWS / MinIO / R2 / B2 credentials
You may also write a s3_config.yaml, use a .env, or set environment variables โ bucket-helper falls back in that order via os_helper.get_config. Required keys:
{
"s3_access_key": "AKIA...",
"s3_secret_key": "...",
"s3_bucket": "my-bucket",
"s3_https": "https://my-bucket.s3.eu-west-3.amazonaws.com"
}
Optional keys:
| Key | Default | Notes |
|---|---|---|
s3_region |
"us-east-1" |
AWS region; mostly cosmetic for MinIO / R2 |
s3_endpoint_url |
empty (= AWS S3) | Set this for S3-compatible backends โ see table below |
s3_prefix |
empty | Default key prefix added by upload(...) when no destination is given |
s3_use_path_style |
"false" |
Force path-style addressing (endpoint/bucket/key instead of bucket.endpoint/key). Typical for MinIO with custom domains. |
s3_verify_ssl |
"true" |
Disable only for dev MinIO with self-signed certs |
Endpoint URLs for common S3-compatible storage
Set s3_endpoint_url to:
| Provider | Endpoint |
|---|---|
| AWS S3 | leave empty / unset |
| MinIO | http://minio.example.com:9000 (or https://... with TLS) |
| DigitalOcean Spaces | https://nyc3.digitaloceanspaces.com (region in subdomain) |
| Cloudflare R2 | https://<account_id>.r2.cloudflarestorage.com |
| Backblaze B2 (S3 API) | https://s3.<region>.backblazeb2.com |
| Wasabi | https://s3.<region>.wasabisys.com |
Usage
For the full catalog of recipes (uploads / downloads / listings, S3-compatible endpoints โ MinIO / R2 / B2 / Spaces / Wasabi, temporary remote keys with auto-cleanup, mirroring with sftp-helper), see ๐ EXAMPLES.md.
import bucket_helper as bh
# Load creds โ JSON / YAML / env / .env (auto-fallback in that order)
cred = bh.credentials("path/to/s3_config.json")
# Upload a local file
uri = bh.upload("local.txt", cred, "folder/uploaded.txt")
# uri == "s3://my-bucket/folder/uploaded.txt"
assert bh.exists(uri, cred)
# Download
bh.download(uri, "downloaded.txt", cred)
# List
for key in bh.list_prefix("folder/", cred):
print(key)
# Delete
bh.delete(uri, cred)
MinIO example
cred = {
"s3_access_key": "minioadmin",
"s3_secret_key": "minioadmin",
"s3_bucket": "uploads",
"s3_https": "http://minio.example.com:9000/uploads",
"s3_endpoint_url": "http://minio.example.com:9000",
"s3_use_path_style": "true",
"s3_region": "us-east-1", # MinIO accepts any region string
}
bh.make_bucket("uploads", cred)
bh.upload("file.bin", cred, "file.bin")
Stage-and-share with remote_tempfile
Drop a generated file at a unique random key, hand the public URL to a downstream worker / webhook, and the object is deleted on block exit (even if the body raises):
import bucket_helper as bh
import requests
cred = bh.credentials("path/to/s3_config.json")
with bh.remote_tempfile(cred, ext="json", prefix="runs") as (s3_addr, public_url):
bh.upload("payload.json", cred, s3_addr, content_type="application/json")
# Hand the URL to something that fetches it once.
requests.post("https://hook.example.com/process", json={"input_url": public_url}).raise_for_status()
# Object is gone here, no manual cleanup.
Multi-surface exposure
Every public function in the library is also exposed as:
- argparse CLI โ
bucket-helper <subcommand>(installed by default). - click CLI โ
bucket-helper-click <subcommand>(install[cli]extra). - FastAPI HTTP โ
uvicorn bucket_helper.api:app --host 0.0.0.0 --port 8000(install[api]extra). - MCP tools โ
bucket-helper-mcp(install[api,mcp]extras).
Both CLIs share the same subcommand names and flags โ pick your favourite.
CLI examples
# argparse CLI (always available)
bucket-helper upload --config s3_config.json --input local.txt --key folder/uploaded.txt
bucket-helper exists --config s3_config.json --key folder/uploaded.txt
bucket-helper download --config s3_config.json --key folder/uploaded.txt --output back.txt
bucket-helper list --config s3_config.json --prefix folder/
bucket-helper delete --config s3_config.json --key folder/uploaded.txt
bucket-helper make-bucket --config s3_config.json --bucket new-bucket
bucket-helper tempfile --config s3_config.json --ext json --prefix runs
bucket-helper strip-path --config s3_config.json --address s3://my-bucket/path/to/obj
# click CLI โ same verbs, same flags
bucket-helper-click upload --config s3_config.json --input local.txt --key folder/uploaded.txt
HTTP + MCP server
# Serve HTTP + MCP (default credentials picked up from BUCKET_HELPER_CONFIG)
BUCKET_HELPER_CONFIG=$PWD/s3_config.json bucket-helper-mcp
# Or run only FastAPI directly:
uvicorn bucket_helper.api:app --host 0.0.0.0 --port 8000
# โ Swagger UI at http://localhost:8000/docs
Per-request credentials can also be sent as multipart form fields
(s3_access_key / s3_secret_key / s3_bucket / s3_https / โฆ).
Docker
docker build -t bucket-helper .
docker run --rm -p 8000:8000 \
-e BUCKET_HELPER_CONFIG=/config/s3_config.json \
-v $PWD/s3_config.json:/config/s3_config.json:ro \
bucket-helper
See also: LANDSCAPE.md (competitive positioning) and GUI.md (visual product design plan).
Author
Acknowledgements
Special thanks to Mohamed Chelali and Bachir Zerroug for fruitful discussions.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
