MinIO MCP Server
Provides tools for interacting with MinIO and S3-compatible object storage through MCP clients like Claude. It enables comprehensive bucket and object management, including listing, creating, uploading, and generating presigned URLs.
README
MinIO MCP Server
MCP (Model Context Protocol) server for MinIO object storage operations. This server provides tools for interacting with MinIO/S3-compatible storage through Claude and other MCP clients.
Features
Bucket Operations
minio_list_buckets- List all bucketsminio_make_bucket- Create a new bucketminio_remove_bucket- Remove an empty bucketminio_bucket_exists- Check if a bucket exists
Object Operations
minio_list_objects- List objects in a bucketminio_get_object- Get object contentminio_put_object- Upload content as an objectminio_upload_file- Upload a local fileminio_download_file- Download object to local fileminio_remove_object- Remove an objectminio_stat_object- Get object metadataminio_presigned_url- Generate presigned download URLminio_copy_object- Copy object to another location
Installation
Using pip
pip install minio-mcp
Using uv (recommended)
uv pip install minio-mcp
From source
git clone <repository-url>
cd minio-mcp
pip install -e .
Configuration
Set the following environment variables:
export MINIO_ENDPOINT="localhost:9000"
export MINIO_ACCESS_KEY="your-access-key"
export MINIO_SECRET_KEY="your-secret-key"
export MINIO_SECURE="false" # Set to "true" for HTTPS
Or create a .env file:
MINIO_ENDPOINT=localhost:9000
MINIO_ACCESS_KEY=your-access-key
MINIO_SECRET_KEY=your-secret-key
MINIO_SECURE=false
Usage with Claude Desktop
Add to your Claude Desktop configuration (~/AppData/Roaming/Claude/claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"minio": {
"command": "uv",
"args": ["--directory", "D:\\Documents\\minio-mcp", "run", "minio-mcp"],
"env": {
"MINIO_ENDPOINT": "localhost:9000",
"MINIO_ACCESS_KEY": "your-access-key",
"MINIO_SECRET_KEY": "your-secret-key",
"MINIO_SECURE": "false"
}
}
}
}
Or using Python directly:
{
"mcpServers": {
"minio": {
"command": "python",
"args": ["-m", "minio_mcp.server"],
"env": {
"MINIO_ENDPOINT": "localhost:9000",
"MINIO_ACCESS_KEY": "your-access-key",
"MINIO_SECRET_KEY": "your-secret-key",
"MINIO_SECURE": "false"
}
}
}
}
Tool Reference
Bucket Operations
minio_list_buckets
List all buckets in MinIO storage.
{}
minio_make_bucket
Create a new bucket.
{
"bucket_name": "my-new-bucket"
}
minio_remove_bucket
Remove an empty bucket.
{
"bucket_name": "my-bucket"
}
minio_bucket_exists
Check if a bucket exists.
{
"bucket_name": "my-bucket"
}
Object Operations
minio_list_objects
List objects in a bucket.
{
"bucket_name": "my-bucket",
"prefix": "folder/",
"recursive": true
}
minio_get_object
Get object content.
{
"bucket_name": "my-bucket",
"object_name": "path/to/file.txt"
}
minio_put_object
Upload content as an object.
{
"bucket_name": "my-bucket",
"object_name": "new-file.txt",
"content": "Hello, MinIO!",
"content_type": "text/plain"
}
minio_upload_file
Upload a local file.
{
"bucket_name": "my-bucket",
"object_name": "uploaded-file.txt",
"file_path": "/path/to/local/file.txt"
}
minio_download_file
Download object to local file.
{
"bucket_name": "my-bucket",
"object_name": "file.txt",
"file_path": "/path/to/save/file.txt"
}
minio_remove_object
Remove an object.
{
"bucket_name": "my-bucket",
"object_name": "file-to-delete.txt"
}
minio_stat_object
Get object metadata.
{
"bucket_name": "my-bucket",
"object_name": "file.txt"
}
minio_presigned_url
Generate a presigned URL for downloading.
{
"bucket_name": "my-bucket",
"object_name": "file.txt",
"expires": 3600
}
minio_copy_object
Copy an object.
{
"source_bucket": "source-bucket",
"source_object": "file.txt",
"dest_bucket": "dest-bucket",
"dest_object": "copied-file.txt"
}
Development
Setup Development Environment
# Clone the repository
git clone <repository-url>
cd minio-mcp
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # Linux/macOS
# or
.venv\Scripts\activate # Windows
# Install with dev dependencies
pip install -e ".[dev]"
Running Tests
pytest
Quick Start with MinIO
If you don't have MinIO running, you can start it with Docker:
docker run -d \
--name minio \
-p 9000:9000 \
-p 9001:9001 \
-e MINIO_ROOT_USER=minioadmin \
-e MINIO_ROOT_PASSWORD=minioadmin \
minio/minio server /data --console-address ":9001"
Then configure the MCP server with:
MINIO_ENDPOINT=localhost:9000MINIO_ACCESS_KEY=minioadminMINIO_SECRET_KEY=minioadminMINIO_SECURE=false
The MinIO Console will be available at http://localhost:9001
License
MIT License
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.