Akave MCP Server
A Model Context Protocol (MCP) server that enables AI models to interact with Akave's S3-compatible storage. This server provides a set of tools for managing your Akave storage buckets and objects through AI models like Claude and local LLMs.
What is MCP?
The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). Think of MCP like a USB-C port for AI applications - it provides a standardized way to connect AI models to different data sources and tools.
Features
- List and manage buckets
- Upload, download, and manage objects
- Generate signed URLs for secure access
- Support for both Claude and local LLMs (via Ollama)
- Simple configuration through JSON
Prerequisites
- Node.js 16+
- Access to an Akave account with:
- Access Key ID
- Secret Access Key
- Endpoint URL
- For local LLM support:
- Go 1.23 or later
- Ollama installed
Quick Start
Create a configuration file (e.g., mcp.json
):
Usage with Claude Desktop
- Download and install Claude for Desktop (macOS or Windows)
- Open Claude Desktop Settings:
- Click on the Claude menu
- Select "Settings..."
- Click on "Developer" in the left-hand bar
- Click on "Edit Config"
- This will create/update the configuration file at:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
- Add the Akave MCP server configuration to the file:
- Restart Claude Desktop
- You should see a slider icon in the bottom left corner of the input box. Click it to see the available Akave tools.
Usage with Local LLMs (Ollama)
- Install MCPHost:
- Start MCPHost with your preferred model using the same configuration file:
You can use any Ollama model, for example:
ollama:mistral
ollama:qwen2.5
ollama:llama2
Available Tools
The server provides the following MCP tools:
list_buckets
: List all buckets in your Akave storagelist_objects
: List objects in a bucket with optional prefix filteringget_object
: Read object contents from a bucketput_object
: Write a new object to a bucketget_signed_url
: Generate a signed URL for secure access to an objectupdate_object
: Update an existing objectdelete_object
: Delete an object from a bucketcopy_object
: Copy an object to another locationcreate_bucket
: Create a new bucketdelete_bucket
: Delete a bucketget_bucket_location
: Get the region/location of a bucketlist_object_versions
: List all versions of objects (if versioning enabled)
Example Usage
Listing Buckets
Reading a File
Uploading a File
Troubleshooting
Common Issues
- Connection Refused
- Ensure your Akave credentials are correct in the MCP configuration
- Check if the endpoint URL is accessible
- Verify your network connection
- File Reading Issues
- For markdown files, ensure proper encoding
- For binary files, use appropriate tools
- Check file permissions
- Local LLM Issues
- Ensure Ollama is running
- Verify model compatibility
- Check MCPHost configuration
- Use
--debug
flag for detailed logs
- Claude Desktop Issues
- Check logs at:
- macOS:
~/Library/Logs/Claude/mcp*.log
- Windows:
%APPDATA%\Claude\logs\mcp*.log
- macOS:
- Ensure Node.js is installed globally
- Verify the configuration file syntax
- Try restarting Claude Desktop
- Check logs at:
Contributing
Contributions are welcome! Please feel free to submit an issue or a pull request.
Support
For issues and feature requests, please create an issue in the GitHub repository.
This server cannot be installed
Enables AI models to interact with Akave's S3-compatible storage by providing tools for managing storage buckets and objects through standardized Model Context Protocol (MCP).
Related MCP Servers
- AsecurityFlicenseAqualityAn MCP server that provides tools for interacting with AWS S3 buckets, enabling direct access to S3 operations through the Model Context Protocol.Last updated -1Python
- AsecurityFlicenseAqualityEnables AI models to perform file system operations (reading, creating, and listing files) on a local file system through a standardized Model Context Protocol interface.Last updated -3JavaScript
- -securityFlicense-qualityImplements the Model Context Protocol (MCP) to provide AI models with a standardized interface for connecting to external data sources and tools like file systems, databases, or APIs.Last updated -90Python
- -securityFlicense-qualityAn S3 resource server based on Model Control Protocol (MCP) that supports accessing and managing Qiniu Cloud Kodo storage services, enabling users to list buckets, browse objects, read content, and handle multiple storage buckets concurrently.Last updated -Python