- MEMORY
- RECALL
- LOGS
- HUMAN
Short answer
How can I give my AI a long-term memory?
You can use an Azure Blob Container as a storage layer for state files. Your AI writes its current context to a blob and reads it back when you restart a session. This setup allows you to maintain continuity across different chat windows.
Where your data lands
The outcomes of persistent memory
The AI manages state files through these specific actions.
MEMORY
Persistent context
The AI saves its current progress to a blob. You can pick up exactly where you left off in a later session.
RECALL
State retrieval
The agent pulls previous state files from the container. This restores the specific variables and history needed for the task.
LOGS
Audit trails
Every state update creates a file in your container. You can inspect these files manually to see how the AI's context evolved.
HUMAN
Manual overrides
You can manually edit or delete state files in Azure. This lets you fix a corrupted state or force the AI to forget something.
The workflow
What your AI does when <the thing arrives>.
The AI handles the heavy lifting of file management so you don't have to.
Capture state
The AI bundles the current conversation variables and history into a single file.
put_blobSave to cloud
The agent uploads that file to your specific Azure Blob Container.
put_blobLocate memory
When you start a new session, the AI looks for the designated state file.
get_blobRestore context
The agent pulls the data from the container to rebuild its internal understanding.
get_blob
Try it
Copy these to start.
Use these prompts to begin managing your AI's memory.
Starting points
Replace the container names and file paths with your actual Azure details.
Azure Blob Container Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_KegC9wyMjVWOSEhCaSwb9DkXf1hOZWEJE3EaqGTJ/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Azure Blob Container capabilities are ready to use.
{
"mcpServers": {
"azure-blob-container-mcp": {
"url": "https://edge.vinkius.com/vk_preview_KegC9wyMjVWOSEhCaSwb9DkXf1hOZWEJE3EaqGTJ/mcp"
}
}
}Save our current conversation state to the 'chat-memory' container as 'session_01.json'.
Load the state from the 'user-context' container using the file 'profile_data.json'.
Check the 'app-logs' container to see if my last state file was uploaded successfully.
Update my current progress in the 'project-alpha' container by saving a new state file.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Azure Blob Container once, then ask.
Just link your Azure account. Your credentials stay encrypted, and you can start managing state files immediately.
Connect Azure Blob Container to your AIFAQ
How this task behaves
- 01
Can the AI delete my existing files in the container?
No. The AI only has the ability to put and get blobs. It cannot delete or overwrite files without you doing it manually.
- 02
Does the AI see all my files in Azure?
The AI can only access the specific files you tell it to get or put. It doesn't have a way to list all files in a container.
- 03
How does the AI know which file to load?
You have to tell the AI the specific name of the blob you want it to retrieve.
- 04
Can I use this to store images?
Yes, as long as you treat the image as a blob that the AI can get or put.
- 05
Will this work with any MCP-compatible client?
Yes, once connected via Vinkius, it works with Claude, Cursor, Windsurf, and VS Code.
More questions about Azure Blob Container? The Connector page answers them. See everything the Azure Blob Container Connector can do
Connect Azure Blob Container to Claude, Cursor, ChatGPT & more
