- SYNC
- DATA
- RELIABILITY
- HUMAN
Short answer
How do I add new data to my vector search index?
You tell your AI to add new documents or existing embeddings to your Astra DB collections. The AI uses the connector to insert these records so your search stays up to date. This keeps your retrieval-augmented generation accurate.
The results.
Where your data lands.
The AI moves information from your chat into your database.
SYNC
Fresh vector search
The AI inserts new embeddings into your collection. Your vector search now includes this latest information.
DATA
Updated collections
New documents land in your Astra DB. Your AI can now query these specific records during search.
RELIABILITY
Current context
The AI ensures your index matches your latest files. This prevents your agent from using stale data.
HUMAN
Manual review
You decide which specific documents or vectors are ready to be added. The AI only pushes what you authorize.
The workflow
What your AI does when <the thing arrives>.
Your AI handles the heavy lifting of formatting and pushing data to your database.
Identify new data
Your AI looks at the text or the pre-computed vectors you provided in the chat. It prepares them for the database format.
insert_documentFormat for Astra DB
The AI structures the data to match your collection's schema. It ensures the vector and metadata are correctly aligned.
insert_documentExecute insertion
The AI sends the command to your Astra DB instance. The new data is written to the collection immediately.
insert_documentConfirm update
The AI verifies the operation was successful. It tells you the data is now ready for vector search.
insert_document
Try it
Copy these to start.
Use these prompts to begin updating your index.
Starting points
Swap out the bracketed text with your actual collection names or specific file details.
DataStax Astra DB Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_AqDRfth2dYqeDTcgeoWzkACu9uC1WOaTh5GDBWN7/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 — DataStax Astra DB capabilities are ready to use.
{
"mcpServers": {
"datastax-astra-db-vector-mcp": {
"url": "https://edge.vinkius.com/vk_preview_AqDRfth2dYqeDTcgeoWzkACu9uC1WOaTh5GDBWN7/mcp"
}
}
}Add this text and its embedding to my 'customer_support' collection.
Insert this new document into the 'product_docs' collection in Astra DB.
Take these pre-generated vectors and add them to my search index.
Update my 'knowledge_base' collection with the information from this file.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect DataStax Astra DB once, then ask.
One connection gives your AI access to your database. Your credentials stay encrypted and secure.
Connect DataStax Astra DB to your AIFAQ
How this task behaves
- 01
Can the AI delete old vectors from my index?
No. This connector only handles inserting new data. You must manage deletions through your own database tools.
- 02
Does the AI create the embeddings for me?
The AI can process text you provide, but it relies on the tools to insert the data. You should provide the embeddings or the text you want to be indexed.
- 03
Can I update existing records?
No. The current tool is for inserting new documents and vectors into your collections.
- 04
Will this work with any vector database?
No. This specific connector is built exclusively for DataStax Astra DB.
- 05
Do I need to manually run SQL commands?
No. Once connected, you just tell your AI what to add, and it handles the insertion for you.
More questions about DataStax Astra DB? The Connector page answers them. See everything the DataStax Astra DB Connector can do
Connect DataStax Astra DB to Claude, Cursor, ChatGPT & more
