GetCollectionsLABSCO SUMMARY
The Data API surface of Astra DB, including vector search, handed to an assistant.
It is a full read-write client: bulk operations and DeleteCollection are one call away, so point it at a database you are willing to let an assistant change. The reason to choose it over a generic database server is HybridSearch — vector and text scoring in a single query, with the weighting exposed as a parameter.
What it is
An MCP server for DataStax Astra DB. It connects to one serverless database over an application token and API endpoint, and exposes the collections and documents in it as tools an assistant can call.
What you get
- GetCollections, CreateCollection, UpdateCollection, DeleteCollection — manage collections, including vector-enabled ones
- EstimateDocumentCount — an estimate of how many documents a collection holds
- ListRecords, GetRecord, CreateRecord, UpdateRecord, DeleteRecord — single-document reads and writes
- FindRecord and FindDistinctValues — look up documents by field value, or list the distinct values of a field
- BulkCreateRecords, BulkUpdateRecords, BulkDeleteRecords — batch writes in one call
- VectorSearch — similarity search over stored embeddings, with an optional score threshold and filter
- HybridSearch — vector similarity combined with a text query, with weights for each side
- OpenBrowser and HelpAddToClient — open a browser for setup, and get help wiring the server into a client
Requirements
A running Astra DB database, plus its Application Token and API Endpoint supplied as ASTRA_DB_APPLICATION_TOKEN and ASTRA_DB_API_ENDPOINT. Set ASTRA_DB_KEYSPACE too if you need a keyspace other than the library default. The client launches it with npx, so there is nothing to install first.
Setup effort
One command plus a key — env ASTRA_DB_APPLICATION_TOKEN=<YOUR_ASTRA_DB_APPLICATION_TOKEN> ASTRA_DB_API_ENDPOINT=<YOUR_ASTRA_DB_API_ENDPOINT> npx -y @datastax/astra-db-mcp
USE CASES
01
Exploring a collection you inherited
List the collections, sample records from one, and find the distinct values of a field before writing any query.
02
Loading a batch of documents
Create a vector-enabled collection with the dimension and metric you need, then write the records in batches.
03
Answering a question over embeddings
Run a similarity search against stored vectors, or combine it with a text query when the wording matters as much as the meaning.
04
Fixing records one at a time
Find the document by field value, read it back, and update or delete it.
19 tools
Listed in project docs. Your client may show a different list.
CreateCollectionUpdateCollectionDeleteCollectionEstimateDocumentCountListRecordsGetRecordCreateRecordUpdateRecordDeleteRecordFindRecordFindDistinctValuesBulkCreateRecordsBulkUpdateRecordsBulkDeleteRecordsVectorSearchHybridSearchOpenBrowserHelpAddToClientBEFORE YOU INSTALL
What to know first
Tools you get
19 tools named in the project's documentation.
Requires
- npx on PATH
- ASTRA_DB_APPLICATION_TOKEN in your environment
- ASTRA_DB_API_ENDPOINT in your environment
Where it runs
All 4 documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
env ASTRA_DB_APPLICATION_TOKEN=<YOUR_ASTRA_DB_APPLICATION_TOKEN> ASTRA_DB_API_ENDPOINT=<YOUR_ASTRA_DB_API_ENDPOINT> npx -y @datastax/astra-db-mcpMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"astra-db-mcp": {
"command": "npx",
"args": [
"-y",
"@datastax/astra-db-mcp"
],
"env": {
"ASTRA_DB_APPLICATION_TOKEN": "<YOUR_ASTRA_DB_APPLICATION_TOKEN>",
"ASTRA_DB_API_ENDPOINT": "<YOUR_ASTRA_DB_API_ENDPOINT>"
}
}
}
}Claude Desktop — Windows, Cursor — Windows
JSON
{
"mcpServers": {
"astra-db-mcp": {
"command": "cmd",
"args": [
"/k",
"npx",
"-y",
"@datastax/astra-db-mcp"
],
"env": {
"ASTRA_DB_APPLICATION_TOKEN": "<YOUR_ASTRA_DB_APPLICATION_TOKEN>",
"ASTRA_DB_API_ENDPOINT": "<YOUR_ASTRA_DB_API_ENDPOINT>"
}
}
}
}
