Astra DB MCP Server
@datastax
About Astra DB MCP Server
An MCP server for Astra DB workloads
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"astra-db-mcp": {
"command": "npx",
"args": [
"-y",
"@datastax/astra-db-mcp"
],
"env": {
"ASTRA_DB_APPLICATION_TOKEN": "your_astra_db_token",
"ASTRA_DB_API_ENDPOINT": "your_astra_db_endpoint"
}
}
}
}Tools
19Get all collections in the Astra DB database
Create a new collection in the database
Update an existing collection in the database
Delete a collection from the database
List records from a collection in the database
Get a specific record from a collection by ID
Create a new record in a collection
Update an existing record in a collection
Delete a record from a collection
Find records in a collection by field value
Find distinct values for a field in a collection
Create multiple records in a collection at once
Update multiple records in a collection at once
Delete multiple records from a collection at once
Search for records in a collection using vector similarity
Search for records using both vector similarity and text matching
Open a web browser to a specific URL
Estimate the number of documents in a collection using a fast, approximate count method
Help the user add the Astra DB client to their MCP client
Overview
What is Astra DB MCP Server?
A Model Context Protocol (MCP) server for interacting with Astra DB. It extends LLMs by allowing them to act as agents that can manage collections, perform CRUD operations, run vector and hybrid search, and execute bulk data operations on an Astra DB database.
How to use Astra DB MCP Server?
Install by running npx -y @datastax/astra-db-mcp with the required environment variables ASTRA_DB_APPLICATION_TOKEN and ASTRA_DB_API_ENDPOINT. Optionally set ASTRA_DB_KEYSPACE to target a specific keyspace. Add the server to an MCP client such as Claude Desktop or Cursor by editing their configuration JSON.
Key features of Astra DB MCP Server
- Collection management: create, update, delete, and list collections
- Vector search and hybrid search on embeddings
- CRUD operations on individual records
- Bulk create, update, and delete records
- Find records by field value and distinct values
- Estimate document count in a collection
Use cases of Astra DB MCP Server
- Let an LLM agent read and write data to an Astra DB database
- Power semantic search with vector similarity on embeddings
- Perform hybrid retrieval combining vector and text queries
- Manage and bulk-load records in collections via natural language
FAQ from Astra DB MCP Server
What prerequisites are needed to run this server?
You need an active Astra DB database, an Astra DB Application Token, and the Astra DB API Endpoint. A free database can be created at the Astra DB registration page.
Which MCP clients are supported?
The README provides setup instructions for Claude Desktop and Cursor. Other MCP clients that accept a command-based server may also work.
How do I configure a specific keyspace?
Add the ASTRA_DB_KEYSPACE environment variable to the server configuration. If omitted, the default keyspace configured in the underlying Astra DB library is used.
Can I perform vector search with this server?
Yes. The server provides VectorSearch for similarity search on embeddings and HybridSearch that combines vector similarity with text search. Both support configurable limits, filters, and scoring.
What runtime environment does the server require?
It runs via npx (Node.js package runner). On Windows PowerShell, the command should use cmd /k npx because npx is a batch command.
Frequently asked questions
What prerequisites are needed to run this server?
You need an active Astra DB database, an Astra DB Application Token, and the Astra DB API Endpoint. A free database can be created at the Astra DB registration page.
Which MCP clients are supported?
The README provides setup instructions for Claude Desktop and Cursor. Other MCP clients that accept a command-based server may also work.
How do I configure a specific keyspace?
Add the `ASTRA_DB_KEYSPACE` environment variable to the server configuration. If omitted, the default keyspace configured in the underlying Astra DB library is used.
Can I perform vector search with this server?
Yes. The server provides `VectorSearch` for similarity search on embeddings and `HybridSearch` that combines vector similarity with text search. Both support configurable limits, filters, and scoring.
What runtime environment does the server require?
It runs via `npx` (Node.js package runner). On Windows PowerShell, the command should use `cmd /k npx` because `npx` is a batch command.
Basic information
More Databases MCP servers
Elasticsearch MCP Server
elastic
Multi Database MCP Server
FreePeakA powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.
mcp-server-qdrant: A Qdrant MCP server
qdrantAn official Qdrant Model Context Protocol (MCP) server implementation
Postgres Mcp
crystaldbaPostgres MCP Pro provides configurable read/write access and performance analysis for you and your AI agents.
MCP Alchemy
runekaagaardA MCP (model context protocol) server that gives the LLM access to and knowledge about relational databases like SQLite, Postgresql, MySQL & MariaDB, Oracle, and MS-SQL.
Comments