Skip to main content
Glama
Astra DB MCP Server

Astra DB MCP Server

Official
by datastax

Astra DB MCP Server

A Model Context Protocol (MCP) server for interacting with Astra DB. MCP extends the capabilities of Large Language Models (LLMs) by allowing them to interact with external systems as agents.

Prerequisites

You need to have a running Astra DB database. If you don't have one, you can create a free database here. From there, you can get two things you need:

  1. An Astra DB Application Token

  2. The Astra DB API Endpoint

To learn how to get these, please read the getting started docs.

Related MCP server: MongoDB MCP Server for LLMs

Adding to an MCP client

Here's how you can add this server to your MCP client.

IBM Bob

For IBM Bob IDE, follow the procedure at this documentation.

IBM Bob IDE

For IBM Bob Shell, follow the procedure at this documentation.

Claude Desktop

Claude Desktop

To add this to Claude Desktop, go to Preferences -> Developer -> Edit Config and add this JSON blob to claude_desktop_config.json:

{
  "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"
      }
    }
  }
}

Optional Keyspace Configuration: By default, this server uses the keyspace configured in the underlying Astra DB library (typically default_keyspace). If you need to connect to a specific keyspace, you can add the ASTRA_DB_KEYSPACE variable to the env object above, like so:

"env": {
  "ASTRA_DB_APPLICATION_TOKEN": "your_astra_db_token",
  "ASTRA_DB_API_ENDPOINT": "your_astra_db_endpoint",
  "ASTRA_DB_KEYSPACE": "your_desired_keyspace"
}

Windows PowerShell Users: npx is a batch command so modify the JSON as follows:

  "command": "cmd",
  "args": ["/k", "npx", "-y", "@datastax/astra-db-mcp"],

Cursor

Cursor

To add this to Cursor, go to Settings -> Cursor Settings -> MCP

From there, you can add the server by clicking the "+ Add New MCP Server" button, where you should be brought to an mcp.json file.

Tip: there is a ~/.cursor/mcp.json that represents your Global MCP settings, and a project-specific .cursor/mcp.json file that is specific to the project. You probably want to install this MCP server into the project-specific file.

Add the same JSON as indiciated in the Claude Desktop instructions.

Alternatively you may be presented with a wizard, where you can enter the following values (for Unix-based systems):

  • Name: Whatever you want

  • Type: Command

  • Command:

env ASTRA_DB_APPLICATION_TOKEN=your_astra_db_token ASTRA_DB_API_ENDPOINT=your_astra_db_endpoint npx -y @datastax/astra-db-mcp

Note: ASTRA_DB_KEYSPACE is optional. If omitted, the default keyspace configured in the Astra DB library will be used.

Once added, your editor will be fully connected to your Astra DB database.

Available Tools

The server provides a comprehensive suite of tools spanning Collections, Vector Search, Tables, Keyspaces, and Administration:

📁 Collections & Documents

  • GetCollections: Get all collections in the active keyspace

  • GetCollectionInfo: Inspect collection options, vector settings, and default ID configuration

  • CreateCollection: Create a collection with vector options, distance metrics (cosine, euclidean, dot_product), and auto-vectorize configurations

  • UpdateCollection: Update or rename a collection

  • DeleteCollection: Delete a collection

  • EstimateDocumentCount: Get an approximate count of documents in a collection

  • ListRecords: List records with optional sorting, pagination (skip), and projection

  • GetRecord: Get a specific record by ID

  • CreateRecord: Insert a single document

  • UpdateRecord: Update a record

  • DeleteRecord: Delete a record by ID

  • FindRecord: Find records by exact field value match

  • FindWithFilter: Rich querying with MongoDB-style filter operators ($and, $or, $gt, $in, $exists, etc.)

  • FindDistinctValues: Find distinct values for a specific field in a collection

  • BulkCreateRecords: Insert multiple documents in batch

  • BulkUpdateRecords: Update multiple documents in batch

  • BulkDeleteRecords: Delete multiple documents in batch

🧠 Vector Search & Reranking

  • FindWithVector: Dense vector similarity search with optional metadata filters, similarity scores, and projection

  • FindWithVectorize: Natural language search query using Astra DB Vectorize serverless embeddings

  • FindAndRerank: Hybrid search (lexical + dense vector / auto-vectorize) with server-side reranking scores

  • VectorSearch: Vector similarity search with minScore threshold and projection

  • HybridSearch: Combine dense vector similarity and text search with weighted scoring

📊 Tables (Astra DB Data API v2)

  • ListTables: List all structured tables in the keyspace

  • CreateTable: Create a typed table with column definitions and primary keys

  • AlterTable: Add or drop columns (including vector columns)

  • DropTable: Drop a table

  • QueryTable: Query table rows with filters, sorting, projection, and pagination

  • InsertTableRow: Insert a single row or batch of rows into a table

  • UpdateTableRow: Update matching rows in a table

  • DeleteTableRow: Delete matching rows from a table

  • CreateTableIndex: Create a secondary index on a table column

  • CreateTableVectorIndex: Create a vector index on a table column with similarity metrics

🔑 Keyspaces & Administration

  • ListKeyspaces: List all keyspaces in the database

  • CreateKeyspace: Create a new keyspace with optional automatic switching

  • DropKeyspace: Drop a keyspace

  • UseKeyspace: Switch the active working keyspace for subsequent operations

  • GetCurrentKeyspace: Inspect the active keyspace name

  • ListEmbeddingProviders: Discover supported embedding models and providers

  • ListRerankingProviders: Discover supported reranking models

  • GetDatabaseInfo: Retrieve environment metadata (ID, region, status, keyspaces)

🛠️ Utilities

  • OpenBrowser: Open a browser for authentication/setup

  • HelpAddToClient: Assistance with MCP client installation

Changelog

All notable changes to this project will be documented in this file. The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

Running evals

The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found here.

OPENAI_API_KEY=your-key  npx mcp-eval evals.ts tools.ts

❤️ Contributors

astra-db-mcp contributors

Badges

Astra DB MCP Server on Glama.ai

Available Tools

16 tools
BulkCreateRecordsC

Create multiple records in a collection at once

Inputs: collectionName (required), records (required).

BulkDeleteRecordsC

Delete multiple records from a collection at once

Inputs: collectionName (required), recordIds (required).

BulkUpdateRecordsC

Update multiple records in a collection at once

Inputs: collectionName (required), records (required).

CreateCollectionC

Create a new collection in the database

Inputs: collectionName (required), dimension, vector.

CreateRecordC

Create a new record in a collection

Inputs: collectionName (required), record (required).

DeleteCollectionC

Delete a collection from the database

Inputs: collectionName (required).

DeleteRecordC

Delete a record from a collection

Inputs: collectionName (required), recordId (required).

EstimateDocumentCountA

Estimate the number of documents in a collection using a fast, approximate count method

Inputs: collectionName (required).

FindRecordC

Find records in a collection by field value

Inputs: collectionName (required), field (required), value (required), limit.

GetCollectionsB

Get all collections in the Astra DB database

Inputs: no named parameters.

GetRecordC

Get a specific record from a collection by ID

Inputs: collectionName (required), recordId (required).

HelpAddToClientB

Help the user add the Astra DB client to their MCP client

Inputs: no named parameters.

ListRecordsC

List records from a collection in the database

Inputs: collectionName (required), limit.

OpenBrowserC

Open a web browser to a specific URL

Inputs: url (required).

UpdateCollectionC

Update an existing collection in the database

Inputs: collectionName (required), newName (required).

UpdateRecordC

Update an existing record in a collection

Inputs: collectionName (required), record (required), recordId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 16 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose with no ambiguity. Tools are well-organized around specific resources (collections, records) and actions (create, get, update, delete, list, find, estimate), and even bulk operations are clearly separated from single operations. There is no overlap that would cause misselection.

    Naming Consistency5/5

    Tool names follow a highly consistent verb_noun pattern throughout, using PascalCase for readability. All tools start with an action verb (e.g., Create, Delete, Get, Update) followed by a noun (e.g., Record, Collection), with only minor variations like 'HelpAddToClient' and 'OpenBrowser' still fitting the pattern. There are no mixed conventions or chaotic naming.

    Tool Count5/5

    With 16 tools, this is well-scoped for a database server covering collections and records. Each tool earns its place by providing comprehensive CRUD operations, bulk handling, and utility functions, without being excessive or thin for the domain. The count supports a complete workflow without overwhelming an agent.

    Completeness5/5

    The tool surface offers complete CRUD/lifecycle coverage for both collections and records, including bulk operations, listing, finding, and estimation. There are no obvious gaps; agents can perform all essential database tasks from creation to deletion, with added utilities like HelpAddToClient and OpenBrowser for setup and navigation.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables LLMs to interact directly with MongoDB databases, allowing users to query collections, inspect schemas, and manage data through natural language.
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables LLMs to interact directly with MongoDB databases, allowing users to query collections, inspect schemas, and manage data through natural language.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables Large Language Models to access and interact with database connections, including viewing schemas and performing CRUD operations on connected databases.
      -
    • A
      license
      B
      quality
      A
      maintenance
      A Model Context Protocol server that enables AI assistants to interact with MongoDB Atlas resources through natural language, supporting database operations and Atlas management functions.
      28
      1,163
      Apache 2.0