mcpSource-backedReview first Safety ✓ Privacy ✓

DataStax Astra DB MCP Server for Claude

Connect Claude to DataStax Astra DB — manage collections and records, run bulk operations, and perform vector and hybrid search — with the official Astra DB Model Context Protocol server.

by DataStax·added 2026-06-17·

Claude Code Codex Cursor Claude Desktop

HarnessClaude CodeCodexCursorClaude Desktop

Install

Source

claude mcp add astra-db -e ASTRA_DB_APPLICATION_TOKEN=<your-token> -e ASTRA_DB_API_ENDPOINT=<your-endpoint> -- npx -y @datastax/astra-db-mcp

Readiness

TrustReview first
Sourcesource-backed
Safety notesPresent
ReviewedYes

Documentation Source repository Registry JSON · LLM text

Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

Tools create, update, and delete collections and records, including bulk operations — scope the application token and confirm destructive actions.
Bulk delete/update operations affect many records at once; review before running them through Claude.

Privacy notes

Documents, vectors, and search results enter the MCP client context and the model's prompt.
ASTRA_DB_APPLICATION_TOKEN and ASTRA_DB_API_ENDPOINT are secrets — keep them in the client config or environment.

Prerequisites

A DataStax Astra DB account and a database.
An Astra DB application token (ASTRA_DB_APPLICATION_TOKEN) and API endpoint (ASTRA_DB_API_ENDPOINT).
Node.js (npx) and an MCP client such as Claude Code or Claude Desktop.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 5 minutes
Difficulty: intermediate

Tool listing metadata

Website: https://www.datastax.com/products/datastax-astra

Full copyable content

{
  "mcpServers": {
    "astra-db-mcp": {
      "command": "npx",
      "args": ["-y", "@datastax/astra-db-mcp"],
      "env": {
        "ASTRA_DB_APPLICATION_TOKEN": "<your-token>",
        "ASTRA_DB_API_ENDPOINT": "<your-endpoint>"
      }
    }
  }
}

About this resource

Overview

The DataStax Astra DB MCP Server is the official Model Context Protocol server for Astra DB, DataStax's serverless database built on Apache Cassandra with native vector search. It lets Claude manage collections and records, run bulk operations, and perform vector and hybrid search in natural language. It runs over stdio via npx @datastax/astra-db-mcp and is licensed under Apache-2.0.

Key capabilities

Area	Tools
Collections	`GetCollections`, `CreateCollection`, `UpdateCollection`, `DeleteCollection`, `EstimateDocumentCount`
Records	`ListRecords`, `GetRecord`, `CreateRecord`, `UpdateRecord`, `DeleteRecord`, `FindRecord`, `FindDistinctValues`
Bulk	`BulkCreateRecords`, `BulkUpdateRecords`, `BulkDeleteRecords`
Search	`VectorSearch`, `HybridSearch`

How it compares

Astra DB combines a document store with native vector search; other vector-database MCP servers focus on embeddings retrieval:

MCP server	Engine	Model	Notable
Astra DB MCP	Astra DB (Cassandra)	Documents + vectors	Document CRUD plus vector & hybrid search
Pinecone MCP	Pinecone	Vector index	Fully managed vector search
Qdrant MCP	Qdrant	Vector index	Self-host or Qdrant Cloud

Choose Astra DB when you want document storage and vector search in one managed service; the Pinecone and Qdrant servers cover dedicated vector indexes.

Installation

Claude Code

claude mcp add astra-db \
  -e ASTRA_DB_APPLICATION_TOKEN=<your-token> \
  -e ASTRA_DB_API_ENDPOINT=<your-endpoint> -- \
  npx -y @datastax/astra-db-mcp

Claude Desktop

{
  "mcpServers": {
    "astra-db-mcp": {
      "command": "npx",
      "args": ["-y", "@datastax/astra-db-mcp"],
      "env": {
        "ASTRA_DB_APPLICATION_TOKEN": "<your-token>",
        "ASTRA_DB_API_ENDPOINT": "<your-endpoint>"
      }
    }
  }
}

Requirements

A DataStax Astra DB account, application token, and API endpoint.
Node.js (npx) and an MCP client (Claude Code or Claude Desktop).

Security

Scope the ASTRA_DB_APPLICATION_TOKEN to least privilege.
Bulk and delete tools change many records at once — review destructive actions before running.
Treat the token and endpoint as secrets.

Source Verification Notes

Verified on 2026-06-17:

The official repository github.com/datastax/astra-db-mcp (Apache-2.0) documents the @datastax/astra-db-mcp package, stdio transport, the ASTRA_DB_APPLICATION_TOKEN/ASTRA_DB_API_ENDPOINT configuration, and the collection, record, bulk, and vector/hybrid-search tools above.
DataStax's Astra DB documentation describes the underlying serverless database and vector search.
Claude Code's MCP documentation describes the connector setup pattern used here.

#astra-db #datastax #vector-database #cassandra #rag

Source citations

Add this badge to your README

Show that DataStax Astra DB MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/mcp/astra-db-mcp-server.svg)](https://heyclau.de/entry/mcp/astra-db-mcp-server)

How it compares

DataStax Astra DB MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	DataStax Astra DB MCP Server for Claude Connect Claude to DataStax Astra DB — manage collections and records, run bulk operations, and perform vector and hybrid search — with the official Astra DB Model Context Protocol server. Open dossier	Weaviate MCP Server for Claude Connect Claude to a Weaviate vector database — run hybrid search, inspect collection config, list tenants, and upsert objects — using Weaviate's built-in Model Context Protocol server. Open dossier	Pinecone Developer MCP Server Official Pinecone Developer MCP server that connects Claude and other MCP clients to Pinecone projects and documentation for index management, record upserts, semantic search, cascading multi-index search, reranking, and documentation lookup over integrated-inference indexes. Open dossier	Chroma MCP Server Official Chroma MCP server for connecting Claude to Chroma collections, documents, semantic search, full-text search, metadata filtering, persistent storage, self-hosted Chroma, and Chroma Cloud. Open dossier
Trust
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Category	mcp	mcp	mcp	mcp
Source	source-backed	source-backed	source-backed	source-backed
Author	DataStax	Weaviate	Pinecone	Chroma
Added	2026-06-17	2026-06-17	2026-06-11	2026-06-06
Platforms	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Source repo	—	—	—	—
Safety notes	✓Tools create, update, and delete collections and records, including bulk operations — scope the application token and confirm destructive actions. Bulk delete/update operations affect many records at once; review before running them through Claude.	✓The MCP server runs inside your Weaviate instance and respects its existing RBAC; scope the API key to least privilege. The object-upsert tool writes data — restrict write access to the collections Claude should modify.	✓The server can create indexes and upsert records, so an agent with a write-capable API key can change live Pinecone project state. Run the npm package `@pinecone-database/mcp` through `npx`, which downloads and executes the published package on each launch; pin to a trusted version if reproducibility matters. Scope the Pinecone API key to the intended project and use read-only or least-privilege keys when index creation and writes are not needed. Require human review before `create-index-for-model` and `upsert-records` runs that mutate production indexes.	✓Chroma MCP can create, modify, and delete collections. Document tools can add, update, query, retrieve, and delete documents, metadata, custom IDs, and embeddings. Persistent, HTTP, and cloud modes can mutate durable retrieval stores rather than temporary test collections. External embedding functions can send document text or image-derived content to third-party embedding providers. Chroma Cloud and self-hosted HTTP modes require careful handling of tenants, databases, API keys, custom auth credentials, SSL settings, and network exposure. Retrieved context can influence Claude output even when stale, irrelevant, over-broad, or not authorized for the task.
Privacy notes	✓Documents, vectors, and search results enter the MCP client context and the model's prompt. ASTRA_DB_APPLICATION_TOKEN and ASTRA_DB_API_ENDPOINT are secrets — keep them in the client config or environment.	✓Query text, retrieved objects, and collection metadata enter the MCP client context and the model's prompt. The Weaviate endpoint URL and API key are secrets — keep them in the client config or environment, not in shared repositories.	✓The `PINECONE_API_KEY` is read from the MCP client environment and grants access to the associated Pinecone project; keep it out of prompts, notes, and committed files. Index names, configurations, namespaces, statistics, record contents, and search queries can be exposed to the MCP client and model provider. Records and search text may contain embedded documents, customer data, or proprietary content, so review what is sent into indexes and returned by searches. Documentation search and tool calls reach Pinecone endpoints such as api.pinecone.io, so network access and request metadata leave the local machine.	✓Collections can store source documents, chunks, embeddings, metadata, IDs, filters, and query results that reveal private project, customer, or research data. Query text, retrieved documents, metadata filters, and embedding inputs may expose sensitive information to Chroma Cloud, self-hosted operators, embedding providers, logs, or downstream model providers. CHROMA_API_KEY, custom auth credentials, embedding provider API keys, tenant IDs, database names, hostnames, and dotenv files should stay out of prompts, issues, logs, screenshots, and committed files. Persistent data directories and exported collections need the same access control, backup, encryption, and retention review as the source documents they index.
Prerequisites	A DataStax Astra DB account and a database. An Astra DB application token (ASTRA_DB_APPLICATION_TOKEN) and API endpoint (ASTRA_DB_API_ENDPOINT). Node.js (npx) and an MCP client such as Claude Code or Claude Desktop.	A Weaviate instance on v1.37.1 or later (self-hosted or Weaviate Cloud). The MCP server enabled on that instance via MCP_SERVER_ENABLED=true. A Weaviate API key with the RBAC permissions for the collections Claude should reach. An MCP client such as Claude Code or Claude Desktop.	Node.js 18 or newer with `npx` available. Pinecone account and API key generated from the Pinecone console at app.pinecone.io. MCP client that supports stdio server configuration, such as Claude Desktop or Cursor. Awareness that index management and record tools require integrated-inference indexes.	Python 3.10 or newer available through uv for local stdio usage. [object Object] Storage, backup, and retention plan for persistent collections before enabling write tools. Chroma Cloud tenant, database, and API key or self-hosted Chroma host credentials if using remote modes.
Install	`claude mcp add astra-db -e ASTRA_DB_APPLICATION_TOKEN=<your-token> -e ASTRA_DB_API_ENDPOINT=<your-endpoint> -- npx -y @datastax/astra-db-mcp`	`claude mcp add --transport http weaviate https://<your-weaviate-host>/v1/mcp`	`npx -y @pinecone-database/mcp`	`uvx chroma-mcp`
Config	`{ "mcpServers": { "astra-db-mcp": { "command": "npx", "args": ["-y", "@datastax/astra-db-mcp"], "env": { "ASTRA_DB_APPLICATION_TOKEN": "<your-token>", "ASTRA_DB_API_ENDPOINT": "<your-endpoint>" } } } }`	`{ "mcpServers": { "weaviate": { "url": "https://<your-weaviate-host>/v1/mcp", "type": "http" } } }`	`{ "mcpServers": { "pinecone": { "command": "npx", "args": ["-y", "@pinecone-database/mcp"], "env": { "PINECONE_API_KEY": "{pinecone-api-key}" } } } }`	`{ "mcpServers": { "chroma": { "command": "uvx", "args": ["chroma-mcp"] } } }`
Citations	Source repositorygithub.com 2026-06-18T07:03:47+00:00 Documentationgithub.com Websitedatastax.com	Source repositorygithub.com 2026-06-18T07:03:47+00:00 Documentationdocs.weaviate.io	Source repositorygithub.com 2026-06-18T07:03:47+00:00 Documentationdocs.pinecone.io Submitted by JSONbored2026-06-11	Source repositorygithub.com 2026-06-18T07:03:47+00:00 Documentationdocs.trychroma.com Submitted by oktofeesh12026-06-06
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed

Signals

Loading live community signals…

Safety notes

Privacy notes

Prerequisites

Schema details

About this resource

Overview

Key capabilities

How it compares

Installation

Claude Code

Claude Desktop

Requirements

Security

Source Verification Notes

Source citations

Add this badge to your README

How it compares

Related resources

Weaviate MCP Server for Claude

Pinecone Developer MCP Server

Chroma MCP Server

MariaDB MCP Server

Signals