Best Databases & Data Stores MCP Servers

Databases & Data Stores MCP servers allow AI assistants to query and manage relational databases, document stores, time-series engines, and vector repositories via the Model Context Protocol. Connect tools like Claude Desktop and Cursor to systems such as MongoDB, YugabyteDB, VictoriaMetrics, and ODBC-compliant databases for automated schema inspection, data retrieval, and querying.

Databases & Data Stores MCP servers let AI assistants query, inspect, and update structured and unstructured data repositories directly through the Model Context Protocol. By exposing database clients as standardized tools and resources, these servers enable language models to execute SQL queries, inspect document schemas, retrieve time-series metrics, and pull records from relational engines, document stores, and vector indices.

How to choose a database MCP server

When evaluating servers in this category, focus on three practical operational criteria:

  1. Transport and hosting: Determine whether the server runs locally via standard input/output (stdio) or as a remote service over Server-Sent Events (SSE) or HTTP. Local engines like SQLite or self-hosted instances benefit from stdio execution within your client workspace, while distributed clusters require stable network routing.
  2. Authentication and security controls: Check how database credentials, connection strings, and access tokens are passed. Look for servers that support read-only connection strings, credential scoping, and role-based permissions to prevent models from executing destructive writes or unauthorized schema alterations.
  3. Maintenance and driver dependencies: Review underlying database drivers and runtime requirements. Connectors using standard packages (like Python DB-API or native Node drivers) require less environment setup than servers relying on specialized native drivers, ODBC bridges, or proprietary JDBC runtimes.

Top picks

  • MongoDB MCP Server provides tools and prompts for inspecting and querying document collections in MongoDB databases.
  • ODBC Server via PyODBC enables broad relational database connectivity, including systems like Virtuoso, through standardized ODBC drivers.
  • YugabyteDB MCP Server acts as a direct bridge allowing language models to query distributed YugabyteDB deployments.
  • Victoriametrics Mcp Server exposes time-series monitoring metrics directly to model contexts.
  • Salesforce Einstein by CData enables read-only querying of live Salesforce analytics data via a specialized CData driver.

Compare the top Databases & Data Stores MCP servers

MCP serverWhat it connects toTypeRepository
Zero-Vector v3Zero-Vector v3 acts like a sophisticated long-term brain for AI assistants and digital personas. In simple terms, it prevents anOpen Sourcehttps://github.com/fernicar/zero-vector-3
Victoriametrics Mcp ServerVictoriametrics Mcp Server is an MCP server that connects large language model interfaces to VictoriaMetrics time series databases. Built forOpen Sourcehttps://github.com/yincongcyincong/VictoriaMetrics-mcp-server
YugabyteDB MCP ServerThe YugabyteDB MCP Server acts as a bridge between artificial intelligence and a YugabyteDB database, allowing AI models to "talk"Open Sourcehttps://github.com/yugabyte/yugabytedb-mcp-server
Movies MCP ServerMovies MCP Server is an MCP server that connects Model Context Protocol clients directly to a PostgreSQL database for comprehensiveUnknown
ODBC Server via PyODBCODBC Server via PyODBC is an MCP server that provides SQL and metadata inspection tools for databases connected through ODBCOpen Sourcehttps://github.com/OpenLinkSoftware/mcp-pyodbc-server
MongoDB MCP ServerMongoDB MCP Server is an MCP server that provides tools and prompts for interacting directly with a MongoDB database. BuiltUnknownhttps://github.com/jb-7-jay/learn-mcp-server-mongo
Salesforce Einstein by CDataSalesforce Einstein by CData is an MCP server that exposes Salesforce Einstein data as relational SQL models for AI assistants.Unknownhttps://github.com/CDataSoftware/salesforce-einstein-mcp-server-by-cdata
RewindDBRewindDB is an MCP server that interfaces with the local Rewind.ai SQLite database to expose recorded audio transcripts and opticalUnknownhttps://github.com/pedramamini/RewindMCP
YouTube Data MCPThe YouTube Data MCP acts as a smart bridge between AI models and the vast library of content on YouTube.Open Sourcehttps://github.com/kirbah/mcp-youtube
Zero-Vector MCPZero-Vector MCP acts like a high-powered digital brain for AI assistants, giving them the ability to remember past conversations andUnknownhttps://github.com/MushroomFleet/zero-vector-MCP
  • Zero-Vector MCP — Zero-Vector MCP acts like a high-powered digital brain for AI assistants, giving them the ability to remember past conversations and user preferences long after a…
  • Zero-Vector v3 — Zero-Vector v3 acts like a sophisticated long-term brain for AI assistants and digital personas. In simple terms, it prevents an AI from "forgetting" important details…
  • YugabyteDB MCP Server — The YugabyteDB MCP Server acts as a bridge between artificial intelligence and a YugabyteDB database, allowing AI models to "talk" directly to stored data. Instead…
  • YouTube Data MCP — The YouTube Data MCP acts as a smart bridge between AI models and the vast library of content on YouTube. In simple terms, it gives…
  • XiYan MCP Server — XiYan MCP Server is an MCP server that enables natural language database querying using the XiYan-SQL model and general large language models. It connects client…
  • Weaviate MCP Client — Weaviate MCP Client is an MCP server that connects LLM applications directly to a Weaviate vector database instance. Developed for developers and data teams, it…
  • Vikingdb Mcp Server — Vikingdb Mcp Server is an MCP server that connects Large Language Model assistants to VikingDB, a high-performance cloud vector database developed by ByteDance. It allows…
  • Mcp Victoriametrics — VictoriaMetrics MCP Server is an MCP server that exposes read-only VictoriaMetrics APIs and embedded documentation to LLM clients and autonomous agents. It connects directly to…
  • Victoriametrics Mcp Server — Victoriametrics Mcp Server is an MCP server that connects large language model interfaces to VictoriaMetrics time series databases. Built for DevOps engineers, site reliability teams,…
  • Vertica MCP Server — Vertica MCP Server is an MCP server that provides AI assistants with read-only database query execution and schema discovery for Vertica analytics environments. Built for…
  • Turso Cloud — Turso Cloud is an MCP server that integrates Turso databases with large language models through a secure two-level authentication model. It connects to the Turso…
  • Typesense MCP Server — Typesense MCP Server is an MCP server that connects AI assistants to the Typesense search engine for administrative tasks, document management, and search querying. Built…
  • Trino MCP Server — Trino MCP Server is an MCP server that connects AI assistants to the Trino distributed SQL query engine. Built using the official Python Model Context…
  • Talk with Your Database — Talk with Your Database is an MCP server that enables AI clients to interact with relational databases using SQLAlchemy under the hood. Designed for developers,…
  • Synechron Text2SQL MCP Server — Synechron Text2SQL MCP Server is an MCP server that provides natural language query interfaces for relational databases using large language models. It connects to multiple…
  • Supavec — Supavec is an MCP server that enables AI assistants to search and retrieve embeddings and indexed file content from the Supavec vector platform. Built for…
  • SupaMCP Server — SupaMCP Server is an MCP server that converts any Supabase project into an AI-compatible tool interface via declarative JSON definitions. It connects directly to Supabase…
  • SurrealDB MCP Server — SurrealDB MCP Server is an MCP server that provides an interface for AI assistants to interact directly with a SurrealDB database instance. Built on the…
  • Swift MCP Server - JavaScript Version — Swift MCP Server - JavaScript Version is an MCP server that connects large language model assistants to a local SQLite database containing curriculum and reference…
  • Supermarket Database — Supermarket Database is an MCP server project that connects Claude Desktop to a containerized PostgreSQL supermarket database. It provides an automated Docker environment packaging both…
  • Superset MCP Server — Superset MCP Server is an MCP server that connects AI assistants like Claude Desktop and Cursor to Apache Superset instances. It is designed for data…
  • supOS MCP Server — supOS MCP Server is an MCP server that integrates AI assistants with the supOS industrial operating system via its open APIs. Built for industrial IoT…
  • Skyvia MCP — Skyvia MCP is an MCP server that provides a no-code gateway linking business data stores directly to AI assistants. It connects large language model interfaces,…
  • SingleStore MCP Server — SingleStore MCP Server is an MCP server that provides tools for interacting directly with SingleStore databases. It enables database administrators, software developers, and data engineers…

What is the best Databases & Data Stores MCP server for Claude Desktop?

The right option depends on your backend architecture. For relational data requiring ODBC drivers, ODBC Server via PyODBC connects smoothly using standard local configuration. If you work with document databases, MongoDB MCP Server exposes document querying tools directly inside Claude Desktop. Teams monitoring operational metrics often use Victoriametrics Mcp Server to pull time-series data into prompts.

How do I connect a Databases & Data Stores MCP server to Cursor?

Add the chosen server command and environment variables to your Cursor configuration file. For instance, point the configuration to your Python or Node runtime executing MongoDB MCP Server, YugabyteDB MCP Server, or OceanBase. Ensure database credentials and connection URIs are securely passed via the configuration environment block so the model can call database tools during code generation.

Can I query relational databases with natural language using MCP?

Yes. XiYan MCP Server is specifically built to enable natural language queries to databases using XiyanSQL. Additionally, servers like ODBC Server via PyODBC, OceanBase, and Movies MCP Server provide schema inspection tools that allow models to inspect table definitions, construct valid SQL statements, and retrieve query results safely.

Are read-only Databases & Data Stores MCP servers available?

Yes. Several servers provide restricted read access to protect production data. For example, Salesforce Einstein by CData functions as a dedicated read-only MCP server for querying live analytics data. Similarly, RewindDB provides read access to local Rewind.ai SQLite transcripts and OCR data without modifying underlying records.

  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories