{"slug": "10-mcp-servers-to-connect-llms-with-databases", "title": "10 MCP servers to connect LLMs with databases", "summary": "Amazon Web Services has released official Model Context Protocol (MCP) servers for Amazon Aurora MySQL, Aurora PostgreSQL, and Aurora DSQL, enabling natural language database queries and administration. The servers convert plain language commands into SQL queries, allowing developers and AI agents to perform lookups, updates, and schema-aware code generation without writing SQL manually. These MCP servers join a growing ecosystem of vendor-backed connectors for relational, NoSQL, graph, vector, and data warehouse platforms, compatible with tools like Claude Code, Cursor, and VS Code.", "body_md": "[Model Context Protocol](https://www.infoworld.com/article/4029634/what-is-model-context-protocol-how-mcp-bridges-ai-and-external-services.html) (MCP) has gained considerable momentum as a standard connector between LLM-powered tools and local systems, internal and external APIs, and data sources. From [major clouds](https://www.infoworld.com/article/4129024/five-mcp-servers-to-rule-the-cloud.html) to [devops tools](https://www.infoworld.com/article/4096223/10-mcp-servers-for-devops.html), MCP servers are enabling powerful, AI-powered development and operations capabilities through natural language commands.\n\nNowhere is this more true than in the world of databases. Most major database platforms now support agentic access through MCP servers. Using an MCP server for databases, you and your AI agent proxies can perform lookups, create and update data, and perform administrative tasks without you having to write SQL by hand.\n\nThe MCP server could also guide your LLMs to write new code or build automations that align with your database schema, like its tables, structure, and fields, as well as embeddings, indexes, and metadata. It could also aid debugging by enabling faster queries to surface data issues or misconfigurations, along with plenty of other possible use cases.\n\nBelow, we’ll cover official MCP servers from some of the top platform options across major database styles. Though maturity varies, the MCP servers discussed below represent some of the best vendor-backed offerings available today across relational [SQL](https://www.infoworld.com/article/4140734/the-revenge-of-sql-how-a-50-year-old-language-reinvents-itself.html), [NoSQL](https://www.infoworld.com/article/2260280/what-is-nosql-databases-for-a-cloud-scale-future.html), [graph](https://www.infoworld.com/article/2265778/what-is-a-graph-database-a-better-way-to-store-connected-data.html), [vector](https://www.infoworld.com/article/2335281/vector-databases-in-llms-and-search.html), and [data warehouse](https://www.infoworld.com/article/2268778/what-is-a-data-warehouse-the-source-of-business-intelligence.html) systems.\n\nThese servers can be used by any MCP-compatible tool, IDE, or agent, whether it’s Claude Code, Codex, Cursor, Gemini CLI, Google Antigravity, VS Code, Windsurf, or something else. Adding them is typically simple, often involving a lightweight JSON addition to your MCP configuration file.\n\n[MySQL](https://www.mysql.com/) and [PostgreSQL](https://www.postgresql.org/) are the world’s most widely-used [open source](https://www.infoworld.com/article/2262355/what-is-open-source-software-open-source-and-foss-explained.html) databases. However, in both cases, there is no canonical MCP server—what we see are different MCP servers emerging across vendors. One of these vendors is Amazon Web Services (AWS), which offers official MCP servers for Amazon Aurora, its managed relational database service compatible with both MySQL and PostgreSQL.\n\nAccording to the [documentation on GitHub](https://github.com/awslabs/mcp/tree/main/src/mysql-mcp-server), the [Amazon Aurora MySQL MCP Server](https://awslabs.github.io/mcp/servers/mysql-mcp-server) can be used to convert natural language commands into MySQL-compatible SQL queries, which can then be executed against Aurora MySQL databases. Similarly, the [Aurora Postgres MCP Server](https://github.com/awslabs/mcp/tree/main/src/postgres-mcp-server) provides MCP tools for working on PostgreSQL databases. The [Aurora DSQL MCP Server](https://github.com/awslabs/mcp/tree/main/src/aurora-dsql-mcp-server) does the same for distributed Postgres databases.\n\nAWS provides a [growing portfolio of official MCP servers](https://github.com/awslabs/mcp) across its product line, including MCP servers for other Amazon database platforms like [DynamoDB](https://awslabs.github.io/mcp/servers/dynamodb-mcp-server), [ElastiCache](https://awslabs.github.io/mcp/servers/elasticache-mcp-server), and [Redshift](https://awslabs.github.io/mcp/servers/redshift-mcp-server). If you’re a heavy AWS shop and you want to enable LLM interactions with your data, these are sensible choices.\n\nBigQuery is Google’s cloud-based data analytics platform, and a popular data source for AI applications. BigQuery users with API access configured can also utilize the [BigQuery MCP Server](https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp) to interact with the platform using MCP-compatible AI clients.\n\nUsing the remote [BigQuery MCP Server](https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp), engineers can generate and execute queries on data sources, or return metadata on datasets, tables, and schema. This can be done with a simple natural language prompt like “List the datasets in project `PROJECT_ID`\n\n.” Results are filterable by region, data set ID, column name, and more.\n\nAs part of Google’s fully-managed, remote-hosted MCP portfolio, the BigQuery MCP Server provides some peace of mind regarding security, maintenance, and ease of use for distributed teams. The MCP tools are subject to some limitations, however, in terms of query result size, processing time, and other factors. If you’re using BigQuery and you want more agentic control, you’ll want to check this one out.\n\nAnother important database category includes platforms designed for keyword and semantic search. In this space, [Elasticsearch](https://www.elastic.co/elasticsearch) is commonly deployed. Instead of providing a single MCP server, Elasticsearch provides the [Elastic Agent Builder](https://www.elastic.co/docs/explore-analyze/ai-features/elastic-agent-builder), which is a more comprehensive framework aimed at agentic workflows.\n\nUsing Elastic Agent Builder, you can chat with an agent to retrieve data context from Elasticsearch data and extend it into various environments. The Agent Builder itself includes an [MCP server](https://www.elastic.co/docs/explore-analyze/ai-features/agent-builder/mcp-server) endpoint for programmability and exposing the agent to other clients.\n\nUnlike others on this list, this is not a direct MCP interface to raw Elasticsearch APIs. Instead, it’s an interface that exposes skills from the agent platform. This should also not be confused with the [Elasticsearch MCP Server](https://github.com/elastic/mcp-server-elasticsearch/releases), released in mid-2025, which has since been deprecated.\n\nA possible downside of using this utility is that it includes an additional layer between your IDE or agent and the data you’re searching. The agent setup requires a higher subscription and takes additional steps to configure compared to other MCP servers.\n\nThat said, if you want an extensible common layer to interact with both Elasticsearch and external MCP servers, while centralizing responsibilities like permissions, this is an interesting proposition.\n\nGraph databases are another key NoSQL database type these days, specializing in using nodes and edges to accelerate queries of highly interconnected data. Of these, [Neo4j](https://neo4j.com/product/neo4j-graph-database/) is a popular graph database option.\n\nThe [Official MCP Server for Neo4j](https://neo4j.com/developer/genai-ecosystem/model-context-protocol-mcp/) works with all kinds of Neo4j deployment (desktop, sandbox, self-managed, and the managed Neo4j Aura cloud service), and allows LLM-based clients to retrieve graph schema, execute read and write statements, execute graph algorithms, and more.\n\nIn addition, several other MCP servers for Neo4j are [available from Neo4j Labs](https://github.com/neo4j-contrib/mcp-neo4j). These have specialized uses, such as generating Cypher queries from natural language, maintaining an in-memory graph database, modeling and visualizing graph, and interacting with the Neo4j Aura API.\n\nThe first MCP server for Neo4j was developed in December 2024. If you’re an avid Neo4j user and want to experiment with interacting with your graph databases in a chat-infused way, these stand as an interesting platform of servers.\n\nGoogle’s [MCP Toolbox for Databases](https://github.com/googleapis/mcp-toolbox) is a notable MCP server because it’s a popular catch-all for various database types. Unlike the other entries on this list, this server connects LLMs not to a single managed database, but unifies LLM access to multiple systems. The open source utility ships with [pre-built configurations](https://mcp-toolbox.dev/documentation/configuration/prebuilt-configs/) for nearly 30 databases including PostgreSQL, MySQL, SQL Server, Oracle Database, MongoDB, Redis, Neo4j, and Snowflake, as well as the databases in Google Cloud.\n\nOnce you define data sources in a tools.yaml file, you can use MCP Toolbox to perform structured queries or semantic searches against databases directly from within an IDE or agentic client using plain English. MCP tools translate commands into actions like `list_tables`\n\nand `execute_sql`\n\n.\n\nMCP Toolbox for Databases is mature, originally built as a generative AI utility and later re-worked for MCP-style workflows. It offers numerous download, configuration, and interaction methods.\n\nIf you’re using a variety of databases on Google Cloud and elsewhere and you want an “all-in-one” MCP server, MCP Toolbox for Databases is a great place to start.\n\n[MongoDB](https://www.mongodb.com/) is the popular NoSQL document-oriented database. The creators of MongoDB have released an [official MCP server](https://github.com/mongodb-js/mongodb-mcp-server) that works with the open-source database as well as the company’s cloud-hosted MongoDB Atlas database platform.\n\nThe MongoDB MCP Server provides a [number of tools](https://github.com/mongodb-js/mongodb-mcp-server#tool-list) to interact with MongoDB. You can query the database, return information on collections, create or remove collections or indexes, gather statistics on database usage, and more. Other tools enable MongoDB Atlas operations, like creating users or clusters, returning cluster data, and other functions.\n\nThe server’s tools are read-only by default but can be switched to allow write capabilities. It can be used locally, but also supports Streamable HTTP transport for remote servers, although that comes with greater security concerns.\n\nFor those using MongoDB and wanting to hook their AI-enabled IDE or CLI up with more automated powers, the official MongoDB MCP Server is worth checking out.\n\nAmong [vector-native databases](https://www.infoworld.com/article/4060211/do-vector-native-databases-beat-add-ons-for-ai-applications.html), [Pinecone](https://www.pinecone.io/) stands as a strong, widely used option with a well-designed [API](https://docs.pinecone.io/reference/api/introduction) and comprehensive SDKs. The [Pinecone MCP server](https://docs.pinecone.io/guides/operations/mcp-server) extends this experience, allowing users to query its documentation and execute functionality via AI agents and AI-enabled IDEs.\n\nTo date, the Pinecone MCP server consists of nine MCP tools. These cover read-only actions, like knowledge gathering via the Pinecone official documentation and querying vector records, index metadata, configurations, and statistics. It also allows for write operations like updating records and creating new indexes.\n\nReleased in mid-2025, the Pinecone MCP server is one of the more complete early implementations, with easy configuration and installation.\n\nFor those using Pinecone who want to test new LLM-assisted workflows for creating indexes with embeddings, performing reranking, or testing results using natural language commands, the Pinecone MCP server is worth trying out.\n\nAn ultra-fast in-memory database, Redis is commonly used for caching, real-time analytics, and other latency-sensitive use cases. And as you might have guessed, the company behind the Redis database provides an [official MCP server](https://redis.io/docs/latest/integrate/redis-mcp/). The server allows read, query, and write capabilities.\n\nDevelopers can use Redis MCP from an LLM client to perform high-level actions to analyze, reference, or embed Redis data and interact with the Redis server within their prompts. The documentation suggests some example prompts for common use cases, such as “Cache this item,” “How many keys does my database have?,” and “What is user:1’s email?”\n\nUnlike other MCP servers, which only allow a slice of platform capabilities, Redis MCP offers full Redis support. This enables working with Redis constructs such as hashes, lists, sets, sorted sets, streams, and more, according to the [GitHub repository](https://github.com/redis/mcp-redis).\n\nOne possible drawback is that Redis MCP has yet to support Streamable HTTP transport. Until this is developed, the server is constrained to local deployment. But for those seeking a local MCP server to work with Redis data, this is the best choice.\n\nSnowflake is a cloud-hosted, AI-enabled data platform widely used in enterprise contexts for data warehousing, data analytics, and data engineering purposes. Compared to other data storage systems, Snowflake is unique in that it’s more fully managed and combines structured and non-structured data types.\n\nThe [Snowflake MCP Server](https://www.snowflake.com/en/developers/guides/getting-started-with-snowflake-mcp-server/), available on [GitHub](https://github.com/Snowflake-Labs/mcp), can be used to perform many of the standard Snowflake platform operations. This includes a “fuzzy” search of all records via Snowflake’s Cortex Search and structured data semantic lookups using Cortex Analyst.\n\nOther abilities include object management operations like creating, updating, and deleting records. The server also can invoke other agentic-designed capabilities, like the ability to generate and execute SQL statements against back-end databases.\n\nSnowflake MCP Server is well-thought-out and well-documented, with walkthroughs for various agent and deployment patterns. Those already building with Snowflake should find it complements the mechanics they already employ.\n\nA longtime open-source favorite, [PostgreSQL](https://www.postgresql.org/) is one of the most popular and trusted object-relational SQL-based database systems. With an active [open source community](https://leaddev.com/technical-direction/postgresql-database-quietly-ate-world), Postgres has been maturing for decades. Given its open source nature, there isn’t a single “official” MCP server for the platform. Anthropic built an original reference implementation, but it’s [now archived](https://github.com/modelcontextprotocol/servers-archived/tree/main/src/postgres).\n\nInstead, database platforms built on PostgreSQL provide [different flavors](https://dbhub.ai/blog/state-of-postgres-mcp-servers-2025) of MCP servers, with a range of vendor neutrality and specificity. One notable option is the [Supabase MCP Server](https://github.com/supabase-community/supabase-mcp#database), provided by [Supabase](https://supabase.com/mcp), a cloud-based “back end as a service” and Postgres development platform.\n\nSupabase MCP Server connects AI agents with Supabase projects, allowing engineers to issue natural language commands to manage tables, query data, get logs, fetch configuration information, and more. The Supabase MCP Server is pre-1.0 release and some features are still experimental.\n\nIf you’re an engineer using Supabase and looking for an MCP server to connect your AI assistant with your Postgres databases, this is a good tool to test out.\n\nSo far, we’ve reviewed official, vendor-backed MCP servers from some of the most-adopted managed databases. However, numerous MCP servers exist across other database platforms and types.\n\nOne MCP server that aggregates LLM access across various database types is [DBHub](https://github.com/bytebase/dbhub), which works with MySQL, PostgreSQL, SQL Server, MariaDB, and SQLite. Developed by [Bytebase](https://www.bytebase.com/), DBHub is described as a zero-dependency, token-efficient MCP server.\n\nFor SQL, the options are nearly endless. Official servers exist for [Microsoft Azure SQL](https://devblogs.microsoft.com/azure-sql/introducing-sql-mcp-server/) and [DuckDB](https://github.com/motherduckdb/mcp-server-motherduck). PulseMCP catalogs more than [100 MCP servers](https://www.pulsemcp.com/servers?q=mysql) for [MySQL](https://dev.to/benborla/mcp-server-for-mysql-3jf1#main-content), although most are unofficial, solo-creator open source projects. Of these, one of the most starred is [MCP Server for MySQL](https://github.com/benborla/mcp-server-mysql), developed by full-stack developer [Ben Borla](https://benborla.dev/) and optimized for Claude Code.\n\nFor Postgres, notable alternatives to Supabase include [pgEdge Postgres MCP](https://github.com/pgEdge/pgedge-postgres-mcp/), [Neon MCP server](https://neon.com/docs/ai/neon-mcp-server), and [Postgres MCP Pro](https://github.com/crystaldba/postgres-mcp). For vector databases, others beyond Pinecone have been quick to adopt MCP as well, including [Weaviate](https://docs.weaviate.io/weaviate/mcp/docs-mcp-server) and [Milvus](https://milvus.io/docs/milvus_and_mcp.md).\n\nBefore diving into MCP servers for enterprise databases, it’s important to understand the security risks. For instance, prompt injection remains an [unsolved problem](https://dbhub.ai/blog/state-of-postgres-mcp-servers-2025), so it’s recommended to limit permissions for SQL statements.\n\nTo mitigate this, [Supabase recommends](https://github.com/supabase-community/supabase-mcp#security-risks) enabling AI client settings that require manual approval for each tool call before execution. Experts also recommend assigning only the minimum permissions required and avoiding exposure of sensitive data like API credentials. Due diligence around authentication and authorization is especially important when hosting remote servers.\n\nLastly, to avoid shadow IT, it’s becoming common practice to catalog the internal MCP servers you use, even for experimental projects. For this, experts recommend an [MCP registry](https://www.infoworld.com/article/4145014/how-to-build-an-enterprise-grade-mcp-registry.html) that documents approved servers. An MCP registry improves both MCP server discovery and security awareness.", "url": "https://wpnews.pro/news/10-mcp-servers-to-connect-llms-with-databases", "canonical_source": "https://www.infoworld.com/article/4181843/10-mcp-servers-to-connect-llms-with-databases.html", "published_at": "2026-06-08 09:00:00+00:00", "updated_at": "2026-06-12 09:57:05.940151+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-agents", "ai-infrastructure", "natural-language-processing"], "entities": ["Model Context Protocol", "MCP"], "alternates": {"html": "https://wpnews.pro/news/10-mcp-servers-to-connect-llms-with-databases", "markdown": "https://wpnews.pro/news/10-mcp-servers-to-connect-llms-with-databases.md", "text": "https://wpnews.pro/news/10-mcp-servers-to-connect-llms-with-databases.txt", "jsonld": "https://wpnews.pro/news/10-mcp-servers-to-connect-llms-with-databases.jsonld"}}