Allows Claude AI to interact directly with MySQL databases.
This is an MCP (Model Context Protocol) server that allows Claude AI to interact directly with MySQL databases.
To install Database Tools for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @elber-code/database-tools --client claude
To install and use this tool, follow these steps:
Clone or download the repository
git clone [repository-url]
or download and extract the ZIP file.
Install dependencies Navigate to the project directory and run:
npm install
For Claude to use this tool, you need to add the configuration to your claude_desktop_config.json
file, which is typically located at:
C:\Users\YOUR_USER\AppData\Roaming\Claude\claude_desktop_config.json
With the following structure:
{
"mcpServers": {
// Other existing configurations...
"database-tools": {
"command": "node",
"args": [
"C:\\path\\to\\index.js"
]
}
}
}
Once configured, you can interact with your MySQL databases from Claude with commands like:
List all databases
"Execute query in MySQL to show me the databases."
View tables in a database
"Execute query in MySQL to show me the table name_table
."
Query the size of a table
"Execute query in MySQL to show me the size of the table name_table
."
Execute custom queries
"Execute query in MySQL: 'The description of what you want your query to do.'"
This tool runs with the permissions configured in the mysql.js
file. Make sure the credentials provided have only the necessary permissions for the operations you want to allow.
If you have connection problems, check:
mysql.js
are correctTo query databases, simply ask Claude something like: "Show me all databases in my MySQL" or "What is the size of the users table?"
A read-only MCP server by CData for querying live Cloudant data with LLMs. Requires the CData JDBC Driver for Cloudant.
Provides tools and resources for coding agents to interact with the Gel database, including automatic project configuration for query builders and ORMs.
a lightweight, local RAG memory store to record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.
Access MySQL databases to inspect schemas and execute SQL queries via a NodeJS-based server.
Enables AI assistants to query, read, and move data on DICOM servers such as PACS and VNA for medical imaging.
Provides tools for querying and managing a MySQL database.
Vector search using the LanceDB vector database and Ollama embedding models.
Connect AI tools with Pinecone projects to search, configure indexes, generate code, and manage data.
Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory
A Go implementation of a Model Context Protocol (MCP) server for Trino, enabling LLM models to query distributed SQL databases through standardized tools.