DynamoDB Read-Only MCP logo

DynamoDB Read-Only MCP

by jjikky

This server utilizes the Model Context Protocol (MCP) to query AWS DynamoDB databases. It allows LLMs like Claude to query DynamoDB data through natural language requests.

View on GitHub

Last updated: N/A

What is DynamoDB Read-Only MCP?

A server that uses the Model Context Protocol (MCP) to enable Large Language Models (LLMs) like Claude to query AWS DynamoDB databases using natural language.

How to use DynamoDB Read-Only MCP?

  1. Clone the repository. 2. Install dependencies with npm install. 3. Configure AWS credentials in a .env file. 4. Build the project with npm run build. 5. Run the server with npm start. 6. Configure Claude Desktop to connect to the server.

Key features of DynamoDB Read-Only MCP

  • Table Management Tools (list-tables, describe-table)

  • Data Query Tools (scan-table, query-table, paginate-query-table, get-item, count-items)

  • Resources (dynamodb-tables-info, dynamodb-table-schema)

  • Prompts (dynamodb-query-help)

Use cases of DynamoDB Read-Only MCP

  • Allowing LLMs to access and analyze data stored in DynamoDB.

  • Enabling natural language queries for DynamoDB data.

  • Providing context information to LLMs about DynamoDB tables and schemas.

  • Assisting users in writing DynamoDB queries.

FAQ from DynamoDB Read-Only MCP

What is MCP?

Model Context Protocol is a standardized message exchange method for LLMs to interact with external tools and resources.

How do I connect this server to Claude?

You need to modify the Claude Desktop configuration file (claude_desktop_config.json) to include the server configuration.

What AWS credentials do I need?

You need AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_REGION. Ensure these credentials have read-only access to your DynamoDB tables.

Can I run this server without installing it?

Yes, you can use npx to run the server without a global installation.

What kind of queries can I perform?

You can perform various queries, including listing tables, describing tables, scanning tables, querying tables with conditions, retrieving specific items, and counting items.