Amazon Bedrock Converse API and Database MCP Server Integration

Created By
aws-samplesa year ago
Overview

What is Amazon Bedrock Converse API and Database MCP Server Integration?

This project demonstrates the integration of AWS Bedrock's Conversational AI capabilities with relational databases through the Model Context Protocol (MCP) Server architecture, enabling natural language interactions with databases in a query-only mode.

How to use the project?

To use this project, clone the repository from GitHub, set up your development environment, configure your AWS account and RDS PostgreSQL database, and run the application to query your database using natural language.

Key features of the project?

  • Integration of RDS PostgreSQL and SQLite with AWS Bedrock's Foundational Models using MCP.
  • Natural language querying of databases using Bedrock foundation models.
  • Secure and efficient database operations through MCP Server.
  • Adding Generative AI capabilities to existing applications.

Use cases of the project?

  1. Enabling conversational interfaces for database applications.
  2. Simplifying database queries for non-technical users.
  3. Enhancing existing applications with AI-driven insights.

FAQ from the project?

  • What databases are supported?

    The sample focuses on RDS PostgreSQL and SQLite but can be adapted for other databases supporting MCP integration.

  • Is there a cost associated with using this project?

    Yes, using AWS services like RDS and Bedrock may incur costs based on usage.

  • What are the prerequisites for using this project?

    An AWS account, IAM permissions, access to Bedrock LLMs, and a local development environment with Python and necessary libraries.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
aws-samples
Star
1
Language
Python
License
Code of conduct

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago