# Amazon Q Business

This MCP server sends queries to an Amazon Q Business application and returns answers based on its ingested content. It requires an anonymous-mode application and configured AWS access.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9939 repo stars
- Author: awslabs
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/awslabs/mcp/tree/HEAD/src/amazon-qbusiness-anonymous-mcp-server
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/amazon-q-business

## What it does

The server exposes `QBusinessQueryTool`. An agent passes a query to the tool, which asks the Amazon Q Business application for a response based on content already ingested there. It supports applications created with anonymous-mode access.

To run it, install `uv` and Python with `uv python install 3.10`, create an Amazon Q Business application, and configure AWS credentials with `aws configure`. The IAM user needs at least the `qbusiness:ChatSync` permission. Requests will fail without the application and AWS access set up.

Add the server to your MCP client configuration. The standard setup runs the package with `uvx`; a Windows example uses `uv tool run`. Configuration includes the application ID, AWS profile, and region. A Docker option is also shown, and temporary AWS credentials must be refreshed on the host.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- query content ingested into Amazon Q Business
- retrieve project details through an application query
- give an agent context from an Amazon Q Business application

## Example prompts
- Find the project details in my Amazon Q Business application.
- Answer this using content ingested into Amazon Q Business.
- Ask Amazon Q Business for context relevant to this question.

## Similar
- [creating-amazon-aurora-db-cluster-with-instances](https://affpapa.org/en/nevibecode/skills/creating-amazon-aurora-db-cluster-with-instances.md) — skill · 6800 installs
- [amazon-aurora-postgresql](https://affpapa.org/en/nevibecode/skills/amazon-aurora-postgresql.md) — skill · 6500 installs
- [amazon-polly](https://affpapa.org/en/nevibecode/skills/calesthio-amazon-polly.md) — skill · 134 installs
- [amazon-transcribe](https://affpapa.org/en/nevibecode/skills/amazon-transcribe.md) — skill · 132 installs
- [amazon-location-service](https://affpapa.org/en/nevibecode/skills/amazon-location-service.md) — skill · 1300 installs
- [Amazon Web Services MCP](https://affpapa.org/en/nevibecode/mcp/amazon-web-services-mcp.md) — MCP server · ★ 87 repo stars

From the same set: [awslabs/mcp](https://affpapa.org/en/nevibecode/by/awslabs/mcp.md) — 36 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
