MCP Server using Amazon Q Business Cross App index

What is MCP Server using Amazon Q Business Cross App index?

An MCP server that integrates with Amazon Q Business' cross-app index to answer questions based on uploaded synthetic data. It is designed for users who want to query support tickets and similar documents through Amazon Q Business.

How to use MCP Server using Amazon Q Business Cross App index?

Upload the files from the synthetic_data directory to an S3 bucket, set up the Token Vending Machine (TVM) from the provided repository, create a .env file with REGION and Q_BUSINESS_APP_NAME, then run the server using ./run_with_uv.sh or manually with uv. The server can be tested with test_mcp_client.py.

Key features of MCP Server using Amazon Q Business Cross App index

• Uses Amazon Q Business cross-app index for semantic search.
• Pre‑built sample questions for IT ticket resolution scenarios.
• Managed via uv for Python dependency handling.
• Includes a test client script for validation.
• Compatible with Claude Desktop as an MCP host.

Use cases of MCP Server using Amazon Q Business Cross App index

• Answering “What are the reasons of keyboard failure?” from indexed tickets.
• Retrieving root causes for software installation issues.
• Finding remediation steps for common user problems.
• Querying timelines for service improvements (e.g., voice receptionist upgrades).

FAQ from MCP Server using Amazon Q Business Cross App index

What does the Token Vending Machine (TVM) do?

The TVM from the amzn-q-auth-tvm repository handles authentication for Amazon Q Business; its output must be copied to tvm_values.json.

What environment variables are required?

REGION (example us-east-1) and Q_BUSINESS_APP_NAME (your Amazon Q Business application name) must be set in a .env file.

How do I run the server?

Execute the ./run_with_uv.sh script, which creates a uv environment, installs dependencies, and launches the MCP server.

What dependencies are needed?

The server requires boto3, mcp[cli], requests, fastmcp, httpx, and python-dotenv.

Where does the data come from?

The data originates from the synthetic_data directory, which must be uploaded to Amazon S3 and used as a data source for your Amazon Q Business application.