sammcj mcp aws kb

WHAT IT CONNECTS

sammcj mcp aws kb 为 AI Agent 提供什么

• **RAG (Retrieval-Augmented Generation)**: Retrieve context from the AWS Knowledge Base based on a query and a Knowledge Base ID.
• **Supports multiple results retrieval**: Option to retrieve a customizable number of results.
• **retrieve_from_aws_kb**
• Perform retrieval operations using the AWS Knowledge Base.
• Inputs:
• `query` (string): The search query for retrieval.
• `knowledgeBaseId` (string): The ID of the AWS Knowledge Base.
• `n` (number, optional): Number of results to retrieve (default: 3).
• Response format:
• The response now returns two separate content items:
• A text item containing the raw context from the knowledge base.
• A JSON item containing the structured RAG sources with metadata (id, fileName, snippet, and score).
• This separation allows for more flexible processing of the results.
• Obtain AWS access key ID, secret access key, and region from the AWS Management Console.
• Ensure these credentials have appropriate permissions for Bedrock Agent Runtime operations.
• Set the environment variables as shown in the configuration examples below.
• For temporary credentials, you can also provide a session token using the `AWS_SESSION_TOKEN` environment variable.
• Configure AWS CLI with your SSO profile: `aws configure sso`
• Set only the AWS_REGION environment variable in the MCP server configuration.
• The server will use the default credential provider chain, which includes SSO credentials.
• Create an array of knowledge base IDs in JSON format.
• Set this as the AWS_KB_IDS environment variable in your configuration.
• When this is configured, the `knowledgeBaseId` parameter becomes optional in the tool.