2 required secrets
AWS Kendra
Query Amazon Kendra indices for enhanced RAG context in AI applications
Retrieval & SearchSaaS & API Integrations
About
Query Amazon Kendra indices as additional RAG context for chatbots and coding assistants.
Features
- Enhance your existing MCP-enabled ChatBot with additional RAG indices
- Enhance the responses from coding assistants such as Cline, Cursor, Windsurf, Amazon Q Developer, etc.
What you’ll need to connect
Required AWS Credentials:
- AWS Access Key ID: Your AWS credential access key
- AWS Secret Access Key: Your AWS credential access secret
Optional Configuration:
- AWS Region: AWS region to use (default:
us-east-1) - AWS Session Token: Required only for temporary credentials like SSO or STS AssumeRole
Prerequisites:
- An AWS account
- An existing Amazon Kendra Index with your RAG documentation
IAM Permissions Required:
kendra:Queryandkendra:ListIndicespermissions (minimum)- Alternatively, use the AWS Managed
AmazonKendraFullAccesspolicy
Configuration
Environment variables
| Variable | Description | Required |
|---|---|---|
AWS_ACCESS_KEY_ID | Your AWS Access Key ID | Yes |
AWS_SECRET_ACCESS_KEY | AWS Secret Access Key | Yes |
AWS_SESSION_TOKEN | AWS Session Token, only required if using temporary credentials such as temporary AWS credentials, such as those obtained through aws sso login or other temporary access methods (for example, STS AssumeRole) | No |
AWS_REGION | AWS Region, default to us-east-1 | No |
Container runtime
- Image
ghcr.io/obot-platform/mcp-images/aws-kendra:1.0.15- Port
8099- Path
/- Args
awslabs.amazon-kendra-index-mcp-server