Amazon Kendra Index — Claude Code MCP server: setup guide
Amazon Kendra Index connects Amazon Kendra indices to AI coding assistants for RAG context. Useful when you need answers sourced directly from enterprise documentation stored in AWS.
Apache-2.0 ★ 9,939 updated 2026-10-23
Open on GitHubWhat Amazon Kendra Index does
Connects Amazon Kendra enterprise search to your coding assistant to enrich model responses with company documentation. It introduces two tools: KendraQueryTool to run targeted search queries against a Kendra index, and KendraListIndexesTool to inspect available indices across an AWS region.
Running this MCP server requires Astral uv and Python 3.10. On the cloud side, you must prepare an active Kendra index and configure credentials via aws configure. The IAM identity requires at least kendra:Query and kendra:ListIndices actions, or the prebuilt AmazonKendraFullAccess policy.
Without an already indexed Kendra repository, queries will yield nothing. You can run the package via uvx awslabs.amazon-kendra-index-mcp-server or package it into a Docker container with host AWS credentials.
What it helps with
- supply enterprise search context to coding assistants via RAG
- query indexed AWS documentation using
KendraQueryTool - list available Kendra indices within a target AWS region
Example prompts for the agent
- Check the Kendra index for details on implementing the event handler in Java.
- List all Kendra indices configured in the us-west-2 region.
- Use test-kendra-index to pull background documentation for this task.
How to install Amazon Kendra Index
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Amazon Kendra Index
How do I configure the Amazon Kendra Index MCP server?
Install uv, then configure your client using the uvx awslabs.amazon-kendra-index-mcp-server command while setting KENDRA_INDEX_ID and AWS_REGION environment variables.
What tools does this MCP server provide?
It provides KendraQueryTool for querying indexed documents and KendraListIndexesTool for retrieving indices in a given AWS region.
What AWS IAM permissions are required?
Your AWS credentials need at least kendra:Query and kendra:ListIndices permissions, or the AmazonKendraFullAccess managed policy.