# Amazon Kendra Index

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.

- 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-kendra-index-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-kendra-index

## What it 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.

## 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
- 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
- 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.

## Similar
- [amazon-bedrock](https://affpapa.org/en/nevibecode/skills/amazon-bedrock.md) — skill · 9500 installs
- [google-cloud-solution-rag-enterprise-search-gke-sqldb](https://affpapa.org/en/nevibecode/skills/google-cloud-solution-rag-enterprise-search-gke-sqldb.md) — skill · 5000 installs
- [llamacloud-index](https://affpapa.org/en/nevibecode/skills/llamacloud-index.md) — skill · 215 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
- [ragstack](https://affpapa.org/en/nevibecode/mcp/ragstack.md) — MCP server · ★ 26 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
