# AWS Bedrock: Knowledge Base

> Use this tool when you need to access and retrieve information from AWS Knowledge Bases to empower AI systems with curated information sources. It solves problems related to retrieval-augmented generation, company-specific knowledge, and technical documentation by providing a seamless interface with AWS services. The tool takes in queries and AWS credentials as inputs and outputs relevant results from specified knowledge bases, making it ideal for building informed AI assistants.

Canonical page: https://skillsregistry.net/skills/aws-bedrock-knowledgebase  
JSON: https://api.skillsregistry.net/v1/skills/aws-bedrock-knowledgebase

## Description

This AWS Knowledge Base Retrieval MCP server, developed by the Model Context Protocol team, enables AI assistants to access information from AWS Knowledge Bases using the Bedrock Agent Runtime. It provides a tool for performing retrieval-augmented generation (RAG) operations, allowing queries against specified knowledge bases and retrieval of multiple results. The server integrates seamlessly with AWS services, requiring proper AWS credentials configuration. By connecting AI capabilities with AWS knowledge repositories, this implementation empowers AI systems to leverage curated information sources. It is particularly useful for building AI assistants that need access to company-specific knowledge, technical documentation, or any scenario where an AI system benefits from retrieving contextual information from AWS-managed knowledge bases.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-05-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/aws-bedrock-knowledgebase)
- **Repository:** <https://github.com/modelcontextprotocol/servers-archived/tree/HEAD/src/aws-kb-retrieval-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "aws-bedrock-knowledgebase"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/aws-bedrock-knowledgebase` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/aws-bedrock-knowledgebase/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt