AWS Knowledge Base Retrieval MCP Server
Supports deployment as a Docker container with options for using IAM Access Keys or AWS SSO authentication methods.
Retrieves information from the AWS Knowledge Base using Bedrock Agent Runtime, supporting RAG (Retrieval-Augmented Generation) with customizable result counts and providing both raw context and structured metadata from search queries.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AWS Knowledge Base Retrieval MCP Serverretrieve best practices for securing S3 buckets from knowledge base kb-aws-security"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AWS Knowledge Base Retrieval MCP Server
An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.
Features
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.
Related MCP server: DuckDB-RAG-MCP-Sample
Tools
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.
Configuration
Setting up AWS Credentials
You have two options for configuring AWS credentials:
Option 1: IAM Access Keys
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_TOKENenvironment variable.
Option 2: AWS SSO (Single Sign-On)
The server now supports AWS SSO credentials:
Configure AWS CLI with your SSO profile:
aws configure ssoSet only the AWS_REGION environment variable in the MCP server configuration.
The server will use the default credential provider chain, which includes SSO credentials.
Optional: Configure Default Knowledge Base IDs
You can optionally specify one or more knowledge base IDs to use by default:
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
knowledgeBaseIdparameter becomes optional in the tool.
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
Docker with IAM Access Keys
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "docker",
"args": [ "run", "-i", "--rm", "-e", "AWS_ACCESS_KEY_ID", "-e", "AWS_SECRET_ACCESS_KEY", "-e", "AWS_REGION", "-e", "AWS_KB_IDS", "mcp/aws-kb-retrieval-server" ],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
"AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
"AWS_SESSION_TOKEN": "YOUR_OPTIONAL_SESSION_ID_FOR_SSO_TEMPORARY_CREDENTIALS_HERE",
"AWS_REGION": "YOUR_AWS_REGION_HERE",
"AWS_KB_IDS": "[\"kb-12345\", \"kb-67890\"]"
}
}
}
}Docker with AWS SSO
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "docker",
"args": [ "run", "-i", "--rm", "-e", "AWS_REGION", "-e", "AWS_KB_IDS", "-v", "${HOME}/.aws:/root/.aws", "mcp/aws-kb-retrieval-server" ],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
"AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
"AWS_SESSION_TOKEN": "YOUR_OPTIONAL_SESSION_ID_FOR_SSO_TEMPORARY_CREDENTIALS_HERE",
"AWS_REGION": "YOUR_AWS_REGION_HERE",
"AWS_KB_IDS": "[\"kb-12345\", \"kb-67890\"]"
}
}
}
}NPX with IAM Access Keys
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
"AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
"AWS_SESSION_TOKEN": "YOUR_OPTIONAL_SESSION_ID_FOR_SSO_TEMPORARY_CREDENTIALS_HERE",
"AWS_REGION": "YOUR_AWS_REGION_HERE",
"AWS_KB_IDS": "[\"kb-12345\", \"kb-67890\"]"
}
}
}
}NPX with AWS SSO
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
"AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
"AWS_SESSION_TOKEN": "YOUR_OPTIONAL_SESSION_ID_FOR_SSO_TEMPORARY_CREDENTIALS_HERE",
"AWS_REGION": "YOUR_AWS_REGION_HERE",
"AWS_KB_IDS": "[\"kb-12345\", \"kb-67890\"]"
}
}
}
}Local Repository (from cloned/built repo)
{
"mcpServers": {
"aws-kb": {
"command": "node",
"args": [
"/path/to/mcp-aws-kb/dist/index.js"
],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
"AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
"AWS_SESSION_TOKEN": "YOUR_OPTIONAL_SESSION_ID_FOR_SSO_TEMPORARY_CREDENTIALS_HERE",
"AWS_REGION": "YOUR_AWS_REGION_HERE",
"AWS_KB_IDS": "[\"kb-12345\", \"kb-67890\"]"
},
"disabled": false,
"autoApprove": [
"retrieve_from_aws_kb"
],
"timeout": 120
}
}
}Building
Docker:
docker build -t mcp/aws-kb-retrieval -f src/aws-kb-retrieval-server/Dockerfile .License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
This README assumes that your server package is named @modelcontextprotocol/server-aws-kb-retrieval. Adjust the package name and installation details if they differ in your setup. Also, ensure that your server script is correctly built and that all dependencies are properly managed in your package.json.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseBqualityCmaintenanceAn MCP server that enables AI models to retrieve information from Ragie's knowledge base through a simple 'retrieve' tool.Last updated128089MIT
- Alicense-qualityDmaintenanceAn MCP server that enables RAG (Retrieval-Augmented Generation) on markdown documents by converting them to embedding vectors and performing vector search using DuckDB.Last updated4Apache 2.0
- Flicense-qualityDmaintenanceAn MCP server that implements Retrieval-Augmented Generation to efficiently retrieve and process important information from various sources, providing accurate and contextually relevant responses.Last updated
- Flicense-qualityCmaintenanceAn MCP server integrating LangChain, RAG, and Agent to provide knowledge retrieval and tool invocation through natural language.Last updated
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Cloud-hosted MCP server for durable AI memory
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sammcj/mcp-aws-kb'
If you have feedback or need assistance with the MCP directory API, please join our Discord server