A
AWS Knowledge Base MCP
Retrieve grounded answers from an AWS Bedrock Knowledge Base
Share:
About
Query an Amazon Bedrock Knowledge Base and get back cited snippets from your indexed documents. Uses AWS credentials with permission to call Bedrock; a good option when your source-of-truth docs already live in an AWS-managed vector store.
Example tools
Illustrative tool names — the actual tool set is defined by the server at runtime.
web_search
Search the web and return top results
fetch_url
Fetch and return the contents of a URL
Screenshots
No screenshots yet.
Frequently Asked Questions
Common questions about AWS Knowledge Base MCP.
- What is the AWS Knowledge Base MCP used for?
- This MCP allows you to query an Amazon Bedrock Knowledge Base to retrieve grounded answers and cited snippets from your indexed documents. It is typically used for RAG applications where document sources are already managed within AWS.
- How do I install the AWS Knowledge Base MCP in a client?
- Installation in a popular MCP client like Claude Desktop, Cursor, or Cline involves adding 'aws-kb-retrieval' as the slug and specifying the 'stdio' transport. Refer to your specific client's documentation for detailed installation steps.
- Does the AWS Knowledge Base MCP require credentials?
- Yes, this MCP requires AWS credentials. These credentials must have the necessary permissions to call Amazon Bedrock services to access your knowledge base.
- What are the primary capabilities of this MCP?
- The primary capability is retrieving grounded answers with cited snippets from an AWS Bedrock Knowledge Base. This facilitates accurate information retrieval based on your pre-indexed documents.
- What are the costs associated with using the AWS Knowledge Base MCP?
- The cost of using this MCP depends on the underlying AWS Bedrock services and data storage you consume. Refer to AWS Bedrock pricing for details on usage costs.
- Are there any prerequisites for using this MCP?
- A key prerequisite for using this MCP is having an existing Amazon Bedrock Knowledge Base with indexed documents. You also need AWS credentials with appropriate Bedrock permissions.
Install AWS Knowledge Base MCP
Claude Desktop
Add this to claude_desktop_config.json.
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
]
}
}
}Cursor
Add this to ~/.cursor/mcp.json.
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
]
}
}
}VS Code
Add this to your workspace settings.json.
{
"mcp.servers": {
"aws-kb-retrieval": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
]
}
}
}Reviews
Sign in to leave a review.
No reviews yet. Be the first!
Discussion(0)
No comments yet.