AWS Knowledge Base MCP Server

@daohoangson

Basic information

About AWS Knowledge Base MCP Server

No overview available yet

#lambda #cloudflare #server-sent-events#pinecone#durable-objects#bedrock-knowledge-base#model-context-protocol #streamable-http#amazon-nova-pro

AWS Knowledge Base MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "aws-knowledge-base-mcp-server": {
      "command": "npx",
      "args": [
        "cdk",
        "deploy"
      ]
    }
  }
}

AWS Knowledge Base MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is AWS Knowledge Base MCP Server?

AWS Knowledge Base MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to search through a knowledge base using AWS Bedrock and Cloudflare Workers. It integrates with AWS Bedrock Knowledge Base, Pinecone for vector search, and an S3 bucket for storing documents, providing a search_knowledge_base tool.

How to use AWS Knowledge Base MCP Server?

Configure it in Claude Desktop by adding a JSON entry to mcpServers with npx mcp-remote pointing to https://aws-knowledge-base-mcp-server.daohoangson.workers.dev/sse. For GitHub Copilot, add a servers entry with type: "sse" and the same URL. The client demo can connect to the server using SSE or streamable HTTP transports via npm start with the appropriate URL.

Key features of AWS Knowledge Base MCP Server

Provides a search_knowledge_base tool for AI assistants.
Integrates with AWS Bedrock Knowledge Base for document retrieval.
Supports both SSE and streamable HTTP transports.
Runs on Cloudflare Workers with Node.js compatibility.
Includes infrastructure as code via AWS CDK.
Comes with a demo client using AI SDK by Vercel.

Use cases of AWS Knowledge Base MCP Server

AI assistants searching indexed documentation for relevant answers.
Demonstrating remote MCP server connectivity with multiple transports.
Retrieving and updating knowledge bases from Cloudflare and MCP websites.
Cost estimation for monthly usage with AWS Bedrock, Lambda, and S3.

Frequently asked questions

What transports does the server support?

The server supports both SSE (Server-Sent Events) and streamable HTTP transports.

What are the dependencies for running the server?

The infrastructure requires AWS Bedrock, Pinecone, an S3 bucket, and a Lambda function. The MCP server itself runs on Cloudflare Workers.

Where does the data live?

Documents are stored in an S3 bucket, vector embeddings are managed in Pinecone, and the knowledge base is indexed by AWS Bedrock Knowledge Base.

How do I set up the infrastructure?

Use the CDK in the `/cdk` directory with environment variables for `PINECONE_API_KEY` and `CDK_APP_ID`, then run `npx cdk deploy`. This creates all required AWS resources.

Can I run the MCP server locally?

Yes, navigate to `/cloudflare-mcp-server`, install dependencies, and run `npm run dev` to run the server locally.

Comments

More Memory & Knowledge MCP servers

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

HandbookHub MCP

veryayskiy

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

agentleFS

One permissioned folder your team and your AI agents both log into.