AWS Knowledge Base MCP Server

@daohoangson

リポジトリホームページ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

daohoangson

AWS Knowledge Base MCP Server について

概要はまだありません

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

AWS Knowledge Base MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

AWS Knowledge Base MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

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.

よくある質問

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.

「メモリとナレッジ」の他のコンテンツ

priostack

ideaswave

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

Neither MCP

stonianua

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

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from