AWS Knowledge Base MCP Server

Created By
daohoangsona year ago
Overview

What is AWS Knowledge Base MCP Server?

AWS Knowledge Base MCP Server is a Model Context Protocol (MCP) server implementation that enables AI assistants to search through a Knowledge Base using AWS Bedrock and Cloudflare Workers.

How to use AWS Knowledge Base MCP Server?

To use the server, set up the infrastructure using AWS resources and deploy the Cloudflare MCP server. You can then use the search_knowledge_base tool to query indexed documents.

Key features of AWS Knowledge Base MCP Server?

  • Integration with AWS Bedrock for document retrieval.
  • Efficient document search using Aurora Serverless with pgvector.
  • Cloudflare Workers for serverless execution.

Use cases of AWS Knowledge Base MCP Server?

  1. AI assistants retrieving information from a knowledge base.
  2. Document search and retrieval for applications.
  3. Efficient management of large document collections.

FAQ from AWS Knowledge Base MCP Server?

  • What technologies does the server use?

The server uses AWS Bedrock, Cloudflare Workers, and Aurora Serverless.

  • Is there a cost associated with using this server?

Yes, costs are incurred based on AWS and Cloudflare usage, which can be estimated based on the provided cost breakdown.

  • How can I deploy the server?

Follow the setup instructions in the documentation to deploy the server on AWS and Cloudflare.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
daohoangson
Star
0
Language
TypeScript
License
-

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

3 hours ago
Gpt Scrambler

2 days ago