--- title: Scaling organizational knowledge in Kiro with Amazon... description: A tutorial showing how to connect Amazon Bedrock Knowledge Bases to the Kiro agentic IDE via the Model Context Protocol (MCP), enabling developers to query... canonical: https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Scaling organizational knowledge in Kiro with Amazon Bedrock Knowledge Bases, LangChain, and MCP | daily.dev og:description: A tutorial showing how to connect Amazon Bedrock Knowledge Bases to the Kiro agentic IDE via the Model Context Protocol (MCP), enabling developers to query... og:url: https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z og:image: https://api.daily.dev/og/posts/51EZ7VF5Z.png og:image:alt: Scaling organizational knowledge in Kiro with Amazon Bedrock Knowledge Bases, LangChain, and MCP og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Scaling organizational knowledge in Kiro with Amazon Bedrock Knowledge Bases, LangChain, and MCP **[AWS](https://daily.dev/sources/aws)** · 13 min read · 1 upvotes · 0 comments ## Summary A tutorial showing how to connect Amazon Bedrock Knowledge Bases to the Kiro agentic IDE via the Model Context Protocol (MCP), enabling developers to query organizational documentation (ADRs, API specs, runbooks, coding standards) directly from their editor without context switching. The integration uses the awslabs bedrock-kb-retrieval-mcp-server, which translates natural language queries into vector search operations against OpenSearch Serverless and returns cited answers in-editor. Two paths are covered: tagging an existing Knowledge Base with mcp-multirag-kb=true for instant connection, or deploying fresh infrastructure via an AWS CDK sample repo. A LangChain alternative is also described for provider portability. The same MCP config works for Kiro CLI, enabling headless Knowledge Base queries in CI/CD pipelines for automated compliance checks. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I connect an existing Amazon Bedrock Knowledge Base to Kiro IDE using MCP? Tag your existing Knowledge Base with the key-value pair mcp-multirag-kb=true so the MCP server can auto-discover it, then add the awslabs.bedrock-kb-retrieval-mcp-server configuration to .kiro/settings/mcp.json in your project root, specifying your AWS region and KB_INCLUSION_TAG_KEY. Restart Kiro and it connects automatically. The uv package manager's uvx command runs the server without a permanent install. Existing documents, embeddings, and vector stores remain untouched. _Teams wiring up Bedrock Knowledge Bases to their editors track integration patterns and gotchas on daily.dev._ ### What is the difference between Kiro steering files and using MCP with Amazon Bedrock Knowledge Bases? Steering files (.kiro/steering/*.md) deliver static, project-level instructions — coding standards and team conventions that fit in a few files and govern Kiro's behavior on every interaction. MCP with Bedrock Knowledge Bases is for large, dynamic corpora: hundreds of ADRs, API specs, runbooks, and security guidelines that no developer can internalize. Semantic search surfaces the right document at the right moment rather than loading everything upfront. _Developers deciding how to structure context for AI coding tools find real-world comparisons on daily.dev._ ### How does the Kiro MCP server query Amazon Bedrock Knowledge Bases under the hood? When a developer asks a question in Kiro, it sends the query to the MCP server as a local child process over stdio. The server calls the Bedrock Knowledge Bases Retrieve API (not RetrieveAndGenerate). Bedrock embeds the query using Amazon Titan Text Embeddings v2 and searches an OpenSearch Serverless vector store. Ranked chunks with relevance scores are returned to Kiro, which synthesizes them into a cited answer using its own LLM and conversation context. _Engineers building RAG pipelines on AWS follow architecture decisions like this one on daily.dev._ ## Similar posts on daily.dev - [Introducing Amazon Bedrock Managed Knowledge Base for faster, more accurate enterprise AI applications](https://daily.dev/posts/introducing-amazon-bedrock-managed-knowledge-base-for-faster-more-accurate-enterprise-ai-applicatio-lfogbfa0k) · AWS · 0 upvotes · 0 comments - [Amazon Bedrock Managed Knowledge Base is now generally available](https://daily.dev/posts/amazon-bedrock-managed-knowledge-base-is-now-generally-available-vgon8g72v) · AWS · 0 upvotes · 0 comments --- Tags: [#mcp](https://daily.dev/tags/mcp), [#rag](https://daily.dev/tags/rag), [#langchain](https://daily.dev/tags/langchain), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock) [View this post on daily.dev](https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Scaling organizational knowledge in Kiro with Amazon Bedrock Knowledge Bases, LangChain, and MCP","url":"https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z"},"datePublished":"2026-08-10T11:25:29.760Z","dateModified":"2026-08-10T11:26:06.343Z","description":"A tutorial showing how to connect Amazon Bedrock Knowledge Bases to the Kiro agentic IDE via the Model Context Protocol (MCP), enabling developers to query...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fd57552cecfecbb5f653b0571108e225?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fd57552cecfecbb5f653b0571108e225?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"AWS","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"mcp,rag,langchain,amazon-bedrock","timeRequired":"PT13M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"Scaling organizational knowledge in Kiro with Amazon Bedrock Knowledge Bases, LangChain, and MCP"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/scaling-organizational-knowledge-in-kiro-with-amazon-bedrock-knowledge-bases-langchain-and-mcp-51ez7vf5z#faq","mainEntity":[{"@type":"Question","name":"How do I connect an existing Amazon Bedrock Knowledge Base to Kiro IDE using MCP?","acceptedAnswer":{"@type":"Answer","text":"Tag your existing Knowledge Base with the key-value pair mcp-multirag-kb=true so the MCP server can auto-discover it, then add the awslabs.bedrock-kb-retrieval-mcp-server configuration to .kiro/settings/mcp.json in your project root, specifying your AWS region and KB_INCLUSION_TAG_KEY. Restart Kiro and it connects automatically. The uv package manager's uvx command runs the server without a permanent install. Existing documents, embeddings, and vector stores remain untouched. Teams wiring up Bedrock Knowledge Bases to their editors track integration patterns and gotchas on daily.dev."}},{"@type":"Question","name":"What is the difference between Kiro steering files and using MCP with Amazon Bedrock Knowledge Bases?","acceptedAnswer":{"@type":"Answer","text":"Steering files (.kiro/steering/*.md) deliver static, project-level instructions — coding standards and team conventions that fit in a few files and govern Kiro's behavior on every interaction. MCP with Bedrock Knowledge Bases is for large, dynamic corpora: hundreds of ADRs, API specs, runbooks, and security guidelines that no developer can internalize. Semantic search surfaces the right document at the right moment rather than loading everything upfront. Developers deciding how to structure context for AI coding tools find real-world comparisons on daily.dev."}},{"@type":"Question","name":"How does the Kiro MCP server query Amazon Bedrock Knowledge Bases under the hood?","acceptedAnswer":{"@type":"Answer","text":"When a developer asks a question in Kiro, it sends the query to the MCP server as a local child process over stdio. The server calls the Bedrock Knowledge Bases Retrieve API (not RetrieveAndGenerate). Bedrock embeds the query using Amazon Titan Text Embeddings v2 and searches an OpenSearch Serverless vector store. Ranked chunks with relevance scores are returned to Kiro, which synthesizes them into a cited answer using its own LLM and conversation context. Engineers building RAG pipelines on AWS follow architecture decisions like this one on daily.dev."}}]} ```