--- title: 4 Ways to Secure Bedrock Agent-Initiated Actions with... description: Bedrock AI agents can now interact directly with AWS services like S3, Lambda, EC2, and RDS, but shared or long-lived credentials make it hard to enforce least... canonical: https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: 4 Ways to Secure Bedrock Agent-Initiated Actions with Teleport | daily.dev og:description: Bedrock AI agents can now interact directly with AWS services like S3, Lambda, EC2, and RDS, but shared or long-lived credentials make it hard to enforce least... og:url: https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc og:image: https://api.daily.dev/og/posts/2Zaw9ggRC.png og:image:alt: 4 Ways to Secure Bedrock Agent-Initiated Actions with Teleport 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. # 4 Ways to Secure Bedrock Agent-Initiated Actions with Teleport **[Teleport](https://daily.dev/sources/teleport)** · 8 min read · 0 upvotes · 0 comments ## Summary Bedrock AI agents can now interact directly with AWS services like S3, Lambda, EC2, and RDS, but shared or long-lived credentials make it hard to enforce least privilege or audit agent behavior. Teleport addresses this by assigning each MCP server and agent a unique identity via AWS IAM roles and x.509 certificates, then issuing short-lived, policy-scoped credentials per task. Four example use cases are covered: scoping Lambda invocations for support agents, just-in-time EC2 access for remediation agents, restricted S3 access for training pipelines, and traceable RDS access for finance report agents. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How can I restrict what AWS resources a Bedrock AI agent using MCP is allowed to access? Assign each MCP server and agent a unique identity using AWS IAM roles and x.509 certificates, then enforce policy at request time. When an agent starts a task, the MCP server sends the agent ID, target resource, and task description to an access control layer like Teleport, which verifies the request against policy and issues a short-lived certificate scoped to that specific session and resource. _Teams securing agentic AWS workflows can track access-control patterns like these on daily.dev._ ### Why is it risky for AI agents and MCP servers to share the same admin AWS credentials? Shared admin credentials make it impossible to distinguish which agent or server performed an action, and these credentials typically do not rotate or expire without manual intervention. This prevents fine-grained revocation after a misfired task and makes it impossible to attribute who or what touched production data at a given time, unlike per-agent short-lived certificates. _Developers designing safer AI agent permissions can follow this kind of guidance on daily.dev._ ## Similar posts on daily.dev - [Securing Amazon Bedrock AgentCore with Auth0 for AI Agents](https://daily.dev/posts/securing-amazon-bedrock-agentcore-with-auth0-for-ai-agents-4vbphqldn) · Auth0 · 0 upvotes · 0 comments - [Cracks in the Bedrock: Agent God Mode](https://daily.dev/posts/cracks-in-the-bedrock-agent-god-mode-euuul4yzk) · Unit 42 · 0 upvotes · 0 comments - [Introducing agent-to-agent protocol support in Amazon Bedrock AgentCore Runtime](https://daily.dev/posts/introducing-agent-to-agent-protocol-support-in-amazon-bedrock-agentcore-runtime-ohtzqijud) · AWS · 7 upvotes · 0 comments - [From 'Works on My Machine' to Production-Ready: Building AI Agents with Amazon Bedrock AgentCore](https://daily.dev/posts/from-works-on-my-machine-to-production-ready-building-ai-agents-with-amazon-bedrock-agentcore-bt6s0repy) · Pulumi · 1 upvotes · 0 comments --- Tags: [#cloud](https://daily.dev/tags/cloud), [#aws](https://daily.dev/tags/aws), [#mcp](https://daily.dev/tags/mcp), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock) [View this post on daily.dev](https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc) ```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":"4 Ways to Secure Bedrock Agent-Initiated Actions with Teleport","url":"https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc"},"datePublished":"2026-08-23T12:19:31.022Z","dateModified":"2026-08-23T12:40:00.713Z","description":"Bedrock AI agents can now interact directly with AWS services like S3, Lambda, EC2, and RDS, but shared or long-lived credentials make it hard to enforce least...","image":"https://media.daily.dev/image/upload/s--0_ODbtD2--/f_auto/v1722860399/public/Placeholder%2008","thumbnailUrl":"https://media.daily.dev/image/upload/s--0_ODbtD2--/f_auto/v1722860399/public/Placeholder%2008","isAccessibleForFree":true,"articleSection":"Teleport","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":"Teleport","logo":"https://media.daily.dev/image/upload/s--Dw-Bbw6O--/c_limit,w_256/f_auto,q_auto/v1787487494/logos/teleport?_a=BAMAMicg0","url":"https://daily.dev/sources/teleport"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cloud,aws,mcp,amazon-bedrock","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Teleport","item":"https://daily.dev/sources/teleport"},{"@type":"ListItem","position":3,"name":"4 Ways to Secure Bedrock Agent-Initiated Actions with Teleport"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/4-ways-to-secure-bedrock-agent-initiated-actions-with-teleport-2zaw9ggrc#faq","mainEntity":[{"@type":"Question","name":"How can I restrict what AWS resources a Bedrock AI agent using MCP is allowed to access?","acceptedAnswer":{"@type":"Answer","text":"Assign each MCP server and agent a unique identity using AWS IAM roles and x.509 certificates, then enforce policy at request time. When an agent starts a task, the MCP server sends the agent ID, target resource, and task description to an access control layer like Teleport, which verifies the request against policy and issues a short-lived certificate scoped to that specific session and resource. Teams securing agentic AWS workflows can track access-control patterns like these on daily.dev."}},{"@type":"Question","name":"Why is it risky for AI agents and MCP servers to share the same admin AWS credentials?","acceptedAnswer":{"@type":"Answer","text":"Shared admin credentials make it impossible to distinguish which agent or server performed an action, and these credentials typically do not rotate or expire without manual intervention. This prevents fine-grained revocation after a misfired task and makes it impossible to attribute who or what touched production data at a given time, unlike per-agent short-lived certificates. Developers designing safer AI agent permissions can follow this kind of guidance on daily.dev."}}]} ```