--- title: Tide launched Raziel for AI security. It assumes hackers... description: Tide Foundation launched Raziel, an MCP server that lets coding agents integrate its TideCloak identity and access management product, which is built around a... canonical: https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Tide launched Raziel for AI security. It assumes hackers are inside. | daily.dev og:description: Tide Foundation launched Raziel, an MCP server that lets coding agents integrate its TideCloak identity and access management product, which is built around a... og:url: https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3 og:image: https://api.daily.dev/og/posts/TZ9sC65W3.png og:image:alt: Tide launched Raziel for AI security. It assumes hackers are inside. 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. # Tide launched Raziel for AI security. It assumes hackers are inside. **[The New Stack](https://daily.dev/sources/newstack)** · [@jkriggins](https://daily.dev/jkriggins) · 7 min read · 0 upvotes · 0 comments ## Summary Tide Foundation launched Raziel, an MCP server that lets coding agents integrate its TideCloak identity and access management product, which is built around a concept called 'emergent authority.' Instead of storing admin credentials, root keys, and permissions in one central location, Tide uses threshold cryptography to compute authority in pieces that only combine momentarily when identity, policy, context, and intent align, then disappear. The goal is that even if an attacker gains root access, there is no permanent authority left to inherit. Raziel gives AI assistants knowledge of Tide's authentication, encryption, and governance model, and can generate integration playbooks, recommend hosting options, and map out an organization's 'blast radius' assuming attackers are already inside. Tide has also partnered with a Lloyd's of London underwriter to offer preferential cyber insurance terms to organizations using TideCloak. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### what is emergent authority in Tide's security model Emergent authority is a security model where authority to access systems, decrypt data, or assign permissions is not permanently held by any person, system, or AI, but is generated only when identity, policy, context, and intent align, then disappears again. It uses threshold cryptography to compute authority in pieces so it cannot be reassembled by an attacker who gains root access, unlike traditional centralized credential vaults. _developers weighing identity architecture choices can track approaches like this one on daily.dev._ ### what does Tide's Raziel MCP server do for AI coding agents Raziel is an MCP server from Tide Foundation that gives AI coding assistants deep knowledge of Tide authentication, threshold cryptography, end-to-end encryption, and governance so agents can handle the integration of TideCloak into a project. It can recommend self-hosted versus managed hosting and generate verified integration playbooks, and it also maps an organization's blast radius by assuming attackers are already inside rather than scanning for entry points. _teams automating security integrations with agents can follow tools like this on daily.dev._ ## Similar posts on daily.dev - [Prevent agentic identity theft](https://daily.dev/posts/prevent-agentic-identity-theft-exphjl34y) · Stack Overflow Blog · 1 upvotes · 0 comments - [Cyber Immunity in the AI Era: Why Traditional Security Fails Agentic AI](https://daily.dev/posts/cyber-immunity-in-the-ai-era-why-traditional-security-fails-agentic-ai-iksqrps9p) · ITNEXT · 0 upvotes · 0 comments - [This AI agent autonomously hacked a network, adapted on the fly, and demanded a ransom](https://daily.dev/posts/this-ai-agent-autonomously-hacked-a-network-adapted-on-the-fly-and-demanded-a-ransom-u3norexvg) · CSO Online · 0 upvotes · 0 comments - [Security briefing: August 2026](https://daily.dev/posts/security-briefing-august-2026-kxp9cfxfi) · Sysdig Blog · 0 upvotes · 0 comments --- Tags: [#cloud](https://daily.dev/tags/cloud), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#cryptography](https://daily.dev/tags/cryptography) [View this post on daily.dev](https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3) ```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":"Tide launched Raziel for AI security. It assumes hackers are inside.","url":"https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3"},"datePublished":"2026-08-31T10:06:04.127Z","dateModified":"2026-09-01T07:00:15.040Z","description":"Tide Foundation launched Raziel, an MCP server that lets coding agents integrate its TideCloak identity and access management product, which is built around a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2ce45ea114132f1e960143d957f3a857?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2ce45ea114132f1e960143d957f3a857?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","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":"Person","name":"Jennifer Riggins","url":"https://daily.dev/jkriggins","image":"https://lh3.googleusercontent.com/a-/AOh14Gi73gNjeWuGfr5F27hqtAdGKRmfEEUKNGT-qRG8N6g=s100","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":80}},"commentCount":0,"discussionUrl":"https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cloud,ai-agents,mcp,cryptography","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Tide launched Raziel for AI security. It assumes hackers are inside."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tide-launched-raziel-for-ai-security-it-assumes-hackers-are-inside--tz9sc65w3#faq","mainEntity":[{"@type":"Question","name":"what is emergent authority in Tide's security model","acceptedAnswer":{"@type":"Answer","text":"Emergent authority is a security model where authority to access systems, decrypt data, or assign permissions is not permanently held by any person, system, or AI, but is generated only when identity, policy, context, and intent align, then disappears again. It uses threshold cryptography to compute authority in pieces so it cannot be reassembled by an attacker who gains root access, unlike traditional centralized credential vaults. developers weighing identity architecture choices can track approaches like this one on daily.dev."}},{"@type":"Question","name":"what does Tide's Raziel MCP server do for AI coding agents","acceptedAnswer":{"@type":"Answer","text":"Raziel is an MCP server from Tide Foundation that gives AI coding assistants deep knowledge of Tide authentication, threshold cryptography, end-to-end encryption, and governance so agents can handle the integration of TideCloak into a project. It can recommend self-hosted versus managed hosting and generate verified integration playbooks, and it also maps an organization's blast radius by assuming attackers are already inside rather than scanning for entry points. teams automating security integrations with agents can follow tools like this on daily.dev."}}]} ```