--- title: How to use Muse's Tailscale integration to control... description: Meta's new personal AI agent, Muse, includes a built-in Tailscale connector that joins a user's tailnet as its own node, letting it check on self-hosted... canonical: https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How to use Muse's Tailscale integration to control access to your network. | daily.dev og:description: Meta's new personal AI agent, Muse, includes a built-in Tailscale connector that joins a user's tailnet as its own node, letting it check on self-hosted... og:url: https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q og:image: https://api.daily.dev/og/posts/WCT0GuG6q.png og:image:alt: How to use Muse's Tailscale integration to control access to your network. 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. # How to use Muse's Tailscale integration to control access to your network. **[Tailscale](https://daily.dev/sources/tailscale)** · 6 min read · 0 upvotes · 0 comments ## Summary Meta's new personal AI agent, Muse, includes a built-in Tailscale connector that joins a user's tailnet as its own node, letting it check on self-hosted services, SSH into machines, and manage devices. The piece explains how Tailscale's access controls (grants, tags, encrypted connections) let users limit what Muse can reach regardless of Meta's own safeguards against the 'lethal trifecta' (private data access, untrusted content exposure, and external communication combined). It also covers Muse's default protections like outbound-only connections and explicit per-device confirmation, plus other Tailscale integrations for AI tools like OpenClaw, Hermes, Pi, LM Studio, and Tailscale's own Aperture gateway and coding-agent skill. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the 'lethal trifecta' in AI agent security? It's a dangerous combination where an AI agent has access to private data, exposure to untrusted content, and the ability to communicate externally, all at once. If an agent combines all three, attackers can potentially exfiltrate sensitive data through prompt injection. Safe agent design keeps at most two of these three conditions true simultaneously. _Developers securing agent architectures track lethal-trifecta mitigation patterns like this on daily.dev._ ### How does Meta's Muse AI agent connect to Tailscale networks? Muse joins a user's tailnet as its own separate node after logging in with an identity provider, independent of any existing Tailscale session on phone or laptop. Once connected, it can check node status, integrate with self-hosted services like Immich, and even use Tailscale SSH. It only makes outbound connections and requires explicit confirmation before first connecting to any device. _Anyone weighing AI agent access to self-hosted gear follows integration details like Muse's on daily.dev._ ### Can Tailscale limit what an AI agent like Muse can access on my network even if the vendor's safeguards fail? Yes, Tailscale treats Muse like any other node, so its own grants, tags, and access control rules apply regardless of vendor-side protections. Users can restrict Muse to only explicitly allowed devices, granting standing or one-time access and revoking it anytime, adding a layer of control independent of Meta's built-in defaults. _Teams deciding how much trust to extend to AI agents on their network follow setups like this on daily.dev._ ## Similar posts on daily.dev - [Tailscale is the only home lab change I made this year that I actually noticed](https://daily.dev/posts/tailscale-is-the-only-home-lab-change-i-made-this-year-that-i-actually-noticed-hkczhi2ty) · XDA Developers · 0 upvotes · 0 comments - [Build a flexible AI stack with Aperture](https://daily.dev/posts/build-a-flexible-ai-stack-with-aperture-njmztuopa) · Tailscale · 0 upvotes · 0 comments - [“Agents need boring infrastructure around them”: Why we need to take an interest in ‘invisible’ AI](https://daily.dev/posts/agents-need-boring-infrastructure-around-them-why-we-need-to-take-an-interest-in-invisible-ai-qpdb4it6t) · The New Stack · 1 upvotes · 0 comments - [What Tailscale can \(and can't\) fix with OpenClaw](https://daily.dev/posts/what-tailscale-can-and-can-t-fix-with-openclaw-9j475kucg) · Tailscale · 3 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#self-hosting](https://daily.dev/tags/self-hosting), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#tailscale](https://daily.dev/tags/tailscale) [View this post on daily.dev](https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q) ```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":"How to use Muse's Tailscale integration to control access to your network.","url":"https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q"},"datePublished":"2026-09-30T15:10:40.968Z","dateModified":"2026-09-30T18:38:10.208Z","description":"Meta's new personal AI agent, Muse, includes a built-in Tailscale connector that joins a user's tailnet as its own node, letting it check on self-hosted...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/628577b83c93a8cc9b72730c8b310ee7?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/628577b83c93a8cc9b72730c8b310ee7?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Tailscale","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":"Tailscale","logo":"https://media.daily.dev/image/upload/s--QeDb_zoC--/f_auto/v1711188591/logos/tailscale","url":"https://daily.dev/sources/tailscale"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,self-hosting,prompt-injection,tailscale","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Tailscale","item":"https://daily.dev/sources/tailscale"},{"@type":"ListItem","position":3,"name":"How to use Muse's Tailscale integration to control access to your network."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-to-use-muse-s-tailscale-integration-to-control-access-to-your-network--wct0gug6q#faq","mainEntity":[{"@type":"Question","name":"What is the 'lethal trifecta' in AI agent security?","acceptedAnswer":{"@type":"Answer","text":"It's a dangerous combination where an AI agent has access to private data, exposure to untrusted content, and the ability to communicate externally, all at once. If an agent combines all three, attackers can potentially exfiltrate sensitive data through prompt injection. Safe agent design keeps at most two of these three conditions true simultaneously. Developers securing agent architectures track lethal-trifecta mitigation patterns like this on daily.dev."}},{"@type":"Question","name":"How does Meta's Muse AI agent connect to Tailscale networks?","acceptedAnswer":{"@type":"Answer","text":"Muse joins a user's tailnet as its own separate node after logging in with an identity provider, independent of any existing Tailscale session on phone or laptop. Once connected, it can check node status, integrate with self-hosted services like Immich, and even use Tailscale SSH. It only makes outbound connections and requires explicit confirmation before first connecting to any device. Anyone weighing AI agent access to self-hosted gear follows integration details like Muse's on daily.dev."}},{"@type":"Question","name":"Can Tailscale limit what an AI agent like Muse can access on my network even if the vendor's safeguards fail?","acceptedAnswer":{"@type":"Answer","text":"Yes, Tailscale treats Muse like any other node, so its own grants, tags, and access control rules apply regardless of vendor-side protections. Users can restrict Muse to only explicitly allowed devices, granting standing or one-time access and revoking it anytime, adding a layer of control independent of Meta's built-in defaults. Teams deciding how much trust to extend to AI agents on their network follow setups like this on daily.dev."}}]} ```