--- title: Laravel AI SDK and Laravel MCP Security Fixes: Update Now description: Two security advisories were published for Laravel's AI-related packages: laravel/ai and laravel/mcp. The laravel/ai SDK had a moderate-severity SSRF... canonical: https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Laravel AI SDK and Laravel MCP Security Fixes: Update Now | daily.dev og:description: Two security advisories were published for Laravel's AI-related packages: laravel/ai and laravel/mcp. The laravel/ai SDK had a moderate-severity SSRF... og:url: https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy og:image: https://api.daily.dev/og/posts/GQnAZbmXy.png og:image:alt: Laravel AI SDK and Laravel MCP Security Fixes: Update Now 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. # Laravel AI SDK and Laravel MCP Security Fixes: Update Now **[Laravel News](https://daily.dev/sources/ln)** · [@ericlbarnes](https://daily.dev/ericlbarnes) · 3 min read · 10 upvotes · 0 comments ## Summary Two security advisories were published for Laravel's AI-related packages: laravel/ai and laravel/mcp. The laravel/ai SDK had a moderate-severity SSRF vulnerability (CVSS 5.3) in its Vercel AI SDK and AG-UI adapters, where server-side URL fetching wasn't validated, allowing requests to internal addresses like cloud metadata services. This is fixed in version 1.0.1, which now blocks private/reserved addresses, validates redirects, and pins connections against DNS rebinding. Separately, laravel/mcp had a low-severity OAuth redirect validation issue that could let an attacker redirect an authenticated user during the OAuth flow to steal tokens or authorization codes; this is fixed in versions 0.9.6 and 1.0.1. Neither advisory has a CVE ID yet, so CVE-based scanners may miss them. Developers running either package in production are urged to run composer update immediately. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What version of laravel/ai fixes the SSRF vulnerability in the Vercel AI SDK and AG-UI adapters? Version 1.0.1 of laravel/ai fixes the server-side request forgery vulnerability. The bug existed in version 1.0.0, where the Vercel AI SDK adapter and AG-UI adapter fetched client-supplied file URLs without validation, letting attackers force the server to request internal addresses like cloud metadata services or localhost. The fix adds a guard blocking private, loopback, and reserved addresses, validates redirects, and pins connections to prevent DNS rebinding. _Teams running Laravel AI SDK in production can track fixes like this one on daily.dev._ ### What is the OAuth redirect vulnerability fixed in Laravel MCP and which versions are affected? Laravel MCP versions below 0.9.6, and version 1.0.0, had an OAuth redirect validation flaw rated Low severity. An attacker who tricks a user into following a crafted link during the OAuth flow could redirect them to an unintended destination and, depending on configuration, obtain authorization codes or tokens to take over the account. The fix ships in versions 0.9.6 and 1.0.1. _Developers configuring OAuth flows in Laravel MCP can follow security advisories like this via daily.dev._ ### Why might a CVE-based vulnerability scanner miss the Laravel AI SDK SSRF issue or the Laravel MCP OAuth issue? Neither the Laravel AI SDK SSRF advisory nor the Laravel MCP OAuth redirect advisory had a CVE ID assigned at the time of disclosure, so vulnerability scanners that rely solely on CVE databases would not flag either issue. Both are documented instead as GitHub Security Advisories, meaning teams need to check package-specific advisories directly rather than relying on CVE feeds alone. _Developers relying on automated scanning can supplement CVE feeds with advisory tracking on daily.dev._ ## Similar posts on daily.dev - [Laravel Boost Update Adds Support for the New MCP Protocol](https://daily.dev/posts/laravel-boost-update-adds-support-for-the-new-mcp-protocol-8827svtqm) · Laravel News · 3 upvotes · 0 comments - [Reusing your Laravel MCP tools in the Laravel AI SDK](https://daily.dev/posts/reusing-your-laravel-mcp-tools-in-the-laravel-ai-sdk-mfjaemkmb) · FREEK.DEV · 2 upvotes · 0 comments - [LiteLLM Vulnerability Chain: What Security Teams Running AI Gateways Need to Do Now](https://daily.dev/posts/litellm-vulnerability-chain-what-security-teams-running-ai-gateways-need-to-do-now-2dh1t9pl9) · Latest Hacking News · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#php](https://daily.dev/tags/php), [#laravel](https://daily.dev/tags/laravel), [#oauth](https://daily.dev/tags/oauth) [View this post on daily.dev](https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy) ```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":"Laravel AI SDK and Laravel MCP Security Fixes: Update Now","url":"https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy"},"datePublished":"2026-09-30T18:36:54.861Z","dateModified":"2026-10-01T15:00:15.170Z","description":"Two security advisories were published for Laravel's AI-related packages: laravel/ai and laravel/mcp. The laravel/ai SDK had a moderate-severity SSRF...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3c1f2f352ae3fe008307e159cefc2071?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3c1f2f352ae3fe008307e159cefc2071?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Laravel News","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":"Eric L. Barnes","url":"https://daily.dev/ericlbarnes","image":"https://media.daily.dev/image/upload/s--K6f982B3--/f_auto/v1755288662/avatars/avatar_9SjPngRVLKMb8ob1eVrqZ?_a=BAMClqZW0","description":"Founder of Laravel News","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":2460}},"commentCount":0,"discussionUrl":"https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":10},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,php,laravel,oauth","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Laravel News","item":"https://daily.dev/sources/ln"},{"@type":"ListItem","position":3,"name":"Laravel AI SDK and Laravel MCP Security Fixes: Update Now"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/laravel-ai-sdk-and-laravel-mcp-security-fixes-update-now-gqnazbmxy#faq","mainEntity":[{"@type":"Question","name":"What version of laravel/ai fixes the SSRF vulnerability in the Vercel AI SDK and AG-UI adapters?","acceptedAnswer":{"@type":"Answer","text":"Version 1.0.1 of laravel/ai fixes the server-side request forgery vulnerability. The bug existed in version 1.0.0, where the Vercel AI SDK adapter and AG-UI adapter fetched client-supplied file URLs without validation, letting attackers force the server to request internal addresses like cloud metadata services or localhost. The fix adds a guard blocking private, loopback, and reserved addresses, validates redirects, and pins connections to prevent DNS rebinding. Teams running Laravel AI SDK in production can track fixes like this one on daily.dev."}},{"@type":"Question","name":"What is the OAuth redirect vulnerability fixed in Laravel MCP and which versions are affected?","acceptedAnswer":{"@type":"Answer","text":"Laravel MCP versions below 0.9.6, and version 1.0.0, had an OAuth redirect validation flaw rated Low severity. An attacker who tricks a user into following a crafted link during the OAuth flow could redirect them to an unintended destination and, depending on configuration, obtain authorization codes or tokens to take over the account. The fix ships in versions 0.9.6 and 1.0.1. Developers configuring OAuth flows in Laravel MCP can follow security advisories like this via daily.dev."}},{"@type":"Question","name":"Why might a CVE-based vulnerability scanner miss the Laravel AI SDK SSRF issue or the Laravel MCP OAuth issue?","acceptedAnswer":{"@type":"Answer","text":"Neither the Laravel AI SDK SSRF advisory nor the Laravel MCP OAuth redirect advisory had a CVE ID assigned at the time of disclosure, so vulnerability scanners that rely solely on CVE databases would not flag either issue. Both are documented instead as GitHub Security Advisories, meaning teams need to check package-specific advisories directly rather than relying on CVE feeds alone. Developers relying on automated scanning can supplement CVE feeds with advisory tracking on daily.dev."}}]} ```