--- title: Tools your agent can actually trust | daily.dev description: A walkthrough demonstrates Foundry Toolbox, a centralized management layer for AI agent components such as MCP servers, knowledge bases, and skills. Instead of... canonical: https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Tools your agent can actually trust | daily.dev og:description: A walkthrough demonstrates Foundry Toolbox, a centralized management layer for AI agent components such as MCP servers, knowledge bases, and skills. Instead of... og:url: https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto og:image: https://api.daily.dev/og/posts/9nXs2QnTo.png og:image:alt: Tools your agent can actually trust 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. # Tools your agent can actually trust **[Microsoft Developer](https://daily.dev/sources/microsoftdeveloper)** · 5 min read · 2 upvotes · 0 comments ## Summary A walkthrough demonstrates Foundry Toolbox, a centralized management layer for AI agent components such as MCP servers, knowledge bases, and skills. Instead of configuring authentication, governance, and endpoints separately for each tool, developers can consolidate everything into a single toolbox with one endpoint and one authentication method. The demo builds a 'cupcake agent' by adding an MCP server, a web search tool, a guardrail for security (jailbreak/prompt injection protection), and a custom skill, then publishes it and integrates the generated code into an IDE using Microsoft Agent Framework, though the toolbox also supports GitHub Copilot SDK and LangGraph. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Foundry Toolbox used for in AI agent development? Foundry Toolbox centralizes management of an agent's tools, knowledge bases, and skills under a single endpoint and authentication method. It handles governance, observability, and access control across MCP servers, web search, and other integrations, and supports versioning so updates propagate automatically. Generated integration code works with frameworks like Microsoft Agent Framework, GitHub Copilot SDK, or LangGraph. _Developers wiring up multi-tool agents can track approaches like this on daily.dev._ ### How do guardrails help secure an AI agent against prompt injection? Guardrails are a configurable safety layer added to an agent's toolbox to reduce risks like jailbreaking and prompt injection, particularly important for consumer-facing applications. They are created alongside the agent's other components such as tools and skills, then published together as part of the toolbox configuration. _Teams shipping consumer-facing agents can compare guardrail approaches on daily.dev._ ## Similar posts on daily.dev - [Introducing Toolboxes in Foundry](https://daily.dev/posts/introducing-toolboxes-in-foundry-lcwb5gnuf) · DevBlogs · 0 upvotes · 0 comments - [Microsoft Foundry Tackles the AI Agent Tool Problem Nobody Talks About](https://daily.dev/posts/microsoft-foundry-tackles-the-ai-agent-tool-problem-nobody-talks-about-msoxw2ziz) · DevOps.com · 0 upvotes · 0 comments - [Building Agents that Act on Your Behalf with Toolboxes in Foundry](https://daily.dev/posts/building-agents-that-act-on-your-behalf-with-toolboxes-in-foundry-zalwkhdfv) · DevBlogs · 0 upvotes · 0 comments --- Tags: [#microsoft](https://daily.dev/tags/microsoft), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#langgraph](https://daily.dev/tags/langgraph) [View this post on daily.dev](https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto) ```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":"Tools your agent can actually trust","url":"https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto"},"datePublished":"2026-09-29T23:16:16.551Z","dateModified":"2026-09-29T23:16:33.102Z","description":"A walkthrough demonstrates Foundry Toolbox, a centralized management layer for AI agent components such as MCP servers, knowledge bases, and skills. Instead of...","image":"https://i.ytimg.com/vi/hW6feo19LXo/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/hW6feo19LXo/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Microsoft Developer","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":"Microsoft Developer","logo":"https://media.daily.dev/image/upload/s--xZzU3zUq--/f_auto/v1746714872/logos/microsoftdeveloper","url":"https://daily.dev/sources/microsoftdeveloper"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"microsoft,ai-agents,mcp,langgraph","timeRequired":"PT5M","video":{"@type":"VideoObject","name":"Tools your agent can actually trust","description":"A walkthrough demonstrates Foundry Toolbox, a centralized management layer for AI agent components such as MCP servers, knowledge bases, and skills. Instead of...","thumbnailUrl":"https://i.ytimg.com/vi/hW6feo19LXo/sddefault.jpg","uploadDate":"2026-09-29T23:16:16.551Z","duration":"PT5M","url":"https://api.daily.dev/r/9nXs2QnTo","embedUrl":"https://www.youtube.com/embed/hW6feo19LXo"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Microsoft Developer","item":"https://daily.dev/sources/microsoftdeveloper"},{"@type":"ListItem","position":3,"name":"Tools your agent can actually trust"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tools-your-agent-can-actually-trust-9nxs2qnto#faq","mainEntity":[{"@type":"Question","name":"What is Foundry Toolbox used for in AI agent development?","acceptedAnswer":{"@type":"Answer","text":"Foundry Toolbox centralizes management of an agent's tools, knowledge bases, and skills under a single endpoint and authentication method. It handles governance, observability, and access control across MCP servers, web search, and other integrations, and supports versioning so updates propagate automatically. Generated integration code works with frameworks like Microsoft Agent Framework, GitHub Copilot SDK, or LangGraph. Developers wiring up multi-tool agents can track approaches like this on daily.dev."}},{"@type":"Question","name":"How do guardrails help secure an AI agent against prompt injection?","acceptedAnswer":{"@type":"Answer","text":"Guardrails are a configurable safety layer added to an agent's toolbox to reduce risks like jailbreaking and prompt injection, particularly important for consumer-facing applications. They are created alongside the agent's other components such as tools and skills, then published together as part of the toolbox configuration. Teams shipping consumer-facing agents can compare guardrail approaches on daily.dev."}}]} ```