Distributed Systems Engineer

Why Ideavo uses E2B sandboxes. If AI can generate code, it also needs a place to run that code. That is exactly why Ideavo is writing this blog. A lot of builders see "sandbox" in Ideavo and understand that it is part of the product, but not necessarily why it exists, why Ideavo ask for an E2B key, or why Ideavo chose this setup in the first place. The short answer is simple: generated code needs a real execution environment, and Ideavo believe that environment should stay transparent, affordable, and under your control. That is why Ideavo integrates with E2B instead of hiding code execution behind its own servers. What is a sandbox? A sandbox is an isolated runtime environment where code can run safely without affecting the rest of your system. Think of it as a separate computer created just for the task at hand. Code can run there, dependencies can be installed, files can be created, and commands can be executed, all inside an isolated environment instead of directly on your machine or inside shared platform infrastructure. That isolation matters a lot when AI is involved, because generated code is only useful if it can actually be executed, tested, and refined in a real environment. Why is a sandbox required? AI-generated code is not finished the moment it is written. It usually needs to be: * executed * tested * debugged * iterated on * connected to files, packages, or terminal commands Without a sandbox, an AI product can generate code, but it cannot meaningfully run that code in a secure and controlled way. That makes the sandbox essential. It is the execution layer that turns generated code into a working development loop. If you want an app builder to do more than just output code snippets, it needs a real runtime behind it. What is E2B? E2B is an open-source runtime for executing AI-generated code in secure cloud sandboxes. E2B describes its sandbox as a fast, secure Linux VM created on demand for an agent, with support for running code, commands, filesystems, and more. In simple terms, E2B gives AI products a dedicated isolated computer in the cloud where generated code can actually run. That makes it a strong fit for products like Ideavo, where code execution is part of the product experience, not just an optional extra. Why Ideavo asks you to bring your own E2B account. Because Ideavo want sandbox execution to stay transparent, affordable, and under your control. 1. Cost: Ideavo gives cost-to-cost API usage. Ideavo is built around transparent usage. The same principle applies to sandbox execution. Running its own managed sandbox layer for every user would mean adding another infrastructure cost on top of the platform. That would either introduce markup or force sandbox usage into a more opaque bundled pricing model. Ideavo do not want that. By asking you to connect your own E2B account, sandbox billing stays direct. You pay E2B for sandbox compute, and that compute remains outside a hidden platform markup layer. That keeps the model simple:Ideavo handles the product experience.E2B handles the sandbox runtime.You keep visibility into where compute costs come from. E2B also publicly states that new users receive $100 in free credits, which is enough to get started and can cover multiple projects depending on usage. 2. Ownership and security: your code runs in your sandbox. The second reason is control. When you connect your own E2B account, the code runs in a sandbox attached to your runtime provider account, not inside a hidden Ideavo-owned execution layer. That matters because code execution is a sensitive part of the stack. Builders should know where code is running and who controls that environment. Using your own E2B key keeps the sandbox layer closer to you. It gives you clearer ownership of the runtime, clearer billing, and a cleaner separation between the product interface and the execution environment. That is a better model than asking users to blindly trust a black-box runtime they cannot see or control. Sandbox compute selection. Not every project needs the same sandbox setup. Some projects only need a lightweight environment for everyday coding tasks. Others become heavier over time more dependencies, larger builds, more background processes, or workflows that simply need more resources to run smoothly. That is why Ideavo lets you choose the compute tier for your sandbox directly from project settings. You can select between: * Default - 4 vCPU / 4 GB RAM - a balanced setup for everyday coding tasks * Pro - 8 vCPU / 8 GB RAM - more compute for heavier, more resource-intensive workflows This becomes useful when your project gets more complex or when your sandbox starts feeling slower than usual. If your app is installing more packages, running larger builds, or handling more demanding workflows, moving to a higher compute tier gives the sandbox more room to work with.

Docker & E2B partner to introduce MCP support in E2B Sandbox. Today, E2b is launching native MCP support in the E2B Sandbox. E2b has partnered with the Docker team to bring over 200+ MCP tools from the official Docker's MCP catalog to every sandbox. Watch the announcement video with Mark Cavage (President & COO at Docker), Tushar Jain (Head of Product & Engineering at Docker), and Vasek Mlejnsky (CEO at E2B). Model Context Protocol (MCP) is an open-source standard that makes it easy to connect AI systems like AI agents to external applications and use those external applications as LLM tools. In short, MCP tools make AI agents more useful and give them easy access to real world applications. However, the MCP tools can suffer from various critical security issues that can put your infrastructure at risk. Additionally, having your agents use MCP tools in sandboxes has been until now painful and required a significant amount of sandbox customization making developers spend their time on manually setting up various MCP tools and frameworks inside the sandbox instead of focusing on building the agent. E2b is bringing the MCP support to E2B sandboxes and partnering with Docker to give developers quick and easy access to hundreds of type-safe MCPs in a secure sandbox. The MCPs have been verified and are safe to consume through a single unified interface. What previously took tens of minutes to hours of setup now takes a few seconds. E2B has already been powering secure sandboxes for agent code paths, and Docker has already produced hundreds of trusted MCP servers. Together, E2b built a completely safe and trustworthy foundation for connecting AI agents with real-world tools. This partnership with Docker spans both the content collaboration and the open-source MCP gateway. Together, E2b is building on the momentum of a growing ecosystem of open, secure, and interoperable tools - while later introducing commercial extensions on top of it. The MCP tools in your E2B sandbox can be reached from both inside (accessing the MCP gateway running on localhost) and outside (via the sandbox URL), allowing your local code and sandboxed agents to share the same tools securely. import Sandbox from 'e2b' const sandbox = await Sandbox.create({ mcp: {browserbase: {apiKey: process.env.BROWSERBASE_API_KEY!, geminiApiKey: process.env.GEMINI_API_KEY!, projectId: process.env.BROWSERBASE_PROJECT_ID!,}, exa: {apiKey: process.env.EXA_API_KEY!,}, notion: {internalIntegrationToken: process.env.NOTION_API_KEY!,},}, }); import os from e2b import Sandbox sandbox = await Sandbox.create( mcp={ "browserbase": {"apiKey": os.environ["BROWSERBASE_API_KEY"], "geminiApiKey": os.environ["GEMINI_API_KEY"], "projectId": os.environ["BROWSERBASE_PROJECT_ID"],}, "exa": {"apiKey": os.environ["EXA_API_KEY"],}, "notion": {"internalIntegrationToken": os.environ["NOTION_API_KEY"],},}) MCP has become a widely adopted standard for connecting tools to LLMs. By bringing native MCP support to the E2B sandboxes, E2b is making it easy for developers and AI agents to securely access all the tools from Docker's MCP catalog such as Browserbase, Stripe, GitHub, Context7, Grafana, or Notion and make their agents more useful in just a few lines of code. Each MCP tool runs as a Docker container inside the E2B sandbox. The E2B SDK gives you autocomplete, type validation, and one unified interface to control and configure each MCP tool. How to start. Get started by installing the latest version of the E2B SDK and following quickstart examples in its documentation. Towards secure and vetted MCP tools. Its partnership with Docker allows E2b to bring many official and verified MCP servers in a secure, isolated environment. The combination of Docker's powerful MCP catalog, wide developer adoption, and its secured sandboxes make running MCP servers not only safer but also very easily accessible for all the AI developers building at the forefront of what's possible with the state-of-the-art models. E2b has given early access to the sandbox MCP support to selected of E2B users and partners. E2b want to thank Genspark, Groq, Exa, Browserbase, and others for providing valuable feedback and supporting this launcj. "E2B MCP with code unlocks an exciting paradigm of MCP in code while keeping the dev experience simple and intuitive." "Genspark uses E2B Sandbox with MCP integration to let users run 200+ MCPs from Docker's official catalog with minimal setup, giving access to tools like Notion, Stripe, Browserbase, or Exa. E2B is an essential layer in our infrastructure, enabling us to securely run any MCP directly from GitHub inside isolated sandboxes." Secure AI Sandbox