Retool launches the first centralized agent harness. Oct 6, 2026 Today, Retool is announcing early access to a new centralized agent harness which gives every employee an agent to work with in Slack, Teams, and Google Chat, while maintaining company-wide control over the tools, data, and models those agents can use. Local agents are extremely powerful. Today, all engineers at Retool use Codex, Claude Code, and Cursor to write code, run tests, install programs, and use the terminal. Because these agents are run locally, they can do this against a real dev environment and automate many coding tasks. And since it lives in a development sandbox, it's safe: it can test code to check if it broke anything and revert the changes to try again if it needs to. The rest of the company doesn't have that sandbox. Give an agent access to live business systems, and its mistakes have real consequences. Agents can revert bad code, but they can't revert an email sent to the wrong customer. Using agents across a company means controlling what they can do before they do it. As more people put agents to work, local-first agent harnesses show their strain. One agent on one computer works fine, even great. But what happens when you have to manage a thousand agents running on a thousand computers? Enterprises need better tools and controls to guide, set limits, and control than what local agent harness platforms can offer. Retool think business agents should be managed on central company infrastructure. The enterprise agent harness. The core idea is straightforward: put a shared policy and execution layer between agents and company systems. Tool calls pass through a single gateway you control, so permissions and policies can be applied consistently and activity can be traced back to the agent that performed it. Retool already handles much of the unglamorous work this requires: connecting to the systems companies run on, mapping who's allowed to touch what, and keeping a record of what happened. Retool has built its agent harness on that foundation and expanded the system. Manage every agent on shared company infrastructure. The harness runs centrally and can be deployed on-prem to your own VPC, giving you full control over the environment and its data ingress and egress. Give every person their own agent (or multiple), each with its own virtualized filesystem, memory, and accumulated context. Preconfigure every agent with skills and scheduled jobs, and customize the onboarding flow to fit your business. From there, your users can delegate access to tools and data within the limits you set centrally. Configure which frontier models or open source models different users can use. Dynamically route models based on the quality they need and the cost that makes sense for their work. The agent infrastructure should always give you the best and cheapest option available on the market. Turn what works into a shared company capability. Every file, skill, and piece of code is stored in centrally hosted permissioned folders that map to your existing identity groups. This means that whenever someone works out a good way to do something, you can promote it once and make it available to the right team. Each team can build on that work instead of starting from scratch. Delegate local authority over the agent's skills and abilities to the early adopters of AI that are close to the teams and departments. Allow them to evangelize best practices and surface efficiency and productivity metrics to them. Control what agents can do. Tool calls pass through a gateway you control. Policies can inspect the arguments passed to a tool, so permission to use a tool doesn't have to mean permission to use it in any way the agent chooses. These limits are enforced outside the model. If an agent misunderstands a request or encounters a malicious instruction, its tool calls still have to pass the policy checks. You don't have to rely on the agent remembering a rule in its prompt. Retool has made deliberate choices about access: no employee laptop access, no browser automation, and no desktop control. Agents run in a centrally hosted sandbox and reach business systems through governed tools. The sandbox contains their local work; the tool policies govern the actions they take outside it. Get visibility into actions and costs. Agents are modeled as their own actor and given a virtual service account with its own set of policies that exist separately from the user model. They are also separate actors in the audit log - you can distinguish what someone did directly from what their agent did with delegated access. As more work gets handed to agents, you need to know who acted, not just whose account was involved. Actions, inputs, and outputs are logged by person, model, and job. You can trace token spend to the work it funded, investigate an expensive run, and decide whether the result was worth the cost. Let everyone work with agents where work happens. People can work with their agents directly in Slack, Google Chat, and Teams. They can ask for work in the tools they already use, without moving to a separate desktop app. Agents can also run on a schedule. Describe a recurring task in a sentence and turn it into an automation, without filing a ticket. A useful one-off task can become something that runs every week. Join the waitlist. Retool has been running this internally at Retool for the last 4 months. Every new hire who joins uses this by default and Retool can't imagine working at Retool without it. On top of its own usage, Retool is happy that the product has been used by scrappy startups all the way to some of the largest companies in the F500. Retool is now beginning to roll out access to the next hundred customers over the next few weeks. If you're interested in learning more, join the waitlist here!

Build and deploy apps with Retool's CLI. Sep 24, 2026 If you've been using its MCP server, you're familiar with the benefits of working in Retool from Claude, Codex, and other agents. Now, with its new command line interface (CLI), you can build Retool apps locally using bash commands or natural language prompting. New CLI capabilities. The new Retool CLI allows users to write and validate React apps directly on their machines while Retool handles governance, permissions, and resource access checks. Retool's agent and sandbox is only invoked for previewing or publishing. This structure allows for faster building - writing code locally avoids an agent-to-agent loop and is more familiar for developers who are used to working directly with their repository. These benefits have been evident from the start of its private beta. Stackdrop, a firm that builds custom internal apps for operations and engineering teams, found retool check to be particularly useful while building apps for a new client. This one command validates the project before it's deployed and it works in seconds, local and offline. The validator caught two subtle placeholder-ordering bugs in code they'd written, where the SQL read perfectly and would have written the wrong values into the wrong columns. These are the type of bugs you otherwise meet in production much later, and no amount of code review was going to find them. Mahmoud, Stackdrop's CTO, summarized his experience, "Building a Retool app this way keeps us in our preferred software development workflow. We haven't opened the app editor once for any of these builds." You can also use Retool's CLI to securely deploy apps built with vibe-coded platforms like Lovable, Cursor, and Replit. Watch Angelik, its developer advocate, export a Replit app and deploy it in Retool using Claude. How does the CLI compare to its MCP server? Generally, you can differentiate between when to use MCP or CLI with the following shorthand: building is platform dependent, admin tasks require MCP, and querying resources can be done with both. | / | MCP server | CLI | | Project plan | You know the outcome you want but you're not exactly sure of the steps | You know the exact steps and have built this kind of app before | | Typical user | Non-technical (e.g. an operations role) | Technical, comfortable with agentic coding | | Example"Take refunds.csv, create a Retool DB table from it, and build an app in the Ops folder that lists pending refunds with an approve button." CLI bash commands or natural language prompts (like the MCP example) | For a detailed look at the differences between its MCP server and CLI, read its post on when to use MCP vs. CLI. Get started with the Retool CLI. The Retool CLI requires the use of a terminal, so the agentic coding tool you choose must meet this requirement. Supported options include Claude Code and Claude from Anthropic, or Codex and ChatGPT Work from OpenAI. Retool's new CLI is currently available in public beta for cloud customers on team, business, and enterprise plans. Self-hosted customers will have access in upcoming edge and stable releases. Read the docs to get started