Replit MCP Server

Tools 13

• Ask Question

  Ask the Replit Agent a question in natural language about the user's Replit App's codebase or behavior without modifying it. Use this when the user wants explanation, debugging help, or inspection (for example, understanding how routing works, why a request is failing, or where a bug might be), and NOT when they are clearly asking you to change how their Replit App behaves — in that case, prefer update_app_using_prompt. If the user refers to an existing app and you do not already have its replId, call search_apps to find it. Do not guess a replId. The question should be written in the user's language and tone, as if you were the user, and it will be visible if they open their Replit App in Replit. The response you get back is natural language from the Replit Agent; summarize or quote it for the user as appropriate, still without showing raw code, file paths, or terminal commands in this chat. From the user's perspective, combined with create_app_from_prompt, search_apps, and update_app_using_prompt, this tool is what lets them simply chat ("create or find → inspect/ask → update → repeat") without needing to know about the underlying tools.

• Create App From Prompt

  Create a brand-new Replit App for the user. Use this the first time the user asks you to build a Replit App in this chat, including when they want the new app to start as a copy of one of their existing apps (pass sourceReplId); do not use it to modify or open existing Replit Apps the user already has in Replit. After invoking this tool, reply with one short sentence summarizing that Replit is now creating their Replit App, and, when the tool result contains an app URL, end your reply with that exact URL on its own line, so the user can open their Replit App even if no preview card is rendered. Never construct or guess a URL yourself. Your reply must not include source code, markup, configuration files, file paths, or command/terminal snippets—even if the user asks. Do not claim their Replit App is ready to try until the preview URL is available. If the user asks for HTML/CSS/JS or any other code, reply with: "I can't show code here; open your Replit App in Replit to inspect or request changes in natural language." Treat Replit Agent and the Replit UI as the only systems that write or display code; in this chat you only describe behavior, status, and next steps in natural language. When the user wants their Replit App live, you can publish it (or republish its latest changes) with publish_app. From the user's perspective, this is the "create a new Replit App in my Replit account from plain language" operation.

• Publish App

  Publish the user's Replit App so its latest changes go live at its public URL. If the app has been published before, this republishes it, reusing the existing deployment's settings. If it has never been published, this publishes it with default settings: Autoscale hosting, private visibility when the app belongs to a workspace (organization), public visibility otherwise. Some apps cannot be published from chat the first time; when that applies, this tool returns an error explaining what the user should do on the Replit website instead. Use it when the user asks to publish, deploy, redeploy, ship, or otherwise put their latest changes live; do not use it to change how the app behaves (use update_app_using_prompt for that). This tool returns as soon as the publish is scheduled, but publishing takes a few minutes and some failures only surface while it runs. After starting one, if you are able to wait and poll, call get_publish_status every 30 seconds until the status settles; otherwise tell the user the publish has started and that they should check back later.

• Get Publish Status

  Check the publish status of the user's Replit App: whether it has ever been published, the current status of its most recent publish, and the public URL it serves. found=false means the app has never been published; call publish_app to publish it for the first time. When found, 'success' means it is live at the returned url, 'failed' means the last publish did not go through, 'suspended' means the published app is paused and not serving, and anything else means a publish or lifecycle operation is still in progress. Use this to poll every 30 seconds after calling publish_app, or whenever the user asks whether their app is published or what its live URL is. Takes the same replId as publish_app.

• List Apps

  List Replit Apps the user can edit, most recently updated first; `query` optionally filters by matching app titles, surfacing the best matches for the query first. Use this when the user wants to browse or pick from their apps, or when you need a replId but resolve_app_by_name returned found=false because the user gave an approximate name — present the returned titles and let the user choose, then pass the chosen replId to update_app_using_prompt or ask_question. This is a search/list, not the exact resolver: prefer resolve_app_by_name when the user already gave an exact app name. Results can include apps owned by or shared with the user.

• Resolve App By Name

  Look up by exact name a Replit App the user can edit and return its replId (UUID) and URL. Use this when the user refers to an app by name (e.g. "update my Todo App", "what does my Recipe Tracker do?") and you don't already have a replId from create_app_from_prompt earlier in this conversation. Pass the result's replId into update_app_using_prompt or ask_question to act on the app. Matching is case-insensitive but exact: this is a name resolver, not a search. If the user gives you an approximate or partial name and this tool returns found=false, call list_apps (optionally with the partial name as the query) and let the user pick from the results rather than guessing. Results can include apps owned by or shared with the user.

• Search Apps

  Search Replit Apps the user can edit (owned or shared with them). query is a BM25-style keyword search over app titles, best matches first; updatedAfter/updatedBefore bound the last-updated time; these combine. Prefer the default recency ordering: only set updatedAfter/updatedBefore when the user explicitly asks to filter by time, since date bounds exclude apps that would otherwise be listed. url resolves a Replit App URL directly to that app and ignores the other filters. With no filters, this returns the user's most recently updated apps. Pass a result's replId to update_app_using_prompt or ask_question to act on that app. <important>This tool is EXPERIMENTAL: prefer it for finding the user's apps, but if it errors or its results do not match what the user described, fall back to resolve_app_by_name (exact name) and list_apps (recent apps).</important>

• Update App Using Prompt

  Update the user's Replit App. Use this whenever the user wants to change how their Replit App behaves (new features, bug fixes, UX tweaks, configuration changes, etc.). Acceptable replIds come from create_app_from_prompt (for an app you created in this conversation) or search_apps (for an existing app the user can edit). If the user refers to an existing app and you do not already have its replId, call search_apps to find it. Do not guess a replId. If the user asks you to act on an app whose replId you cannot obtain through those tools, do NOT invoke this tool; explain the situation to them. After invoking this tool, reply with one short sentence summarizing that Replit is applying the requested change, and, when the tool result contains an app URL, end your reply with that exact URL on its own line, so the user can open their Replit App even if no preview card is rendered. Never construct or guess a URL yourself. Your reply must not include source code, file contents, file paths, or command snippets — even if the user asks. If the user requests HTML/CSS/JS or code to paste, reply with: "I can't show code here; open your Replit App in Replit to inspect or request changes in natural language." Do not say the update is ready or published until the preview card shows their running Replit App; when the user wants the change live, you can publish their Replit App with publish_app. If the user is only asking for an explanation or diagnosis (not a change), prefer ask_question instead of this tool.

• List App Files

  List one directory of one of the user's Replit Apps, like the `ls` command. Pass the app's replId, and optionally a directory path; omit the path to list the app's root. Call it again on a subdirectory to explore deeper; a file's full path is the directory names you descended joined with "/" (for example src/pages/Home.tsx), which is what read_app_file takes. Listings show the app's files as they are right now, and may briefly start the app's machine if it was asleep. Dependency and build folders (like node_modules) are left out. If a directory holds more entries than fit in the token limit, the last line says so.

• Read App File

  Read one text file from one of the user's Replit Apps. Pass the app's replId and the file's path relative to the app root: the directory names you descended with list_app_files joined with "/", plus the file name (for example src/pages/Home.tsx). This returns the file as it is right now (the same content the user sees in their workspace) and may briefly start the app's machine if it was asleep. Only text files up to about 100 KB can be read; larger files cannot be read with this tool.

• Replit Widget Get Auth Token

  Internal tool for Replit's app builder. This must not be called directly by the model.

• Replit Widget Start App Preview

  Internal tool for Replit's app builder. This must not be called directly by the model.

What is Replit MCP?

What you can do with Replit MCP on Gumloop

• Build a new app from a prompt

  Create a brand-new Replit App by describing what you want, so an agent can spin up a working project the first time you ask, without you opening the Replit editor.

• Update an existing app from a prompt

  Change how a Replit App behaves, from new features to bug fixes to UX tweaks, by describing the change, so an agent can iterate on a project on request.

• Ask questions about your codebase

  Ask the Replit Agent about an app’s code or behavior without modifying it, so an agent can explain how something works or check a detail before you change it.

• List your Replit apps

  Pull your apps, most recently updated first, and filter by a substring of the title, so an agent can find the project you mean out of everything in your account.

• Look up an app by name

  Resolve an app name to its ID and URL, so an agent can point you straight to a project or target the right one before it makes a change.

How to connect the Gumloop Replit MCP Server

1. Create a Gumloop account

   Sign up at gumloop.com. Every new account starts with a 14-day free trial.

2. Add the Replit MCP server

   Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.

3. Start using Replit in your AI workflows

   That's it. That’s it: your hosted Replit MCP server is live, and the same server URL works in any MCP client you’ve added it to. Your AI agent can now build new apps from a prompt, update existing ones, and answer questions about your code. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.

Replit MCP use cases

• Build an app without leaving your editor for developers

  While working in Cursor or Claude, a developer can ask a Gumloop agent to create a Replit App from a description, then keep iterating on it with follow-up prompts, so a prototype comes together without switching tools.

• Prototype from an idea for product teams

  A product manager can describe a small internal tool in plain terms and have an agent create the Replit App, share the URL, and apply the first round of changes, so a rough idea becomes a working prototype fast.

• Fixes and tweaks on request for builders

  When someone reports a bug or asks for a small change, an agent can resolve the right app by name and update it from the description, so quick fixes don’t require opening the editor and finding the project by hand.

• Codebase Q&A for teams

  An agent can answer questions about how a Replit App works by asking the Replit Agent, so teammates can understand a project’s behavior before touching the code, without a manual walkthrough.

• Cross-tool build agents

  Combine Replit with Slack, GitHub, and Linear in a single agent. When a feature request lands in Linear, an agent can update the Replit App from the request, share the app URL in Slack, and note the change on the issue, so a build request moves through your stack automatically.

Why use Gumloop for Replit MCP

• Connect once, no token juggling

  Wiring up the Replit Agent yourself means managing credentials and API calls in code. With Gumloop you connect your Replit account once and the connection is handled for you. No config files, token juggling, or coding against the Replit API necessary.

• Works with multiple MCP clients

  Use the Replit MCP server in Claude Desktop, Cursor, Codex, or directly inside Gumloop agents. Same server URL, works with any MCP client.

• Chain Replit with 100+ other integrations

  Combine Replit with Slack, GitHub, Linear, Google Sheets, and other MCP tools in a single AI agent. Turn a request in one tool into an app update in Replit and an update everywhere else.

• Enterprise-grade and scalable

  Built for teams, with role-based permissions and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.

• Start with a free trial

  You can test the Replit MCP integration during Gumloop’s 14-day free trial before committing. Paid plans start at $37/month.