Base44
Build and edit Base44 apps from an AI assistant, and query data your app's users submit.
Build, update and publish Replit apps from your AI assistant.
Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.
Paste it into any MCP client. Setup docs
The Replit MCP server lets Claude, ChatGPT or any MCP-compatible agent build and change apps on Replit. An agent can create a project from a description, ask questions about an existing app, update it in plain language and publish it to a public URL. Sign-in is OAuth, and the build tools hand work to Replit Agent, which is billed.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.
publish_app — the deploy tool — is documented but not listed, and import-claude-design-from-url is listed but not in Replit's tool table.prompts/list, so we cannot say whether the server serves any.create_app_from_prompt and update_app_using_prompt hand a sentence to Replit Agent. Their effective surface is whatever Replit Agent can do, and the documentation does not bound that. There is no diff to review before the change lands./anthropic/mcp; Replit's docs publish /server/mcp. Both are live; the documentation does not explain the difference.Replit's own documentation lists eight; Anthropic's directory snapshot lists five. Three names differ. The docs add `search_apps`, `list_apps`, `publish_app` and `get_publish_status`, while the directory carries `import-claude-design-from-url`, which the docs table omits. The gap matters because `publish_app` is a deploy button, and it is absent from the listing a reviewer reads before approving the connector.
It can, because the build tools run Replit Agent, and Agent work is billed. Replit prices paid Agent work by effort, bundling a completed request into one billable checkpoint. Core and Pro subscribers get a Free Mode allowance that resets every five hours with a weekly limit. Replit states it asks for confirmation before a paid action starts, but does not document how that prompt reaches an MCP client.
No, not by itself. Replit documents publishing as a separate five-stage pipeline that ends by switching your URL to the new version, and `publish_app` as the tool that starts it. An Agent update changes the project and its preview. On the ChatGPT surface, however, Replit documents that Agent generates and publishes apps automatically, so that boundary is client-dependent.
Yes, through checkpoints. Replit documents Agent as creating checkpoints automatically at development milestones, capturing project files, conversation context, environment configuration and database contents. Rollback restores a checkpoint with one click and you can roll forward again. Two limits: a rollback leaves your database untouched unless you opt in, and the production database is restored separately.
Replit runs the MCP server on a dedicated host, separate from the main site and from the OAuth issuer at `replit.com/oidc`. The path segment is per-integration rather than per-client. We confirmed on 19 August 2026 that only two paths are real MCP endpoints — the directory's `/anthropic/mcp` and the documented generic `/server/mcp`. Every other path returns the site's HTML.
It queries one of your apps, not Replit's documentation. Replit documents `ask_question` as asking Agent about an app without changing it, taking the app id and your question as required inputs. It is the read-only member of the Agent-backed group: useful for orienting yourself in a project you inherited before any tool touches its code.
One workspace, chosen during the OAuth sign-in. Replit's setup steps for both Codex and Claude Code say to pick the workspace to connect and then select Allow, and the Claude design handoff repeats the same choice. The connection reaches apps you can edit, which Replit states includes apps other people have shared with you, not only apps you own.
.md suffix; this is the URL Anthropic's directory publishes, and the source of the eight-tool table and the troubleshooting notes) · retrieved 2026-08-19docs.replit.com/robots.txt allows the docs paths and carries Content-Signal: ai-train=yes, search=yes, ai-input=yes — synthesis is expressly permitted on all three axes (fetched 2026-08-19). replit-mcp.com serves no robots.txt; the path returns the site's HTML shell · retrieved 2026-08-19issuer is https://replit.com/oidc) · retrieved 2026-08-19POST to the endpoint returns HTTP 401 with www-authenticate: Bearer resource_metadata="https://replit-mcp.com/.well-known/oauth-protected-resource/anthropic/mcp". Path probes of /mcp, /openai/mcp, /cursor/mcp, /claude/mcp and /vscode/mcp returned HTTP 200 with text/html, not MCP responses · retrieved 2026-08-19Connect Replit once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.