Your agent can build the integration.See the two prompts

Agent setup

Your agent builds the login.
You paste one prompt.

No provider apps. No callback URLs. No signup per app. Give your coding agent the AnyOAuth skill and MCP server, then tell it which app to connect.

Quick startCopy these two prompts into your agent.
Step 1

Connect the skill and MCP server

Add the AnyOAuth skill with:
npx skills add AnyOAuth/anyoauth --skill anyoauth

Connect the AnyOAuth MCP server with:
npx anyoauth-mcp

Paste this into Claude Code, Codex, Cursor, or any agent that supports skills and MCP.

Step 2

Ask for the integration

Create AnyOAuth login for example.com using AnyOAuth. Enable Google, GitHub and Magic Email Link.

Replace example.com with your app or domain. Your agent inspects the app and does the rest.

Works with your tools

The agents and IDEs you already use.

If it can run a skill and connect an MCP server, it can build the integration. No new editor, no separate dashboard workflow.

What happens next

From prompt to signed-in user.

Your agent handles the setup that used to live in three dashboards.

01

It reads your app.

Your agent finds the backend, frontend, framework, local port, and existing auth routes. It decides the exact callback and session strategy.

02

It creates the project.

It installs the skill and MCP server, creates or reuses one AnyOAuth project, registers the callback, and stores the client secret on the backend.

03

It writes the login.

It adds the provider buttons, backend exchange, browser-bound PKCE, application session, and checks. You review the diff and sign in once.

Less setup

One account. Unlimited apps. Zero callback wrangling.

AnyOAuth is built for agents: one skill, one MCP server, and one API for every application you own. Your projects stay in one account while the agent does the per-app work.

No provider appsNo callback copyingNo signup per appNo JSON editing
See plans
Before
  • Create a provider app
  • Copy client ID and secret
  • Add a callback URL
  • Wire PKCE and sessions
  • Debug provider differences
With your agent
  • Paste two prompts
  • Review the integration
  • Sign in once
  • Ship

A few good questions.

What agent-driven setup changes, and what stays in your control.

Do I need to sign up for each app?

No. One AnyOAuth account covers unlimited applications. Your agent creates or reuses a project for each app, so there is no account-per-app and no repeated provider setup.

Do I need to register callback URLs?

No. Your agent reads the app, determines the exact callback path, registers it with AnyOAuth, and writes the matching server route. You do not copy callback URLs between dashboards.

Do I need my own Google or GitHub OAuth app?

No. AnyOAuth manages the provider applications. Your agent creates the AnyOAuth project and uses the managed credentials; you never create a provider app ID or secret per project.

Which agents and IDEs work?

Any agent or IDE that can install a skill and connect an MCP server. The prompt works with Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode, VS Code, JetBrains, Zed, Neovim, Replit, v0, and other MCP clients.

What does the agent actually do?

It installs the AnyOAuth skill and MCP server, inspects the application, creates or reuses the project, registers callbacks, adds the backend and browser login code, stores the client secret on the backend, and runs the checks.

What if the agent does not support MCP yet?

Use the same prompt but ask it to use the AnyOAuth CLI directly. The skill includes the CLI fallback and the generated command reference.

Is an API key required?

Not necessarily. Your agent can use Google or GitHub browser approval, a Magic Email Link sent to an inbox it can read (MailKite, SendHog, or AgentMailbox), or an owner-scoped API key for long-running automation.

Your next integration
is one prompt away.

Copy the prompt. Tell your agent which app. Review the result.