Let AI agents use your app
Your AI reads your app's code and makes it easy for AI agents to use: an llms.txt and docs page, a remote MCP server with sign-in and limits, a small CLI, your name and icon in agent apps, and a listing in the MCP Registry. Then it tests the result with Claude, ChatGPT, Cursor and Grok. These are the steps Francisco used to build CloneKit.
Francisco@franguzmanxCreatorWhat your AI will deliver
- AGENT-READY.md: the first 3 to 5 jobs agents can do, what each one changes, and the gaps
- A /llms.txt file and a docs page written for people and agents
- API errors with one shape: code, message and fix
- A remote MCP server (Streamable HTTP) with your first tools, honest annotations and errors that say what to do next
How it runs
In your AI, with your accounts. It starts by researching your business. How kits work ›
- Understand
Researches your business first, then asks you 6 questions it can't answer alone
- Choose
1 A/B choice with examples
- Build
9 steps, risky ones ask you first
- Deliver
6 checks before delivery
Tools it uses
You pay each tool directly, not CloneKit. Your AI checks which ones you already have.
Details
What the creator's process is built on. Your AI loads them during the run.
- Source
Tools, annotations, structured content and the Streamable HTTP transport.
- Source
The 401 challenge, protected resource metadata, client registration and token audience.
- Source
How to name, describe and shape tools so agents pick the right one.
- Source
- Source
- Source
- Source
- Source
- Source
- Source
- Source
- Source
- Source
- Source
- Template
A live example of the file step 2 builds.
- Template
A live example of a docs page with connect cards and install buttons.
- The app's code, in a repo your AI can read and change
- The app's domain, and access to deploy it
- Admin access to the sign-in provider, for one-tap sign-in
Reference files your AI can read during and after the work.
- Let AI agents use your appREADME.md
- Sign-in and limits: how CloneKit does itreference/auth-and-limits.md
- CLI: how CloneKit does itreference/cli.md
- Directories: how CloneKit did itreference/directories.md
- The read-only server for directories: how CloneKit does itreference/directory-server.md
- Discovery and branding: how CloneKit does itreference/discovery.md
- MCP server: how CloneKit does itreference/mcp-server.md
- Testing with real agents: how CloneKit does itreference/testing-with-agents.md
- Ask the person before you deploy, change DNS, create OAuth apps, publish to the MCP Registry or submit to a directory.
- Keep tokens, API keys, signing keys and OAuth secrets in environment variables or the person's secret store. Never put them in code, logs, chat or a test fixture.
- Build on the app's own auth, API and functions. Don't add a framework or a service when the current one does the job.
First version: nine steps, from the audit to tests with real agents, with code from CloneKit.
Everyone running this kit gets updates. See changelog ›
- Type
- Delivery
- License
- Own use
- Uses
- 0
- Runs completed
- 0