Prompts & Examples
Once everything is set up, you can start using your AI assistant as usual. It will now have access to the tools provided by Openfort's MCP Server and will call them when needed.
- It can create projects without the need for you to set them up in the dashboard.
- It can automatically retrieve keys from your project and store them safely.
- It can set up policies, contracts, and create users and accounts.
- It can fetch real-time data from your project.
- It can scaffold your project faster than ever.
- It can get context from the latest version of Openfort's documentation.
If you need further inspiration, here are some considerations and use cases.
Rules
LLMs tend to forget about the availability of tools and can make some pathological mistakes. Therefore, it's a good idea to include rules to remind them about this. Here's how to set them up.
Add these rules to the configuration at Rules & Memories > User Rules > Add Rule.
For project-specific rules, you can add them at .cursor/rules/openfort.md
Add these rules to the root folder of your project at .windsurf/rules/openfort.md.
For global rules, you can add them at:
Windsurf Settings > Cascade > Customizations > Cascade Rules > + Global
Copy these rules and add them to any AI assistant you use.
Prompts
Here are some example prompts to guide your AI assistant in creating projects with Openfort’s features. Copy and paste them directly into the chat to try them out.
Common Issues
General Errors
After the agent finishes creating a project, it may still throw errors, even with extended context. This is especially common for complex prompts or large applications.
Don’t expect the AI to flawlessly generate entire applications in a single prompt without any issues.
To resolve these errors, fix them manually or ask the AI for help. Iteration is normal, review the output, make corrections, and continue prompting as needed.
Loop When Creating a Policy
Occasionally, the AI agent may get stuck in a loop while creating a policy. The policy is successfully created, but the agent repeatedly attempts to update it with the same values.
The cause is unknown, and the effect is harmless.
To fix this, simply cancel the generation and prompt the agent to continue with the next step.
npm Error: Missing script: "dev"
If the AI agent fails to start the project using npm run dev, it’s often because it created the project in a subfolder and didn’t change into that directory before running the command.
Manually navigate to the subfolder and run the project again.
No Permission to Edit the .env File
When the AI agent fails to edit or create a .env file with your project keys, it’s usually due to insufficient file permissions.
In Cursor, add a
.cursorignorefile with!.envto explicitly allow the AI to edit the.envfile.For other editors or environments, follow an equivalent approach to ensure the file is not ignored.