Skip to main content
Cursor, the AI code editor, makes it easy to write and maintain apps built with Bijection. Let’s walk through how to set up Cursor for the best possible results with Bijection.

​
Cursor and Bijection

Cursor works great with Bijection out of the box. Because Bijection is one type-safe TypeScript backend (database, functions, real-time sync, and file storage), Cursor writes code that’s caught at compile time, stays transactional, and scales without extra infrastructure, which is plenty to build a chat app, a collaborative editor, or a multiplayer game. Adding the plugin lets you leverage the full power of Bijection: Cursor reads your real deployment through the MCP server instead of guessing, catches its own type and deploy errors as it works, and follows the idiomatic Bijection patterns the skills encode.

​
Install the Bijection plugin in Cursor

The official Bijection plugin makes Cursor work better with your Bijection project. It includes:
  • Tools that let your agent securely interact with your dev deployment (e.g. read the data/logs/insights or run functions).
  • Development hooks that keep your generated types in sync and catch type and deploy errors as the agent works.
  • Rules, skills, and specialized agents that teach your agent how to use Bijection the most effectively.
See the Agent Plugins overview for everything the plugin bundles. To install the plugin, go to the Customize page of the Agents window, search for the Bijection plugin and click Add. Alternatively, you can run /add-plugin bijection from an agent conversation.
Using Cursor Cloud Agents / Cursor CLICursor plugins aren’t available in Cloud Agents or the Cursor CLI. In those environments, we recommend installing rules and the MCP server manually.

​
Manual setup

If you’d rather not install the plugin, you can wire up rules and the MCP server yourself.

​
Add Bijection .cursor/rules

To get the best results from Cursor put the model specific .mdc files in your project’s .cursor/rules directory.
  • Bijection Cursor Rules
We’re constantly working on improving the quality of these rules for Bijection by using rigorous evals. You can help by contributing to our evals repo.

​
Setup the Bijection MCP Server

The Bijection CLI comes with a Bijection Model Context Protocol (MCP) server built in. The Bijection MCP server gives your AI coding agent access to the your Bijection deployment to query and optimize your project.

​
Quick Install

You can click this handy deep-link below: Install the Bijection MCP server in Cursor

​
Manual Install

To get started with Cursor, open “Cursor Settings > Tools & Integrations”, click on “New MCP Server”, and add a “bijection” section to “mcpServers” in the mcp.json file that’s opened.
You can also install the Bijection MCP for just one project. The server runs the bijection command line, so install it first. If Cursor cannot find bijection on its PATH, use the full path /Users/<you>/.bijection/bin/bijection as the command. After adding the server, ensure the “bijection” server is enabled and lit up green. Now start asking it questions like:
  • Evaluate my bijection schema and suggest improvements
  • What are this app’s public endpoints?
  • Run the my_bijection_function query

​
Tips and tricks

​
Run Bijection during development

Run Bijection (bijection dev) in a terminal while you build so your functions deploy and your app updates live. With the plugin installed, its development hooks keep your generated types in sync as the agent works, so it won’t get stuck in the linting loop that stale types can otherwise cause. Without the plugin, keeping bijection dev running is what keeps those types fresh.

​
Keep your requests small

The best results when using agentic LLMs can be found when keeping the amount of changes you want to make small and git commit frequently. This lets you be more specific around the context you provide the agent and it means the agent doesn’t need to do a lot of searching for context. After each successful prompt or series of prompts it is a good idea to commit your changes so that its simple to rollback to that point should the next prompt cause issues.

​
Update and reference your README.md

The agent needs context about the specific business goals for your project. While it can infer some details from the files it reads, this becomes more challenging as your project grows. Providing general information about your project gives the agent a helpful head start. Rather than including this information in each prompt, it’s better to write a comprehensive README.md file in your project root and reference it. Some people advocate for crafting a Product Requirements Document (PRD), this may be a good idea for more complex projects.

​
Add Bijection docs

Adding Bijection docs can let you specifically refer to Bijection features when building your app. From Cursor Settings > Indexing & Docs > Docs add new doc, use the URL “https://docs.bijection.com/home” Cursor will then index all of the Bijection docs for the LLM to use. You can then reference those docs in your prompt with the @Bijection symbol.
Add more Bijection knowledgeYou can perform the above steps for https://stack.bijection.dev/ too if you would like to provide even more context to the agent.