What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Cursor does not necessarily send your entire repository to the model for every request. It retrieves code and other context it estimates are relevant, while references such as @file, @folder, and @code let you point it to specific parts of a project. For Lambda development, you can use Cursor as an editor for AWS Lambda applications; a separate, advanced setup runs Cursor Cloud Agent tool calls on AWS Lambda MicroVMs.
How does Cursor understand your codebase?
Cursor describes context as information supplied to the model. It can automatically retrieve portions of a repository it estimates are relevant to a request, including the current file and semantically similar code patterns. The amount and selection depend on the task and the model’s available context; this is not a guarantee that the whole repository is included in every request. Cursor’s context guide explains how context affects responses.
As an Amazon Associate I earn from qualifying purchases.
It helps to distinguish two kinds of context:
- Intent context: What you want done, including the goal, constraints, and expected result.
- State context: The code, logs, configuration, and other information describing the project’s current condition.
A request with too little relevant context can lead to inaccurate suggestions or inefficient agent work. When a change crosses important code paths, name the files or symbols that define those paths instead of relying only on automatic retrieval.
Does Cursor read your whole repository?
Not as a universal, per-request behavior. Cursor’s documentation describes automatic retrieval of relevant portions, not a promise that every file is always sent to the model. Indexing helps Cursor find relevant material, but indexing and model context are different things: an indexed repository is not necessarily all present in a particular prompt.
Cursor’s security documentation says that opening a project folder triggers codebase indexing. It describes honoring .gitignore and .cursorignore, processing files into chunks and embeddings, and storing metadata used for vector search, including obfuscated relative paths and line ranges. Cursor’s privacy page says code chunks are uploaded for embedding; plaintext code ceases to exist after the embedding request, while embeddings and metadata are stored. That means you should not assume indexing keeps all code entirely on your machine. Review the current Cursor security documentation, privacy policy, and project settings before indexing sensitive code, since implementation details and policies can change.
How to steer Cursor toward the right code
Use explicit references when you know where the relevant logic lives. Cursor documents these context controls:
@codeto reference a known symbol or function.@fileto include a particular file.@folderto direct attention to a directory and its contents.
For example, for a Lambda change involving request parsing, business logic, and infrastructure configuration, reference the handler, the relevant service function, and the SAM template. Then state what behavior should change and what must remain unchanged. Cursor can still retrieve other relevant context, but explicit references reduce ambiguity about the important code paths.
For repeated project conventions—such as runtime choices, error-handling rules, or how tests should be run—use Cursor rules so the guidance is reusable rather than repeated in every prompt. For external systems and information, Model Context Protocol (MCP) can connect Cursor to tools and data sources, such as internal documentation or project-management systems. See Cursor’s documentation for rules and MCP.
Can you use Cursor with AWS Lambda?
Yes. There are two distinct workflows: developing a Lambda application in Cursor, and deploying self-hosted Cursor Cloud Agent workers on Lambda MicroVMs. The first is an editing and development workflow; the second is an AWS infrastructure pattern for executing agent tool calls. You do not need the MicroVM setup simply to edit Lambda code in Cursor.
Develop a Lambda application in Cursor
In an AWS announcement dated August 6, 2026, AWS described opening a Lambda function in Cursor directly from the Lambda console. The workflow preserves the function’s existing code and configuration, and AWS says Cursor can help convert applications to an AWS Serverless Application Model (AWS SAM) template. AWS stated that the integration is available in commercial AWS Regions where Lambda is available, at no additional charge. Check the current AWS announcement and your region’s availability before relying on the console option.
AWS also provides setup instructions for adding its serverless skill and configuring the AWS Serverless MCP Server in Cursor. These can give an agent AWS-specific guidance and tool access; they do not replace deployment permissions, review of proposed changes, or application testing. Follow the current AWS guide to setting up Cursor for serverless development.
Recommended Free Tools
Run Cursor Cloud Agent workers on Lambda MicroVMs
AWS documents a separate self-hosted-machine configuration for Cursor Cloud Agents. In this design, Cursor hosts the agent loop and model, while a Lambda MicroVM worker claims work and executes tool calls inside the customer’s AWS environment. A scheduled controller Lambda responds to pending requests. AWS says each MicroVM session runs for up to eight hours, does not share state with other sessions, and is terminated when the session ends. AWS’s Lambda MicroVM guide describes the architecture.
This is an advanced enterprise deployment, not the normal way a developer opens and edits a Lambda project. AWS lists these prerequisites:
- An AWS account with Lambda MicroVMs enabled and permissions for S3, IAM, CloudFormation, and Systems Manager Parameter Store.
- Cursor Enterprise with self-hosted machines enabled, plus a service-account API key.
- A current AWS CLI and Docker.
The guide stores the service-account API key in Parameter Store as a SecureString rather than baking it into the worker image. Follow AWS’s deployment instructions and credential-handling guidance in the MicroVM guide.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Which Lambda workflow fits your situation?
| Workflow | Where work happens | What it is for | Key requirements |
|---|---|---|---|
| Develop a Lambda application in Cursor | Cursor is used as the developer’s editing environment; the Lambda function and its AWS configuration remain part of the application workflow. | Editing Lambda code, using AWS-specific guidance, or converting an application to AWS SAM. | Cursor and the AWS integration or setup appropriate to the task; check current regional availability for opening a function from the Lambda console. |
| Self-host Cursor Cloud Agent workers on Lambda MicroVMs | Cursor hosts the agent loop and model; a Lambda MicroVM in your AWS environment executes tool calls. | Running Cloud Agent workers as self-hosted machines with isolated AWS-side execution. | Cursor Enterprise with self-hosted machines enabled, AWS account and permissions, a service-account API key, AWS CLI, and Docker. |
Choose the first workflow when you want to work on a Lambda project in an editor. Consider the second only when you specifically need the documented Cloud Agent worker architecture and can meet its enterprise and AWS infrastructure prerequisites.
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Repair Windows errors before they cause bigger problems3Fix the driver behind crashes, sound loss and screen glitchesQuick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
