# Cursor edits the file. Maguyva sees the repo.

Canonical source: https://maguyva.ai/for-cursor

License: text under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); code samples under [MIT-0](https://opensource.org/license/mit-0); the Maguyva name, logos, brand assets and other code are not covered. Details: [maguyva.ai/license](https://maguyva.ai/license).

Cursor is the editor. In a monorepo, the agent still needs a map of which file matters. Maguyva indexes your codebase and serves it back over MCP (semantic, AST, graph, and text), so “where does auth happen” returns the actual auth flow, not seven test stubs.

> Cursor edits what you point at. Maguyva tells the agent which file to point at.

## What each layer does

Four pieces. Each one has a job.

### Cursor

Where you actually code.

### @ mentions + pins

Manual context wins, until the repo is big.

### Maguyva

Automatic codebase facts over MCP.

### Workspaces, not seats

Agents don’t pay seats. [See pricing](https://maguyva.ai/pricing)

## Cursor is the editor. Use it.

The IDE is not the problem. Cursor’s tab completion, edit-with-AI, multi-file edits, and `.cursor/rules` are excellent, and you already use them for:

- Inline suggestions and edit-with-AI in the open file.
- Multi-file edits when the change is local.
- `.cursor/rules` for repo conventions and style guardrails.
- `@`-mentions to pull a specific file into context.

Keep doing that. None of it goes away.

But in a real monorepo (TypeScript with workspace deps, Python services, mixed packages) agent context breaks the moment the relevant file isn’t already on your radar.

## Manual fixes you’ve already tried, and where they break

Four manual fixes paired with their failure mode. Left = what you do today. Right = where it breaks.

### // pin the files

You `@`-mention the three files you think matter. Cursor edits cleanly inside them.

### // pinning is a guess

Pinning works when you already know which files are involved. The whole point of context tools is to surface the files you didn’t know to pin.

### // paste the snippets

You paste 200 lines from another package into the chat to give the agent enough context.

### // pasted code goes stale

The snippet you pasted at 9 a.m. doesn’t reflect the rebase your teammate landed at 11 a.m. The agent is editing against a phantom version of the package.

### // write a context doc

You write a `.cursor/rules` file or an architecture markdown. It’s right today.

### // docs drift faster than code

Anything you write by hand drifts. The code is the source of truth. A doc explaining the queue layer is correct for a week, then wrong forever.

### // keep the rules files

You add `.cursor/rules` for naming, lint, build commands. Great for behavior.

### // rules ≠ index

`.cursor/rules` is the right place for “always run pnpm tsc -b before commits.” It is not a queryable index of every symbol, file, and call-site in your monorepo.

## Maguyva is the layer underneath

Not a Cursor replacement. The repo-context layer that hangs off Cursor’s MCP support.

- **Semantic + AST + graph + text**: search by meaning, structure, dependency, or literal. Every hit returns a file path and line number.
- **Cross-package by default**: call-sites and importers across every package in the monorepo, not just the one currently open.
- **Branch-aware**: Maguyva sees the version of the code Cursor is editing.
- **Complementary, not competitive**: `.cursor/rules` keeps doing its job. `@`-mentions keep doing their job. Maguyva fills the gap they don’t fill.

> Cursor edits the file you point at.
> Maguyva tells the agent *which file to point at.*

## Three monorepo workflows

Cross-package, cross-language. Grounded against the actual call graph, not Cursor’s grep.

### 01. Find the auth flow across packages, without pinning anything

```text
cursor> where does authentication happen in this monorepo?

graph::query("authentication flow")
  packages/web/src/auth/session.ts:42       middleware
  packages/api/src/auth/jwt.ts:88           token verify
  packages/shared/src/auth/types.ts:12      AuthContext
  packages/admin/src/auth/admin-only.ts:31  rbac gate

→ 4 entry points across 4 packages, ranked by call-site density.
[exit 0]
```

You didn’t pin a file. You didn’t paste a snippet. The agent has the four files that matter, in the right ranking, and can make a grounded edit.

### 02. Find the real implementation, not the test stub

```text
cursor> how does normalizePhoneNumber handle E.164?

semantic::query("normalize phone E.164")
  packages/shared/util/phone.ts:88     normalizePhoneNumber()  ← real impl
  packages/api/test/phone.spec.ts:14   jest.mock(...)          ← stub
[exit 0]
```

Names lie. Mocks shadow real code. Maguyva ranks the real implementation above the test mock, across every package.

### 03. Check blast radius before you refactor

```text
cursor> what calls QueueDispatcher.publish across the monorepo?

graph::callers(QueueDispatcher.publish)
  3 in packages/billing/*
  1 in packages/audit/*
  1 in packages/notifications/*
  1 in services/python-worker/*  ← cross-language via gRPC stub
[exit 0]
```

Cross-package, and cross-language when you have a polyglot repo, call-sites surface inline. The diff is grounded against real importers, not Cursor’s grep.

## Setup with Cursor

Three steps. Free tier: 3 repos, 50K indexed lines, no card.

### 01. Index a repo at maguyva.ai

Pick the monorepo where you’ve felt the most context pain.

### 02. Add Maguyva as an MCP server in Cursor’s settings

`~/.cursor/mcp.json`

```json
{
  "mcpServers": {
    "maguyva": {
      "url": "https://maguyva.tools/mcp",
      "headers": {
        "Authorization": "Bearer ${env:MAGUYVA_API_KEY}"
      }
    }
  }
}
```

### 03. Ask one question whose answer you already know

Don’t start with your whole company. Start with one repo and one verifiable question, like “what calls `formatInvoice` across packages?”

## Index one repo you already know.

Test one question whose answer you can verify.