@mastra/mcp-docs-server 1.0.0-beta.10 → 1.0.0-beta.13

package/.docs/raw/agents/processors.mdx

@@ -12,6 +12,8 @@ Processors are configured as:
 - **`inputProcessors`**: Run before messages reach the language model.
 - **`outputProcessors`**: Run after the language model generates a response, but before it's returned to users.
 
+You can use individual `Processor` objects or compose them into workflows using Mastra's workflow primitives. Workflows give you advanced control over processor execution order, parallel processing, and conditional logic.
+
 Some processors implement both input and output logic and can be used in either array depending on where the transformation should occur.
 
 ## When to use processors
@@ -168,6 +170,81 @@ This is useful for:
 - Filtering or modifying semantic recall content to prevent "prompt too long" errors
 - Dynamically adjusting system instructions based on the conversation
 
+### Per-step processing with processInputStep
+
+While `processInput` runs once at the start of agent execution, `processInputStep` runs at **each step** of the agentic loop (including tool call continuations). This enables per-step configuration changes like dynamic model switching or tool choice modifications.
+
+```typescript title="src/mastra/processors/step-processor.ts" showLineNumbers copy
+import type { Processor, ProcessInputStepArgs, ProcessInputStepResult } from "@mastra/core";
+
+export class DynamicModelProcessor implements Processor {
+  id = "dynamic-model";
+
+  async processInputStep({
+    stepNumber,
+    model,
+    toolChoice,
+    messageList,
+  }: ProcessInputStepArgs): Promise<ProcessInputStepResult> {
+    // Use a fast model for initial response
+    if (stepNumber === 0) {
+      return { model: "openai/gpt-4o-mini" };
+    }
+
+    // Disable tools after 5 steps to force completion
+    if (stepNumber > 5) {
+      return { toolChoice: "none" };
+    }
+
+    // No changes for other steps
+    return {};
+  }
+}
+```
+
+The `processInputStep` method receives:
+- `stepNumber`: Current step in the agentic loop (0-indexed)
+- `steps`: Results from previous steps
+- `messages`: Current messages snapshot (read-only)
+- `systemMessages`: Current system messages (read-only)
+- `messageList`: The full MessageList instance for mutations
+- `model`: Current model being used
+- `tools`: Current tools available for this step
+- `toolChoice`: Current tool choice setting
+- `activeTools`: Currently active tools
+- `providerOptions`: Provider-specific options
+- `modelSettings`: Model settings like temperature
+- `structuredOutput`: Structured output configuration
+
+The method can return any combination of:
+- `model`: Change the model for this step
+- `tools`: Replace or add tools (use spread to merge: `{ tools: { ...tools, newTool } }`)
+- `toolChoice`: Change tool selection behavior
+- `activeTools`: Filter which tools are available
+- `messages`: Replace messages (applied to messageList)
+- `systemMessages`: Replace all system messages
+- `providerOptions`: Modify provider options
+- `modelSettings`: Modify model settings
+- `structuredOutput`: Modify structured output configuration
+
+#### Using prepareStep callback
+
+For simpler per-step logic, you can use the `prepareStep` callback on `generate()` or `stream()` instead of creating a full processor:
+
+```typescript
+await agent.generate({
+  prompt: "Complex task",
+  prepareStep: async ({ stepNumber, model }) => {
+    if (stepNumber === 0) {
+      return { model: "openai/gpt-4o-mini" };
+    }
+    if (stepNumber > 5) {
+      return { toolChoice: "none" };
+    }
+  },
+});
+```
+
 ### Custom output processor
 
 ```typescript title="src/mastra/processors/custom-output.ts" showLineNumbers copy
@@ -273,7 +350,81 @@ const agent = new Agent({
 
 > **Note:** The example above filters tool calls and limits tokens for the LLM, but these filtered messages will still be saved to memory. To also filter messages before they're saved to memory, manually add memory processors before utility processors. See [Memory Processors](/docs/v1/memory/memory-processors#manual-control-and-deduplication) for details.
 
+## Using workflows as processors
+
+You can use Mastra workflows as processors to create complex processing pipelines with parallel execution, conditional branching, and error handling:
+
+```typescript title="src/mastra/processors/moderation-workflow.ts" showLineNumbers copy
+import { createWorkflow, createStep } from "@mastra/core/workflows";
+import { ProcessorStepSchema } from "@mastra/core/processors";
+import { Agent } from "@mastra/core/agent";
+
+// Create a workflow that runs multiple checks in parallel
+const moderationWorkflow = createWorkflow({
+  id: "moderation-pipeline",
+  inputSchema: ProcessorStepSchema,
+  outputSchema: ProcessorStepSchema,
+})
+  .then(createStep(new LengthValidator({ maxLength: 10000 })))
+  .parallel([
+    createStep(new PIIDetector({ strategy: "redact" })),
+    createStep(new ToxicityChecker({ threshold: 0.8 })),
+  ])
+  .commit();
+
+// Use the workflow as an input processor
+const agent = new Agent({
+  id: "moderated-agent",
+  name: "Moderated Agent",
+  model: "openai/gpt-4o",
+  inputProcessors: [moderationWorkflow],
+});
+```
+
+When an agent is registered with Mastra, processor workflows are automatically registered as workflows, allowing you to view and debug them in the playground.
+
+## Retry mechanism
+
+Processors can request that the LLM retry its response with feedback. This is useful for implementing quality checks, output validation, or iterative refinement:
+
+```typescript title="src/mastra/processors/quality-checker.ts" showLineNumbers copy
+import type { Processor } from "@mastra/core";
+
+export class QualityChecker implements Processor {
+  id = "quality-checker";
+
+  async processOutputStep({ text, abort, retryCount }) {
+    const qualityScore = await evaluateQuality(text);
+
+    if (qualityScore < 0.7 && retryCount < 3) {
+      // Request a retry with feedback for the LLM
+      abort("Response quality score too low. Please provide a more detailed answer.", {
+        retry: true,
+        metadata: { score: qualityScore },
+      });
+    }
+
+    return [];
+  }
+}
+
+const agent = new Agent({
+  id: "quality-agent",
+  name: "Quality Agent",
+  model: "openai/gpt-4o",
+  outputProcessors: [new QualityChecker()],
+  maxProcessorRetries: 3, // Maximum retry attempts (default: 3)
+});
+```
+
+The retry mechanism:
+- Only works in `processOutputStep` and `processInputStep` methods
+- Replays the step with the abort reason added as context for the LLM
+- Tracks retry count via the `retryCount` parameter
+- Respects `maxProcessorRetries` limit on the agent
+
 ## Related documentation
 
 - [Guardrails](/docs/v1/agents/guardrails) - Security and validation processors
 - [Memory Processors](/docs/v1/memory/memory-processors) - Memory-specific processors and automatic integration
+- [Processor Interface](/reference/v1/processors/processor-interface) - Full API reference for processors

package/.docs/raw/agents/using-tools.mdx

@@ -94,4 +94,4 @@ export const weatherAgent = new Agent({
 
 - [MCP Overview](/docs/v1/mcp/overview)
 - [Agent Memory](/docs/v1/agents/agent-memory)
-- [Request Context](/docs/v1/server-db/request-context)
+- [Request Context](/docs/v1/server/request-context)

package/.docs/raw/course/01-first-agent/07-creating-your-agent.md

@@ -8,7 +8,6 @@ Now add the necessary imports at the top of your file:
 
 ```typescript
 import { Agent } from "@mastra/core/agent";
-import { openai } from "@ai-sdk/openai";
 // We'll import our tool in a later step
 ```
 
@@ -43,7 +42,7 @@ SUCCESS CRITERIA
 - Deliver accurate and helpful analysis of transaction data.
 - Achieve high user satisfaction through clear and helpful responses.
 - Maintain user trust by ensuring data privacy and security.`,
-  model: openai("gpt-4o"), // You can use "gpt-3.5-turbo" if you prefer
+  model: "openai/gpt-4.1-mini",
   tools: {}, // We'll add tools in a later step
 });
 ```

package/.docs/raw/course/01-first-agent/12-connecting-tool-to-agent.md

@@ -19,7 +19,7 @@ export const financialAgent = new Agent({
   TOOLS
   - Use the getTransactions tool to fetch financial transaction data.
   - Analyze the transaction data to answer user questions about their spending.`,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { getTransactionsTool }, // Add our tool here
 });
 ```

package/.docs/raw/course/01-first-agent/16-adding-memory-to-agent.md

@@ -6,7 +6,6 @@ Now, let's update our agent to include memory. Open your `agents/index.ts` file
 
 ```typescript
 import { Agent } from "@mastra/core/agent";
-import { openai } from "@ai-sdk/openai";
 import { Memory } from "@mastra/memory";
 import { LibSQLStore } from "@mastra/libsql";
 import { getTransactionsTool } from "../tools";
@@ -20,7 +19,7 @@ export const financialAgent = new Agent({
   instructions: `ROLE DEFINITION
   // ... existing instructions ...
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { getTransactionsTool },
   memory: new Memory({
     storage: new LibSQLStore({

package/.docs/raw/course/02-agent-tools-mcp/05-updating-your-agent.md

@@ -10,7 +10,7 @@ export const personalAssistantAgent = new Agent({
     
     Keep your responses concise and friendly.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { ...mcpTools }, // Add MCP tools to your agent
 });
 ```

package/.docs/raw/course/02-agent-tools-mcp/10-updating-agent-instructions-zapier.md

@@ -18,7 +18,7 @@ export const personalAssistantAgent = new Agent({
     
     Keep your responses concise and friendly.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { ...mcpTools },
   memory,
 });

package/.docs/raw/course/02-agent-tools-mcp/16-updating-agent-instructions-github.md

@@ -22,7 +22,7 @@ export const personalAssistantAgent = new Agent({
     
     Keep your responses concise and friendly.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { ...mcpTools },
   memory,
 });

package/.docs/raw/course/02-agent-tools-mcp/21-updating-agent-instructions-hackernews.md

@@ -27,7 +27,7 @@ export const personalAssistantAgent = new Agent({
     
     Keep your responses concise and friendly.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { ...mcpTools },
   memory,
 });

package/.docs/raw/course/02-agent-tools-mcp/27-updating-agent-instructions-filesystem.md

@@ -34,7 +34,7 @@ export const personalAssistantAgent = new Agent({
     
     Keep your responses concise and friendly.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { ...mcpTools },
   memory,
 });

package/.docs/raw/course/02-agent-tools-mcp/31-enhancing-memory-configuration.md

@@ -14,7 +14,7 @@ const memory = new Memory({
     id: "learning-memory-vector",
     connectionUrl: "file:../../memory.db",
   }),
-  embedder: openai.embedding("text-embedding-3-small"),
+  embedder: "openai/text-embedding-3-small",
   options: {
     // Keep last 20 messages in context
     lastMessages: 20,
@@ -61,7 +61,7 @@ export const personalAssistantAgent = new Agent({
     Always maintain a helpful and professional tone.
     Use the stored information to provide more personalized responses.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   tools: { ...mcpTools },
   memory,
 });

package/.docs/raw/course/03-agent-memory/04-creating-basic-memory-agent.md

@@ -8,7 +8,6 @@ Create or update your `src/mastra/agents/index.ts` file:
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
 import { LibSQLStore } from "@mastra/libsql";
-import { openai } from "@ai-sdk/openai";
 
 // Create a basic memory instance
 const memory = new Memory({
@@ -27,7 +26,7 @@ export const memoryAgent = new Agent({
     When a user shares information about themselves, acknowledge it and remember it for future reference.
     If asked about something mentioned earlier in the conversation, recall it accurately.
   `,
-  model: openai("gpt-4o"), // You can use "gpt-3.5-turbo" if you prefer
+  model: "openai/gpt-4.1-mini",
   memory: memory,
 });
 ```

package/.docs/raw/course/03-agent-memory/08-configuring-conversation-history.md

@@ -5,7 +5,6 @@ By default, the `Memory` instance includes the last 10 messages from the current
 ```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { openai } from "@ai-sdk/openai";
 import { LibSQLStore } from "@mastra/libsql";
 
 // Create a memory instance with custom conversation history settings
@@ -27,7 +26,7 @@ export const memoryAgent = new Agent({
     When a user shares information about themselves, acknowledge it and remember it for future reference.
     If asked about something mentioned earlier in the conversation, recall it accurately.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   memory: memory,
 });
 ```

package/.docs/raw/course/03-agent-memory/16-configuring-semantic-recall.md

@@ -5,7 +5,6 @@ Let's update our agent with custom semantic recall settings:
 ```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { openai } from "@ai-sdk/openai";
 import { LibSQLStore, LibSQLVector } from "@mastra/libsql";
 
 // Create a memory instance with semantic recall configuration
@@ -18,7 +17,7 @@ const memory = new Memory({
     id: "learning-memory-vector",
     connectionUrl: "file:../../vector.db", // relative path from the `.mastra/output` directory
   }), // Vector database for semantic search
-  embedder: openai.embedding("text-embedding-3-small"), // Embedder for message embeddings
+  embedder: "openai/text-embedding-3-small", // Embedder for message embeddings
   options: {
     lastMessages: 20, // Include the last 20 messages in the context
     semanticRecall: true, // Enable semantic recall with default settings
@@ -35,9 +34,9 @@ export const memoryAgent = new Agent({
     If asked about something mentioned earlier in the conversation, recall it accurately.
     You can also recall relevant information from older conversations when appropriate.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   memory: memory,
 });
 ```
 
-For semantic recall to work, you need to have a **vector store** configured. You also need to have an **embedder** configured. You may use any `@ai-sdk`-compatible embedding model for this. In this example, we're using OpenAI's `text-embedding-3-small` model.
+For semantic recall to work, you need to have a **vector store** configured. You also need to have an **embedder** configured. You may use any compatible embedding model for this. In this example, we're using OpenAI's `openai/text-embedding-3-small` model.

package/.docs/raw/course/03-agent-memory/21-configuring-working-memory.md

@@ -5,7 +5,6 @@ Let's update our agent with working memory capabilities:
 ```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { openai } from "@ai-sdk/openai";
 import { LibSQLStore, LibSQLVector } from "@mastra/libsql";
 
 // Create a memory instance with working memory configuration
@@ -18,7 +17,7 @@ const memory = new Memory({
     id: "learning-memory-vector",
     connectionUrl: "file:../../vector.db", // relative path from the `.mastra/output` directory
   }), // Vector database for semantic search
-  embedder: openai.embedding("text-embedding-3-small"), // Embedder for message embeddings
+  embedder: "openai/text-embedding-3-small", // Embedder for message embeddings
   options: {
     semanticRecall: {
       topK: 3,
@@ -52,7 +51,7 @@ export const memoryAgent = new Agent({
     Always refer to your working memory before asking for information the user has already provided.
     Use the information in your working memory to provide personalized responses.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   memory: memory,
 });
 ```

package/.docs/raw/course/03-agent-memory/22-custom-working-memory-templates.md

@@ -7,7 +7,6 @@ Let's update our agent with a custom working memory template:
 ```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { openai } from "@ai-sdk/openai";
 
 // Create a memory instance with a custom working memory template
 const memory = new Memory({
@@ -18,7 +17,7 @@ const memory = new Memory({
   vector: new LibSQLVector({
     connectionUrl: "file:../../vector.db", // relative path from the `.mastra/output` directory
   }), // Vector database for semantic search
-  embedder: openai.embedding("text-embedding-3-small"), // Embedder for message embeddings
+  embedder: "openai/text-embedding-3-small", // Embedder for message embeddings
   options: {
     semanticRecall: {
       topK: 3,
@@ -74,7 +73,7 @@ export const memoryAgent = new Agent({
     When the user shares personal information such as their name, location, or preferences,
     acknowledge it and update your working memory accordingly.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   memory: memory,
 });
 ```

package/.docs/raw/course/03-agent-memory/25-combining-memory-features.md

@@ -10,7 +10,6 @@ Let's create a comprehensive agent that utilizes conversation history, semantic
 // src/mastra/agents/memory-agent.ts
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { openai } from "@ai-sdk/openai";
 import { LibSQLStore, LibSQLVector } from "@mastra/libsql";
 
 // Create a comprehensive memory configuration
@@ -22,7 +21,7 @@ const memory = new Memory({
   vector: new LibSQLVector({
     connectionUrl: "file:../../vector.db", // relative path from the `.mastra/output` directory
   }),
-  embedder: openai.embedding("text-embedding-3-small"),
+  embedder: "openai/text-embedding-3-small",
   options: {
     // Conversation history configuration
     lastMessages: 20, // Include the last 20 messages in the context

package/.docs/raw/course/03-agent-memory/27-creating-learning-assistant.md

@@ -6,7 +6,6 @@ Let's create a practical example of a memory-enhanced agent: a Personal Learning
 // src/mastra/agents/learning-assistant.ts
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { openai } from "@ai-sdk/openai";
 import { LibSQLStore, LibSQLVector } from "@mastra/libsql";
 
 // Create a specialized memory configuration for the learning assistant
@@ -18,7 +17,7 @@ const learningMemory = new Memory({
   vector: new LibSQLVector({
     connectionUrl: "file:../../vector.db", // relative path from the `.mastra/output` directory
   }),
-  embedder: openai.embedding("text-embedding-3-small"),
+  embedder: "openai/text-embedding-3-small",
   options: {
     lastMessages: 20,
     semanticRecall: {
@@ -88,7 +87,7 @@ export const learningAssistantAgent = new Agent({
     Always be encouraging and supportive. Focus on building the user's confidence
     and celebrating their progress.
   `,
-  model: openai("gpt-4o"),
+  model: "openai/gpt-4.1-mini",
   memory: learningMemory,
 });
 

package/.docs/raw/course/04-workflows/11-creating-an-ai-agent.md

@@ -8,7 +8,6 @@ Create a new file for your agent in the `src/mastra/agents` directory. Use `cont
 
 ```typescript
 // src/mastra/agents/content-agent.ts
-import { openai } from "@ai-sdk/openai";
 import { Agent } from "@mastra/core/agent";
 
 export const contentAgent = new Agent({
@@ -23,7 +22,7 @@ export const contentAgent = new Agent({
     
     Always provide constructive, actionable feedback.
   `,
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-4.1-mini",
 });
 ```
 
@@ -32,7 +31,7 @@ export const contentAgent = new Agent({
 - **Name**: Unique identifier for the agent
 - **Description**: What the agent does
 - **Instructions**: Detailed prompts that guide the AI's behavior
-- **Model**: Which AI model to use (GPT-4o-mini is fast and cost-effective)
+- **Model**: Which AI model to use (GPT-4.1-mini is fast and cost-effective)
 
 ## Registering and Testing Your Agent
 

package/.docs/raw/deployment/cloud-providers.mdx

@@ -0,0 +1,20 @@
+---
+title: "Deploy to Cloud Providers | Deployment"
+description: Deploy your Mastra applications to cloud providers
+---
+
+# Deploy to Cloud Providers
+
+Mastra applications can be deployed to cloud providers and serverless platforms. Mastra includes optional built-in deployers for Vercel, Netlify, and Cloudflare to automate the deployment process.
+
+## Supported Cloud Providers
+
+The following guides show how to deploy Mastra to specific cloud providers:
+
+- [Amazon EC2](/guides/v1/deployment/amazon-ec2)
+- [AWS Lambda](/guides/v1/deployment/aws-lambda)
+- [Azure App Services](/guides/v1/deployment/azure-app-services)
+- [Cloudflare](/guides/v1/deployment/cloudflare-deployer)
+- [Digital Ocean](/guides/v1/deployment/digital-ocean)
+- [Netlify](/guides/v1/deployment/netlify-deployer)
+- [Vercel](/guides/v1/deployment/vercel-deployer)

package/.docs/raw/deployment/{building-mastra.mdx → mastra-server.mdx}

@@ -1,9 +1,9 @@
 ---
-title: "Building Mastra | Deployment"
+title: "Deploy a Mastra Server | Deployment"
 description: "Learn how to build a Mastra server with build settings and deployment options."
 ---
 
-# Building Mastra
+# Deploy a Mastra Server
 
 Mastra runs as a standard Node.js server and can be deployed across a wide range of environments.
 

package/.docs/raw/deployment/monorepo.mdx

@@ -1,11 +1,25 @@
 ---
-title: "Monorepo Deployment | Deployment"
+title: "Deploy in a Monorepo | Deployment"
 description: Learn how to deploy Mastra applications that are part of a monorepo setup
 ---
 
-# Monorepo Deployment
+# Deploy in a Monorepo
 
-Deploying Mastra in a monorepo follows the same approach as deploying a standalone application. While some [Cloud](./cloud-providers/) or [Serverless Platform](./cloud-providers/) providers may introduce extra requirements, the core setup is the same.
+Deploying Mastra in a monorepo follows the same approach as deploying a standalone application. While some [Cloud](/guides/v1/deployment) or [Serverless Platform](/guides/v1/deployment) providers may introduce extra requirements, the core setup is the same.
+
+## Supported monorepos
+
+Mastra works with:
+
+- npm workspaces
+- pnpm workspaces
+- Yarn workspaces
+- Turborepo
+
+Known limitations:
+
+- Bun workspaces - partial support; known issues
+- Nx - You can use Nx's [supported dependency strategies](https://nx.dev/concepts/decisions/dependency-management) but you need to have `package.json` files inside your workspace packages
 
 ## Example monorepo
 
@@ -44,10 +58,15 @@ api/
 
 ## Deployment configuration
 
-The image below shows how to select `apps/api` as the project root when deploying to [Mastra Cloud](./mastra-cloud/overview). While the interface may differ between providers, the configuration remains the same.
+The image below shows how to select `apps/api` as the project root when deploying to [Mastra Cloud](/docs/v1/mastra-cloud/overview). While the interface may differ between providers, the configuration remains the same.
 
 ![Deployment configuration](/img/monorepo/monorepo-mastra-cloud.jpg)
 
+
+:::info
+Make sure the correct package (e.g. `apps/api`) is selected as the deploy target. Selecting the wrong project root is a common deployment issue in monorepos.
+:::
+
 ## Dependency management
 
 In a monorepo, keep dependencies consistent to avoid version conflicts and build errors.
@@ -55,43 +74,3 @@ In a monorepo, keep dependencies consistent to avoid version conflicts and build
 - Use a **single lockfile** at the project root so all packages resolve the same versions.
 - Align versions of **shared libraries** (like Mastra or frameworks) to prevent duplicates.
 
-## Deployment pitfalls
-
-Common issues to watch for when deploying Mastra in a monorepo:
-
-- **Wrong project root**: make sure the correct package (e.g. `apps/api`) is selected as the deploy target.
-
-## Bundler options
-
-Use `transpilePackages` to compile TypeScript workspace packages or libraries. List package names exactly as they appear in each `package.json`. Use `externals` to exclude dependencies resolved at runtime, and `sourcemap` to emit readable stack traces.
-
-```typescript title="src/mastra/index.ts" showLineNumbers copy
-import { Mastra } from "@mastra/core";
-
-export const mastra = new Mastra({
-  // ...
-  bundler: {
-    transpilePackages: ["utils"],
-    externals: ["ui"],
-    sourcemap: true,
-  },
-});
-```
-
-> See [Mastra Class](/reference/v1/core/mastra-class) for more configuration options.
-
-## Supported monorepos
-
-Mastra works with:
-
-- npm workspaces
-- pnpm workspaces
-- Yarn workspaces
-- Turborepo
-
-Known limitations:
-
-- Bun workspaces — partial support; known issues
-- Nx — You can use Nx's [supported dependency strategies](https://nx.dev/concepts/decisions/dependency-management) but you need to have `package.json` files inside your workspace packages
-
-> If you are experiencing issues with monorepos see our: [Monorepos Support mega issue](https://github.com/mastra-ai/mastra/issues/6852).