@mastra/mcp-docs-server 1.0.0-beta.13 → 1.0.0-beta.15

package/.docs/raw/streaming/tool-streaming.mdx

@@ -18,7 +18,7 @@ By combining writable tool streams with agent streaming, you gain fine grained c
 
 Agent streaming can be combined with tool calls, allowing tool outputs to be written directly into the agent’s streaming response. This makes it possible to surface tool activity as part of the overall interaction.
 
-```typescript {2,9} showLineNumbers copy
+```typescript {2,9}
 import { Agent } from "@mastra/core/agent";
 import { testTool } from "../tools/test-tool";
 
@@ -41,7 +41,7 @@ You must `await` the call to `writer.write()` or else you will lock the stream a
 
 :::
 
-```typescript {4,7,14} showLineNumbers copy
+```typescript {4,7,14}
 import { createTool } from "@mastra/core/tools";
 
 export const testTool = createTool({
@@ -70,7 +70,7 @@ export const testTool = createTool({
 You can also use `writer.custom()` if you want to emit top level stream chunks, This useful and relevant when
 integrating with UI Frameworks
 
-```typescript {4,7,14} showLineNumbers copy
+```typescript {4,7,14}
 import { createTool } from "@mastra/core/tools";
 
 export const testTool = createTool({
@@ -100,7 +100,7 @@ export const testTool = createTool({
 
 Events written to the stream are included in the emitted chunks. These chunks can be inspected to access any custom fields, such as event types, intermediate values, or tool-specific data.
 
-```typescript showLineNumbers copy
+```typescript
 const stream = await testAgent.stream([
   "What is the weather in London?",
   "Use the testTool",
@@ -119,7 +119,7 @@ Tools support lifecycle hooks that allow you to monitor different stages of tool
 
 ### Example: Using onInputAvailable and onOutput
 
-```typescript showLineNumbers copy
+```typescript
 import { createTool } from "@mastra/core/tools";
 import { z } from "zod";
 
@@ -161,7 +161,7 @@ For detailed documentation on all lifecycle hooks, see the [createTool() referen
 
 Pipe an agent's `fullStream` to the tool's `writer`. This streams partial output, and Mastra automatically aggregates the agent's usage into the tool run.
 
-```typescript showLineNumbers copy
+```typescript
 import { createTool } from "@mastra/core/tools";
 import { z } from "zod";
 

package/.docs/raw/streaming/workflow-streaming.mdx

@@ -24,13 +24,12 @@ You must `await` the call to `writer.write(...)` or else you will lock the strea
 
 :::
 
-```typescript {5,8,15} showLineNumbers copy
+```typescript {5,7,14}
 import { createStep } from "@mastra/core/workflows";
 
 export const testStep = createStep({
-  // ...
   execute: async ({ inputData, writer }) => {
-     const { value } = inputData;
+    const { value } = inputData;
 
     await writer?.write({
       type: "custom-event",
@@ -39,7 +38,7 @@ export const testStep = createStep({
 
     const response = await fetch(...);
 
-   await writer?.write({
+    await writer?.write({
       type: "custom-event",
       status: "success"
     });
@@ -55,7 +54,7 @@ export const testStep = createStep({
 
 Events written to the stream are included in the emitted chunks. These chunks can be inspected to access any custom fields, such as event types, intermediate values, or step-specific data.
 
-```typescript showLineNumbers copy
+```typescript
 const testWorkflow = mastra.getWorkflow("testWorkflow");
 
 const run = await testWorkflow.createRun();
@@ -86,7 +85,7 @@ if (result!.status === "suspended") {
 
 If a workflow stream is closed or interrupted for any reason, you can resume it with the `resumeStream` method. This will return a new `ReadableStream` that you can use to observe the workflow events.
 
-```typescript showLineNumbers copy
+```typescript
 const newStream = await run.resumeStream();
 
 for await (const chunk of newStream) {
@@ -98,12 +97,11 @@ for await (const chunk of newStream) {
 
 Pipe an agent's `textStream` to the workflow step's `writer`. This streams partial output, and Mastra automatically aggregates the agent's usage into the workflow run.
 
-```typescript showLineNumbers copy
+```typescript
 import { createStep } from "@mastra/core/workflows";
 import { z } from "zod";
 
 export const testStep = createStep({
-  // ...
   execute: async ({ inputData, mastra, writer }) => {
     const { city } = inputData;
 

package/.docs/raw/tools-mcp/advanced-usage.mdx

@@ -82,13 +82,13 @@ Mastra maintains compatibility with the tool format used by the Vercel AI SDK (`
 
 First, ensure you have the `ai` package installed:
 
-```bash npm2yarn copy
+```bash npm2yarn
 npm install ai
 ```
 
 Here's an example of a tool defined using the Vercel AI SDK format:
 
-```typescript title="src/mastra/tools/vercelWeatherTool.ts" copy
+```typescript title="src/mastra/tools/vercelWeatherTool.ts"
 import { tool } from "ai";
 import { z } from "zod";
 

package/.docs/raw/tools-mcp/mcp-overview.mdx

@@ -29,7 +29,7 @@ npm install @mastra/mcp@beta
 
 The `MCPClient` connects Mastra primitives to external MCP servers, which can be local packages (invoked using `npx`) or remote HTTP(S) endpoints. Each server must be configured with either a `command` or a `url`, depending on how it's hosted.
 
-```typescript title="src/mastra/mcp/test-mcp-client.ts" showLineNumbers copy
+```typescript title="src/mastra/mcp/test-mcp-client.ts"
 import { MCPClient } from "@mastra/mcp";
 
 export const testMcpClient = new MCPClient({
@@ -48,13 +48,17 @@ export const testMcpClient = new MCPClient({
 });
 ```
 
-> See [MCPClient](/reference/v1/tools/mcp-client) for a full list of configuration options.
+:::info
+
+Visit [MCPClient](/reference/v1/tools/mcp-client) for a full list of configuration options.
+
+:::
 
 ## Using `MCPClient` with an agent
 
 To use tools from an MCP server in an agent, import your `MCPClient` and call `.listTools()` in the `tools` parameter. This loads from the defined MCP servers, making them available to the agent.
 
-```typescript {3,15} title="src/mastra/agents/test-agent.ts" showLineNumbers copy
+```typescript {3,15} title="src/mastra/agents/test-agent.ts"
 import { Agent } from "@mastra/core/agent";
 
 import { testMcpClient } from "../mcp/test-mcp-client";
@@ -74,13 +78,17 @@ export const testAgent = new Agent({
 });
 ```
 
-> See the [Agent Class](/reference/v1/agents/agent) for a full list of configuration options.
+:::info
+
+Visit [Agent Class](/reference/v1/agents/agent) for a full list of configuration options.
+
+:::
 
 ## Configuring `MCPServer`
 
 To expose agents, tools, and workflows from your Mastra application to external systems over HTTP(S) use the `MCPServer` class. This makes them accessible to any system or agent that supports the protocol.
 
-```typescript title="src/mastra/mcp/test-mcp-server.ts" showLineNumbers copy
+```typescript title="src/mastra/mcp/test-mcp-server.ts"
 import { MCPServer } from "@mastra/mcp";
 
 import { testAgent } from "../agents/test-agent";
@@ -97,7 +105,11 @@ export const testMcpServer = new MCPServer({
 });
 ```
 
-> See [MCPServer](/reference/v1/tools/mcp-server) for a full list of configuration options.
+:::info
+
+Visit [MCPServer](/reference/v1/tools/mcp-server) for a full list of configuration options.
+
+:::
 
 ### Serverless deployments
 
@@ -109,13 +121,12 @@ export const testMcpServer = new MCPServer({
 
 To make an MCP server available to other systems or agents that support the protocol, register it in the main `Mastra` instance using `mcpServers`.
 
-```typescript title="src/mastra/index.ts" showLineNumbers copy
+```typescript title="src/mastra/index.ts"
 import { Mastra } from "@mastra/core";
 
 import { testMcpServer } from "./mcp/test-mcp-server";
 
 export const mastra = new Mastra({
-  // ...
   mcpServers: {
     testMcpServer,  // Registry key: 'testMcpServer'
   },
@@ -141,9 +152,13 @@ mastra.getMCPServerById('test-mcp-server');    // By intrinsic ID
 
 Use the `.listTools()` method to fetch tools from all configured MCP servers. This is suitable when configuration (such as API keys) is static and consistent across users or requests. Call it once and pass the result to the `tools` property when defining your agent.
 
-> See [listTools()](/reference/v1/tools/mcp-client#listtools) for more information.
+:::info
+
+Visit [listTools()](/reference/v1/tools/mcp-client#listtools) for more information.
+
+:::
 
-```typescript {7} title="src/mastra/agents/test-agent.ts" showLineNumbers copy
+```typescript {7} title="src/mastra/agents/test-agent.ts"
 import { Agent } from "@mastra/core/agent";
 
 import { testMcpClient } from "../mcp/test-mcp-client";
@@ -158,7 +173,7 @@ export const testAgent = new Agent({
 
 Use the `.listToolsets()` method when tool configuration may vary by request or user, such as in a multi-tenant system where each user provides their own API key. This method returns toolsets that can be passed to the `toolsets` option in the agent's `.generate()` or `.stream()` calls.
 
-```typescript {5-16,21} showLineNumbers copy
+```typescript {5-16,21}
 import { MCPClient } from "@mastra/mcp";
 import { mastra } from "./mastra";
 
@@ -190,7 +205,11 @@ async function handleRequest(userPrompt: string, userApiKey: string) {
 }
 ```
 
-> See [listToolsets()](/reference/v1/tools/mcp-client#listtoolsets) for more information.
+:::info
+
+Visit [listToolsets()](/reference/v1/tools/mcp-client#listtoolsets) for more information.
+
+:::
 
 ## Connecting to an MCP registry
 

package/.docs/raw/tools-mcp/overview.mdx

@@ -18,7 +18,7 @@ Each tool typically defines:
 
 In Mastra, you create tools using the [`createTool`](/reference/v1/tools/create-tool) function from the `@mastra/core/tools` package.
 
-```typescript title="src/mastra/tools/weatherInfo.ts" copy
+```typescript title="src/mastra/tools/weatherInfo.ts"
 import { createTool } from "@mastra/core/tools";
 import { z } from "zod";
 
@@ -58,21 +58,16 @@ To make tools available to an agent, you configure them in the agent's definitio
 
 Use [RequestContext](/docs/v1/server/request-context) to access request-specific values. This lets you conditionally adjust behavior based on the context of the request.
 
-```typescript title="src/mastra/tools/test-tool.ts" showLineNumbers
+```typescript title="src/mastra/tools/test-tool.ts"
 export type UserTier = {
   "user-tier": "enterprise" | "pro";
 };
 
-const advancedTools = () => {
-  // ...
-};
+const advancedTools = () => {};
 
-const baseTools = () => {
-  // ...
-};
+const baseTools = () => {};
 
 export const testTool = createTool({
-  // ...
   execute: async ({ requestContext }) => {
     const userTier = requestContext.get("user-tier") as UserTier["user-tier"];
 
@@ -81,7 +76,11 @@ export const testTool = createTool({
 });
 ```
 
-> See [Request Context](/docs/v1/server/request-context) for more information.
+:::info
+
+Visit [Request Context](/docs/v1/server/request-context) for more information.
+
+:::
 
 ## Testing with Studio
 

package/.docs/raw/voice/overview.mdx

@@ -917,7 +917,7 @@ const voiceAgent = new Agent({
   id: "aisdk-voice-agent",
   name: "AI SDK Voice Agent",
   instructions: "You are a helpful assistant with voice capabilities.",
-  model: openai("gpt-5.1"),
+  model: "openai/gpt-5.1",
   voice,
 });
 ```
@@ -1031,4 +1031,4 @@ For more information on the CompositeVoice, refer to the [CompositeVoice Referen
 - [Google Gemini Live Voice](/reference/v1/voice/google-gemini-live)
 - [Deepgram Voice](/reference/v1/voice/deepgram)
 - [PlayAI Voice](/reference/v1/voice/playai)
-- [Voice Examples](/examples/v1/voice/text-to-speech)
+- [Voice Examples](https://github.com/mastra-ai/voice-examples)

package/.docs/raw/workflows/agents-and-tools.mdx

@@ -9,15 +9,14 @@ Workflow steps can call agents to leverage LLM reasoning or call tools for type-
 
 ## Using agents in workflows
 
-Use agents in workflow steps when you need reasoning, language generation, or other LLM-based tasks. Call from a step's `execute` function for more control over the agent call (e.g., track conversation history or return structured output). Compose agents as steps when you don't need to modify how the agent is invoked.
+Use agents in workflow steps when you need reasoning, language generation, or other LLM-based tasks. Call from a step's `execute` function for more control over the agent call (e.g., track message history or return structured output). Compose agents as steps when you don't need to modify how the agent is invoked.
 
 ### Calling agents
 
 Call agents inside a step's `execute` function using `.generate()` or `.stream()`. This lets you modify the agent call and handle the response before passing it to the next step.
 
-```typescript {7-12} title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript {6-14} title="src/mastra/workflows/test-workflow.ts"
 const step1 = createStep({
-  // ...
   execute: async ({ inputData, mastra }) => {
     const { message } = inputData;
 
@@ -45,13 +44,12 @@ Compose an agent as a step using `createStep()` when you don't need to modify th
 
 ![Agent as step](/img/workflows/workflows-agent-tools-agent-step.jpg)
 
-```typescript {1,3,8-13} title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript {1,3,7-12} title="src/mastra/workflows/test-workflow.ts"
 import { testAgent } from "../agents/test-agent";
 
 const step1 = createStep(testAgent);
 
 export const testWorkflow = createWorkflow({
-  // ...
 })
   .map(async ({ inputData }) => {
     const { message } = inputData;
@@ -64,7 +62,11 @@ export const testWorkflow = createWorkflow({
   .commit();
 ```
 
-> See [Input Data Mapping](./input-data-mapping) for more information.
+:::info
+
+Visit [Input Data Mapping](./input-data-mapping) for more information.
+
+:::
 
 When no `structuredOutput` option is provided, Mastra agents use a default schema that expects a `prompt` string as input and returns a `text` string as output:
 
@@ -83,7 +85,7 @@ When no `structuredOutput` option is provided, Mastra agents use a default schem
 
 When you need the agent to return structured data instead of plain text, pass the `structuredOutput` option to `createStep()`. The step's output schema will match your provided schema, enabling type-safe chaining to subsequent steps.
 
-```typescript {1-6,8-10} title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript {1-6,8-10} title="src/mastra/workflows/test-workflow.ts"
 const articleSchema = z.object({
   title: z.string(),
   summary: z.string(),
@@ -104,9 +106,7 @@ const processStep = createStep({
   }),
 });
 
-export const testWorkflow = createWorkflow({
-  // ...
-})
+export const testWorkflow = createWorkflow({})
   .map(async ({ inputData }) => ({
     prompt: `Generate an article about: ${inputData.topic}`,
   }))
@@ -117,7 +117,11 @@ export const testWorkflow = createWorkflow({
 
 The `structuredOutput.schema` option accepts any Zod schema. The agent will generate output conforming to this schema, and the step's `outputSchema` will be automatically set to match.
 
-> See [Structured Output](/docs/v1/agents/structured-output) for more options like error handling strategies and streaming with structured output.
+:::info
+
+Visit [Structured Output](/docs/v1/agents/structured-output) for more options like error handling strategies and streaming with structured output.
+
+:::
 
 ## Using tools in workflows
 
@@ -127,11 +131,10 @@ Use tools in workflow steps to leverage existing tool logic. Call from a step's
 
 Call tools inside a step's `execute` function using `.execute()`. This gives you more control over the tool's input context, or process its response before passing it to the next step.
 
-```typescript {8-13,16} title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript {7-12} title="src/mastra/workflows/test-workflow.ts"
 import { testTool } from "../tools/test-tool";
 
 const step2 = createStep({
-  // ...
   execute: async ({ inputData, requestContext }) => {
     const { formatted } = inputData;
 
@@ -149,7 +152,11 @@ const step2 = createStep({
 });
 ```
 
-> See [Calling Tools](/docs/v1/workflows/agents-and-tools#calling-tools) for more examples.
+:::info
+
+Visit [Calling Tools](/docs/v1/workflows/agents-and-tools#calling-tools) for more examples.
+
+:::
 
 ### Tools as steps
 
@@ -157,14 +164,12 @@ Compose a tool as a step using `createStep()` when the previous step's output ma
 
 ![Tool as step](/img/workflows/workflows-agent-tools-tool-step.jpg)
 
-```typescript {1,3,9-14} title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript {1,3,7-12} title="src/mastra/workflows/test-workflow.ts"
 import { testTool } from "../tools/test-tool";
 
 const step2 = createStep(testTool);
 
-export const testWorkflow = createWorkflow({
-  // ...
-})
+export const testWorkflow = createWorkflow({})
   .then(step1)
   .map(async ({ inputData }) => {
     const { formatted } = inputData;
@@ -176,7 +181,11 @@ export const testWorkflow = createWorkflow({
   .commit();
 ```
 
-> See [Input Data Mapping](./input-data-mapping) for more information.
+:::info
+
+Visit [Input Data Mapping](./input-data-mapping) for more information.
+
+:::
 
 ## Related