@mastra/mcp-docs-server 0.13.12-alpha.2 → 0.13.12-alpha.4

package/.docs/organized/changelogs/%40mastra%2Frag.md

@@ -1,5 +1,27 @@
 # @mastra/rag
 
+## 1.0.9-alpha.0
+
+### Patch Changes
+
+- a741dde: generateVNext plumbing
+- Updated dependencies [0a7f675]
+- Updated dependencies [12cae67]
+- Updated dependencies [5a37d0c]
+- Updated dependencies [4bde0cb]
+- Updated dependencies [1a80071]
+- Updated dependencies [36a3be8]
+- Updated dependencies [361757b]
+- Updated dependencies [2bb9955]
+- Updated dependencies [2454423]
+- Updated dependencies [a44d91e]
+- Updated dependencies [dfb91e9]
+- Updated dependencies [a741dde]
+- Updated dependencies [7cb3fc0]
+- Updated dependencies [195eabb]
+- Updated dependencies [b78b95b]
+  - @mastra/core@0.14.0-alpha.4
+
 ## 1.0.8
 
 ### Patch Changes
@@ -276,27 +298,5 @@
 - a85fa13: Add model to createVectorQueryTool runtimeContext
 - Updated dependencies [15e9d26]
 - Updated dependencies [07d6d88]
-- Updated dependencies [5d74aab]
-- Updated dependencies [144eb0b]
-  - @mastra/core@0.10.7-alpha.2
-
-## 1.0.0
-
-### Major Changes
-
-- 75136cd: Add LaTeX chunking support by adding a case for Language.LATEX in getSeparatorsForLanguage.
-
-### Patch Changes
 
-- 63f6b7d: dependencies updates:
-  - Updated dependency [`zod@^3.25.57` ↗︎](https://www.npmjs.com/package/zod/v/3.25.57) (from `^3.25.56`, in `dependencies`)
-- Updated dependencies [63f6b7d]
-- Updated dependencies [12a95fc]
-- Updated dependencies [4b0f8a6]
-- Updated dependencies [51264a5]
-- Updated dependencies [8e6f677]
-- Updated dependencies [d70c420]
-- Updated dependencies [ee9af57]
-- Updated dependencies [36f1c36]
-
-... 2415 more lines hidden. See full changelog in package directory.
+... 2437 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fserver.md

@@ -1,5 +1,38 @@
 # @mastra/server
 
+## 0.14.0-alpha.4
+
+### Patch Changes
+
+- bc1684a: Fix lint
+- dfb91e9: Server handlers
+- 57f7019: Add modelVersion to agent response
+- Updated dependencies [0a7f675]
+- Updated dependencies [12cae67]
+- Updated dependencies [5a37d0c]
+- Updated dependencies [4bde0cb]
+- Updated dependencies [1a80071]
+- Updated dependencies [36a3be8]
+- Updated dependencies [361757b]
+- Updated dependencies [2bb9955]
+- Updated dependencies [2454423]
+- Updated dependencies [a44d91e]
+- Updated dependencies [dfb91e9]
+- Updated dependencies [a741dde]
+- Updated dependencies [7cb3fc0]
+- Updated dependencies [195eabb]
+- Updated dependencies [b78b95b]
+  - @mastra/core@0.14.0-alpha.4
+
+## 0.14.0-alpha.3
+
+### Patch Changes
+
+- Updated dependencies [227c7e6]
+- Updated dependencies [fd3a3eb]
+- Updated dependencies [a8f129d]
+  - @mastra/core@0.14.0-alpha.3
+
 ## 0.14.0-alpha.2
 
 ### Patch Changes
@@ -266,37 +299,4 @@
 
 ### Patch Changes
 
-- ff9c125: enhance thread retrieval with sorting options in libsql and pg
-- b8efbb9: feat: add flexible deleteMessages method to memory API
-  - Added `memory.deleteMessages(input)` method that accepts multiple input types:
-    - Single message ID as string: `deleteMessages('msg-123')`
-    - Array of message IDs: `deleteMessages(['msg-1', 'msg-2'])`
-    - Message object with id property: `deleteMessages({ id: 'msg-123' })`
-    - Array of message objects: `deleteMessages([{ id: 'msg-1' }, { id: 'msg-2' }])`
-  - Implemented in all storage adapters (LibSQL, PostgreSQL, Upstash, InMemory)
-  - Added REST API endpoint: `POST /api/memory/messages/delete`
-  - Updated client SDK: `thread.deleteMessages()` accepts all input types
-  - Updates thread timestamps when messages are deleted
-  - Added comprehensive test coverage and documentation
-
-- Updated dependencies [27cc97a]
-- Updated dependencies [41daa63]
-- Updated dependencies [254a36b]
-- Updated dependencies [0b89602]
-- Updated dependencies [4d37822]
-- Updated dependencies [ff9c125]
-- Updated dependencies [b8efbb9]
-- Updated dependencies [71466e7]
-- Updated dependencies [0c99fbe]
-  - @mastra/core@0.12.0-alpha.2
-
-## 0.12.0-alpha.1
-
-### Patch Changes
-
-- Updated dependencies [e0f73c6]
-- Updated dependencies [cda801d]
-- Updated dependencies [a77c823]
-  - @mastra/core@0.12.0-alpha.1
-
-... 2811 more lines hidden. See full changelog in package directory.
+... 2844 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fvoice-google.md

@@ -1,5 +1,28 @@
 # @mastra/voice-google
 
+## 0.10.8-alpha.0
+
+### Patch Changes
+
+- 50210fc: dependencies updates:
+  - Updated dependency [`@google-cloud/text-to-speech@^6.2.0` ↗︎](https://www.npmjs.com/package/@google-cloud/text-to-speech/v/6.2.0) (from `^6.1.0`, in `dependencies`)
+- Updated dependencies [0a7f675]
+- Updated dependencies [12cae67]
+- Updated dependencies [5a37d0c]
+- Updated dependencies [4bde0cb]
+- Updated dependencies [1a80071]
+- Updated dependencies [36a3be8]
+- Updated dependencies [361757b]
+- Updated dependencies [2bb9955]
+- Updated dependencies [2454423]
+- Updated dependencies [a44d91e]
+- Updated dependencies [dfb91e9]
+- Updated dependencies [a741dde]
+- Updated dependencies [7cb3fc0]
+- Updated dependencies [195eabb]
+- Updated dependencies [b78b95b]
+  - @mastra/core@0.14.0-alpha.4
+
 ## 0.10.7
 
 ### Patch Changes
@@ -275,28 +298,5 @@
 - Updated dependencies [344f453]
 - Updated dependencies [0a3ae6d]
 - Updated dependencies [95911be]
-- Updated dependencies [5eb5a99]
-- Updated dependencies [7e632c5]
-- Updated dependencies [1e9fbfa]
-- Updated dependencies [b2ae5aa]
-- Updated dependencies [a7292b0]
-- Updated dependencies [0dcb9f0]
-  - @mastra/core@0.10.0-alpha.1
-
-## 0.1.19-alpha.0
-
-### Patch Changes
-
-- Updated dependencies [f53a6ac]
-- Updated dependencies [eabdcd9]
-- Updated dependencies [90be034]
-- Updated dependencies [99f050a]
-- Updated dependencies [d0ee3c6]
-- Updated dependencies [23f258c]
-- Updated dependencies [2672a05]
-  - @mastra/core@0.9.5-alpha.0
-
-## 0.1.18
-
 
-... 1073 more lines hidden. See full changelog in package directory.
+... 1096 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/create-mastra.md

@@ -1,5 +1,13 @@
 # create-mastra
 
+## 0.10.22-alpha.3
+
+## 0.10.22-alpha.2
+
+### Patch Changes
+
+- 36928f0: Use right icon for anthropic in model switcher
+
 ## 0.10.22-alpha.1
 
 ### Patch Changes
@@ -291,12 +299,4 @@
 
 ## 0.10.6
 
-### Patch Changes
-
-- 5d74aab: vNext network in playground
-- 9102d89: Fix final output not showing on playground for previously suspended steps
-- 21ffb97: Make dynamic form handle schema better
-- f9b4350: fix icons not showing on all agents
-
-
-... 1206 more lines hidden. See full changelog in package directory.
+... 1214 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/mastra.md

@@ -1,5 +1,46 @@
 # mastra
 
+## 0.10.22-alpha.3
+
+### Patch Changes
+
+- 1d59515: Add options to playground based on modelVersion
+- Updated dependencies [0a7f675]
+- Updated dependencies [12cae67]
+- Updated dependencies [96518cc]
+- Updated dependencies [5a37d0c]
+- Updated dependencies [4bde0cb]
+- Updated dependencies [e1aed55]
+- Updated dependencies [1a80071]
+- Updated dependencies [36a3be8]
+- Updated dependencies [c712849]
+- Updated dependencies [361757b]
+- Updated dependencies [2bb9955]
+- Updated dependencies [2454423]
+- Updated dependencies [a44d91e]
+- Updated dependencies [dfb91e9]
+- Updated dependencies [a741dde]
+- Updated dependencies [95e1330]
+- Updated dependencies [7cb3fc0]
+- Updated dependencies [195eabb]
+- Updated dependencies [33eb340]
+- Updated dependencies [b78b95b]
+  - @mastra/core@0.14.0-alpha.4
+  - @mastra/deployer@0.14.0-alpha.4
+  - @mastra/mcp@0.10.12-alpha.1
+
+## 0.10.22-alpha.2
+
+### Patch Changes
+
+- 36928f0: Use right icon for anthropic in model switcher
+- Updated dependencies [227c7e6]
+- Updated dependencies [fd3a3eb]
+- Updated dependencies [04dcd66]
+- Updated dependencies [a8f129d]
+  - @mastra/core@0.14.0-alpha.3
+  - @mastra/deployer@0.14.0-alpha.3
+
 ## 0.10.22-alpha.1
 
 ### Patch Changes
@@ -257,46 +298,5 @@
 - Updated dependencies [b4a8df0]
   - @mastra/core@0.12.1-alpha.0
   - @mastra/mcp@0.10.9-alpha.0
-  - @mastra/deployer@0.12.1-alpha.0
-
-## 0.10.16
-
-### Patch Changes
 
-- bc6b44a: Extract tools import from `createHonoServer`; the function now receives tools via a prop on the `options` parameter.
-- f442224: speech to text using voice config
-- 7a7754f: Fast follow scorers fixing input types, improve llm scorer reliability, fix ui to display scores that are 0
-- d8dec5e: add a cta to invite to deploy to cloud
-- 6336993: Fix workflow input form overflow
-- d5cc460: This change implements a fix to sourcemap mappings being off due to `removeDeployer` Babel plugin missing source map config.
-- f42c4c2: update peer deps for packages to latest core range
-- a5681f2: fix: pagination breaks trace grouping
-- 89d2f4e: add TTS to the playground
-- Updated dependencies [510e2c8]
-- Updated dependencies [2f72fb2]
-- Updated dependencies [27cc97a]
-- Updated dependencies [832691b]
-- Updated dependencies [557bb9d]
-- Updated dependencies [27cc97a]
-- Updated dependencies [3f89307]
-- Updated dependencies [9eda7d4]
-- Updated dependencies [9d49408]
-- Updated dependencies [bc6b44a]
-- Updated dependencies [41daa63]
-- Updated dependencies [ad0a58b]
-- Updated dependencies [254a36b]
-- Updated dependencies [2ecf658]
-- Updated dependencies [7a7754f]
-- Updated dependencies [fc92d80]
-- Updated dependencies [e0f73c6]
-- Updated dependencies [0b89602]
-- Updated dependencies [4d37822]
-- Updated dependencies [23a6a7c]
-- Updated dependencies [cda801d]
-- Updated dependencies [a77c823]
-- Updated dependencies [ff9c125]
-- Updated dependencies [09bca64]
-- Updated dependencies [9802f42]
-- Updated dependencies [d5cc460]
-
-... 4912 more lines hidden. See full changelog in package directory.
+... 4953 more lines hidden. See full changelog in package directory.

package/.docs/organized/code-examples/agent.md

@@ -5,6 +5,7 @@
   "dependencies": {
     "@ai-sdk/google": "^1.2.22",
     "@ai-sdk/openai": "^1.3.23",
+    "@ai-sdk/openai-v5": "npm:@ai-sdk/openai@2.0.0",
     "@mastra/client-js": "latest",
     "@mastra/core": "latest",
     "@mastra/evals": "latest",
@@ -14,6 +15,7 @@
     "@mastra/memory": "latest",
     "@mastra/voice-openai": "latest",
     "ai": "^4.3.16",
+    "ai-v5": "npm:ai@^5.0.0",
     "fetch-to-node": "^2.1.0",
     "mastra": "latest",
     "typescript": "^5.8.3",
@@ -474,7 +476,6 @@ import { Agent, InputProcessor } from '@mastra/core/agent';
 import { cookingTool } from '../tools/index.js';
 import { myWorkflow } from '../workflows/index.js';
 import { PIIDetector, LanguageDetector, PromptInjectionDetector, ModerationProcessor } from '@mastra/core/processors';
-import { MCPClient } from '@mastra/mcp';
 import { createAnswerRelevancyScorer } from '@mastra/evals/scorers/llm';
 
 const memory = new Memory();
@@ -511,8 +512,8 @@ export const chefAgent = new Agent({
   description: 'A chef agent that can help you cook great meals with whatever ingredients you have available.',
   instructions: `
     YOU MUST USE THE TOOL cooking-tool
-    You are Michel, a practical and experienced home chef who helps people cook great meals with whatever 
-    ingredients they have available. Your first priority is understanding what ingredients and equipment the user has access to, then suggesting achievable recipes. 
+    You are Michel, a practical and experienced home chef who helps people cook great meals with whatever
+    ingredients they have available. Your first priority is understanding what ingredients and equipment the user has access to, then suggesting achievable recipes.
     You explain cooking steps clearly and offer substitutions when needed, maintaining a friendly and encouraging tone throughout.
     `,
   model: openai('gpt-4o-mini'),
@@ -599,8 +600,8 @@ const moderationDetector = new ModerationProcessor({
 export const chefAgentResponses = new Agent({
   name: 'Chef Agent Responses',
   instructions: `
-    You are Michel, a practical and experienced home chef who helps people cook great meals with whatever 
-    ingredients they have available. Your first priority is understanding what ingredients and equipment the user has access to, then suggesting achievable recipes. 
+    You are Michel, a practical and experienced home chef who helps people cook great meals with whatever
+    ingredients they have available. Your first priority is understanding what ingredients and equipment the user has access to, then suggesting achievable recipes.
     You explain cooking steps clearly and offer substitutions when needed, maintaining a friendly and encouraging tone throughout.
     `,
   model: openai.responses('gpt-4o'),
@@ -608,6 +609,7 @@ export const chefAgentResponses = new Agent({
   tools: async () => {
     return {
       web_search_preview: openai.tools.webSearchPreview(),
+      cooking_tool: cookingTool,
     };
   },
   workflows: {
@@ -695,6 +697,58 @@ export const evalAgent = new Agent({
 
 ```
 
+### mastra/agents/model-v2-agent.ts
+```typescript
+import { Agent } from '@mastra/core/agent';
+import { openai as openai_v5 } from '@ai-sdk/openai-v5';
+import { createTool } from '@mastra/core/tools';
+import { z } from 'zod';
+import { cookingTool } from '../tools';
+import { myWorkflow } from '../workflows';
+import { Memory } from '@mastra/memory';
+
+export const weatherInfo = createTool({
+  id: 'weather-info',
+  description: 'Fetches the current weather information for a given city',
+  inputSchema: z.object({
+    city: z.string(),
+  }),
+  execute: async ({ context }) => {
+    return {
+      city: context.city,
+      weather: 'sunny',
+      temperature_celsius: 19,
+      temperature_fahrenheit: 66,
+      humidity: 50,
+      wind: '10 mph',
+    };
+  },
+});
+
+const memory = new Memory();
+
+export const chefModelV2Agent = new Agent({
+  name: 'Chef Agent V2 Model',
+  description: 'A chef agent that can help you cook great meals with whatever ingredients you have available.',
+  instructions: `
+      YOU MUST USE THE TOOL cooking-tool
+      You are Michel, a practical and experienced home chef who helps people cook great meals with whatever
+      ingredients they have available. Your first priority is understanding what ingredients and equipment the user has access to, then suggesting achievable recipes.
+      You explain cooking steps clearly and offer substitutions when needed, maintaining a friendly and encouraging tone throughout.
+      `,
+  model: openai_v5('gpt-4o-mini'),
+  tools: {
+    cookingTool,
+    weatherInfo,
+  },
+  workflows: {
+    myWorkflow,
+  },
+  memory,
+});
+
+```
+
 ### mastra/index.ts
 ```typescript
 import { Mastra } from '@mastra/core';
@@ -704,13 +758,21 @@ import { LibSQLStore } from '@mastra/libsql';
 import { agentThatHarassesYou, chefAgent, chefAgentResponses, dynamicAgent, evalAgent } from './agents/index';
 import { myMcpServer, myMcpServerTwo } from './mcp/server';
 import { myWorkflow } from './workflows';
+import { chefModelV2Agent } from './agents/model-v2-agent';
 
 const storage = new LibSQLStore({
   url: 'file:./mastra.db',
 });
 
 export const mastra = new Mastra({
-  agents: { chefAgent, chefAgentResponses, dynamicAgent, agentThatHarassesYou, evalAgent },
+  agents: {
+    chefAgent,
+    chefAgentResponses,
+    dynamicAgent,
+    agentThatHarassesYou,
+    evalAgent,
+    chefModelV2Agent,
+  },
   logger: new PinoLogger({ name: 'Chef', level: 'debug' }),
   storage,
   mcpServers: {
@@ -995,14 +1057,14 @@ import { z } from 'zod';
 
 export const cookingTool = createTool({
   id: 'cooking-tool',
-  description: 'My tool description',
+  description: 'My cooking tool description',
   inputSchema: z.object({
     ingredient: z.string(),
   }),
   execute: async ({ context }, options) => {
-    console.log('My tool is running!', context.ingredient);
+    console.log('My cooking tool is running!', context.ingredient);
     if (options?.toolCallId) {
-      console.log('Tool call ID:', options.toolCallId);
+      console.log('Cooking tool call ID:', options.toolCallId);
     }
     return 'My tool result';
   },
@@ -1051,9 +1113,11 @@ const step2 = createStep({
   outputSchema: z.object({
     result: z.string(),
   }),
-  execute: async ({ inputData, mastra }) => {
+  execute: async ({ inputData, mastra, aiTracingContext }) => {
     const agent = mastra.getAgent('chefAgentResponses');
-    const response = await agent.generate(inputData.result);
+    const response = await agent.generate(inputData.result, {
+      aiTracingContext,
+    });
     return {
       result: 'suh',
     };

package/.docs/raw/deployment/server-deployment.mdx

@@ -1,41 +1,75 @@
 ---
-title: "Deploy A Mastra Server"
-description: "Deploy a Mastra server with middleware and other options"
+title: "Deploy a Mastra Server"
+description: "Learn how to deploy a Mastra server with build settings and deployment options."
 ---
 
-# Deploy A Mastra Server
+import { FileTree } from "nextra/components";
 
-Mastra builds to a standard Node.js server, so you can deploy it to any platform that supports Node.js applications.
+# Deploy a Mastra Server
 
-- Cloud VMs (AWS EC2, DigitalOcean Droplets, GCP Compute Engine)
-- Container platforms (Docker, Kubernetes)
-- Platform as a Service (Heroku, Railway)
-- Self-hosted servers
+Mastra runs as a standard Node.js server and can be deployed across a wide range of environments.
 
-See the [Cloud Providers](/docs/deployment/cloud-providers/) for more information.
+## Default project structure
 
-### Building
+The [getting started guide](/docs/getting-started/installation) scaffolds a project with sensible defaults to help you begin quickly. By default, the CLI organizes application files under the `src/mastra/` directory, resulting in a structure similar to the following:
 
-Build the application:
+<FileTree>
+  <FileTree.Folder name="src" defaultOpen>
+    <FileTree.Folder name="mastra" defaultOpen>
+      <FileTree.Folder name="agents" />
+      <FileTree.Folder name="tools" />
+      <FileTree.Folder name="workflows" />
+      <FileTree.File name="index.ts" />
+    </FileTree.Folder>
+  </FileTree.Folder>
+  <FileTree.File name="package.json" />
+  <FileTree.File name="tsconfig.json" />
+</FileTree>
+
+## Building
+
+The `mastra build` command starts the build process:
 
 ```bash copy
-# Build from current directory
 mastra build
+```
+
+### Customizing the input directory
 
-# Or specify a directory
-mastra build --dir ./my-project
+If your Mastra files are located elsewhere, use the `--dir` flag to specify the custom location. The `--dir` flag tells Mastra where to find your entry point file (`index.ts` or `index.js`) and related directories.
+
+```bash copy
+mastra build --dir ./my-project/mastra
 ```
 
-The build process:
+## Build process
+
+The build process follows these steps:
 
-1. Locates entry file (`src/mastra/index.ts` or `src/mastra/index.js`)
-2. Creates `.mastra` output directory
-3. Bundles code using Rollup with tree shaking and source maps
-4. Generates [Hono](https://hono.dev) HTTP server
+1. **Locates entry file**: Finds `index.ts` or `index.js` in your specified directory (default: `src/mastra/`).
+2. **Creates build directory**: Generates a `.mastra/` directory containing:
+    - **`.build`**: Contains dependency analysis, bundled dependencies, and build configuration files.
+    - **`output`**: Contains the production-ready application bundle with `index.mjs`, `instrumentation.mjs`, and project-specific files.
+3. **Copies static assets**: Copies the `public/` folder contents to the `output` directory for serving static files.
+4. **Bundles code**: Uses Rollup with tree shaking and source maps for optimization.
+5. **Generates server**: Creates a [Hono](https://hono.dev) HTTP server ready for deployment.
 
-See [`mastra build`](/reference/cli/build) for all options.
+### Build output structure
 
-### Running the Server
+After building, Mastra creates a `.mastra/` directory with the following structure:
+
+<FileTree>
+  <FileTree.Folder name=".mastra" defaultOpen>
+    <FileTree.Folder name=".build" />
+    <FileTree.Folder name="output" />
+  </FileTree.Folder>
+</FileTree>
+
+### `public` folder
+
+If a `public` folder exists in `src/mastra`, its contents are copied into the `.build/output` directory during the build process.
+
+## Running the Server
 
 Start the HTTP server:
 
@@ -43,14 +77,10 @@ Start the HTTP server:
 node .mastra/output/index.mjs
 ```
 
-### Enable Telemetry for build output
+## Enable Telemetry
 
-Load instrumentation for the build output like so:
+To enable telemetry and observability, load the instrumentation file:
 
 ```bash copy
 node --import=./.mastra/output/instrumentation.mjs .mastra/output/index.mjs
 ```
-
-## Serverless Deployment
-
-Mastra also supports serverless deployment on Cloudflare Workers, Vercel, and Netlify. See [Serverless Platforms](/docs/deployment/serverless-platforms/) for more information.

package/.docs/raw/deployment/serverless-platforms/cloudflare-deployer.mdx

@@ -24,14 +24,11 @@ import { CloudflareDeployer } from "@mastra/deployer-cloudflare";
 export const mastra = new Mastra({
   // ...
   deployer: new CloudflareDeployer({
-    scope: "your-account-id",
     projectName: "hello-mastra",
-    scope: "",
-    auth: {
-      apiToken: process.env.CLOUDFLARE_API_TOKEN!,
-      apiEmail: "name@email.com"
-    }
-  })
+    env: {
+      NODE_ENV: "production",
+    },
+  }),
 });
 ```