@mastra/mcp-docs-server 0.13.11 → 0.13.12-alpha.0

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

@@ -1,5 +1,47 @@
 # mastra
 
+## 0.10.22-alpha.0
+
+### Patch Changes
+
+- 97c1d5e: Add new `scorers` subcommand for managing scorers.
+  Refactor cli to be more modular.
+- Updated dependencies [c30bca8]
+  - @mastra/core@0.13.3-alpha.0
+  - @mastra/deployer@0.13.3-alpha.0
+
+## 0.10.21
+
+### Patch Changes
+
+- 63449d0: Change the globbing of tools to exclude test files. Files inside `__tests__` directory and files with `.test.` or `.spec.` in their file name are now excluded from bundling.
+- 77b6cfe: Use just modelId for gpt-5 check
+- 96169cc: Create handler that returns providers user has keys for in their env
+- 33da97c: Set temperature to 1 for gpt-5 model in playground
+- c6d2603: Properly set baseUrl in playground when user sets the host or port in Mastra instance.
+- 7aad750: Fix tool ui showing after message when chat is refreshed
+- ce04175: Add update agent model handler
+- Updated dependencies [d5330bf]
+- Updated dependencies [aaf0224]
+- Updated dependencies [2e74797]
+- Updated dependencies [42cb4e9]
+- Updated dependencies [8388649]
+- Updated dependencies [a239d41]
+- Updated dependencies [dd94a26]
+- Updated dependencies [3ba6772]
+- Updated dependencies [96169cc]
+- Updated dependencies [b5cf2a3]
+- Updated dependencies [2fff911]
+- Updated dependencies [b32c50d]
+- Updated dependencies [c6d2603]
+- Updated dependencies [63449d0]
+- Updated dependencies [121a3f8]
+- Updated dependencies [ce04175]
+- Updated dependencies [ec510e7]
+  - @mastra/core@0.13.2
+  - @mastra/deployer@0.13.2
+  - @mastra/mcp@0.10.11
+
 ## 0.10.21-alpha.2
 
 ### Patch Changes
@@ -256,47 +298,5 @@
   - @mastra/mcp@0.10.8-alpha.0
   - @mastra/core@0.12.0-alpha.5
 
-## 0.10.16-alpha.2
-
-### Patch Changes
-
-- d5cc460: This change implements a fix to sourcemap mappings being off due to `removeDeployer` Babel plugin missing source map config.
-- a5681f2: fix: pagination breaks trace grouping
-- Updated dependencies [27cc97a]
-- Updated dependencies [27cc97a]
-- Updated dependencies [41daa63]
-- Updated dependencies [254a36b]
-- Updated dependencies [0b89602]
-- Updated dependencies [4d37822]
-- Updated dependencies [ff9c125]
-- Updated dependencies [d5cc460]
-- Updated dependencies [b8efbb9]
-- Updated dependencies [71466e7]
-- Updated dependencies [0c99fbe]
-  - @mastra/core@0.12.0-alpha.2
-  - @mastra/deployer@0.12.0-alpha.2
-
-## 0.10.16-alpha.1
-
-### Patch Changes
-
-- 6336993: Fix workflow input form overflow
-- Updated dependencies [e0f73c6]
-- Updated dependencies [cda801d]
-- Updated dependencies [a77c823]
-  - @mastra/core@0.12.0-alpha.1
-  - @mastra/deployer@0.12.0-alpha.1
-
-## 0.10.16-alpha.0
-
-### 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
-- 89d2f4e: add TTS to the playground
-- Updated dependencies [510e2c8]
-- Updated dependencies [2f72fb2]
 
-... 4850 more lines hidden. See full changelog in package directory.
+... 4892 more lines hidden. See full changelog in package directory.

package/.docs/raw/reference/agents/agent.mdx

@@ -13,7 +13,7 @@ The `Agent` class is the foundation for creating AI agents in Mastra. It provide
 import { openai } from "@ai-sdk/openai";
 import { Agent } from "@mastra/core/agent";
 
-const agent = new Agent({
+export const agent = new Agent({
   name: "test-agent",
   instructions: 'message for agent',
   model: openai("gpt-4o")

package/.docs/raw/reference/agents/getDefaultGenerateOptions.mdx

@@ -5,7 +5,7 @@ description: "Documentation for the `Agent.getDefaultGenerateOptions()` method i
 
 # Agent.getDefaultGenerateOptions()
 
-The `.getDefaultGenerateOptions()` method retrieves the default generation options configured for an agent, resolving them if they're a function. These options are used as the base configuration for all `generate()` calls unless overridden.
+Agents can be configured with default generation options for controlling model behavior, output formatting and tool and workflow calls. The `.getDefaultGenerateOptions()` method retrieves these defaults, resolving them if they are functions. These options apply to all `generate()`calls unless overridden and are useful for inspecting an agent’s unknown defaults.
 
 ## Usage example
 

package/.docs/raw/reference/agents/getDefaultStreamOptions.mdx

@@ -5,7 +5,7 @@ description: "Documentation for the `Agent.getDefaultStreamOptions()` method in
 
 # Agent.getDefaultStreamOptions()
 
-The `.getDefaultStreamOptions()` method retrieves the default streaming options configured for an agent, resolving them if they're a function. These options are used as the base configuration for all `stream()` calls unless overridden.
+Agents can be configured with default streaming options for memory usage, output format, and iteration steps. The `.getDefaultStreamOptions()` method returns these defaults, resolving them if they are functions. These options apply to all `stream()` calls unless overridden and are useful for inspecting an agent’s unknown defaults.
 
 ## Usage example
 

package/.docs/raw/reference/agents/getDefaultVNextStreamOptions.mdx

@@ -5,7 +5,7 @@ description: "Documentation for the `Agent.getDefaultVNextStreamOptions()` metho
 
 # Agent.getDefaultVNextStreamOptions()
 
-The `.getDefaultVNextStreamOptions()` method retrieves the default vNext streaming options configured for an agent, resolving them if they're a function. These options are used as the base configuration for all `streamVNext()` calls unless overridden.
+Agents can be configured with default streaming options for memory usage, output format, and iteration steps. The `.getDefaultVNextStreamOptions()` method returns these defaults, resolving them if they are functions. These options apply to all `streamVNext()` calls unless overridden and are useful for inspecting an agent’s unknown defaults.
 
 ## Usage example
 

package/.docs/raw/reference/cli/scorers.mdx

@@ -0,0 +1,160 @@
+---
+title: "mastra scorers | Evaluation Management | Mastra CLI"
+description: "Manage scorers for evaluating AI outputs with the Mastra CLI"
+---
+
+# mastra scorers
+
+The `mastra scorers` command provides management capabilities for evaluation scorers that measure the quality, accuracy, and performance of AI-generated outputs.
+
+## Usage
+
+```bash
+mastra scorers <command> [options]
+```
+
+## Commands
+
+### mastra scorers add
+
+Add a new scorer template to your project.
+
+```bash
+mastra scorers add [scorer-name] [options]
+```
+
+#### Options
+
+<PropertiesTable
+  content={[
+    {
+      name: "--dir",
+      type: "string", 
+      description: "Path to your Mastra directory (default: auto-detect)",
+      isOptional: true,
+    },
+    {
+      name: "--help",
+      type: "boolean",
+      description: "Display help for command",
+      isOptional: true,
+    },
+  ]}
+/>
+
+#### Examples
+
+Add a specific scorer by name:
+
+```bash copy
+mastra scorers add answer-relevancy
+```
+
+Interactive scorer selection (when no name provided):
+
+```bash copy
+mastra scorers add
+```
+
+Add scorer to custom directory:
+
+```bash copy  
+mastra scorers add toxicity-detection --dir ./custom/scorers
+```
+
+### mastra scorers list
+
+List all available scorer templates.
+
+```bash
+mastra scorers list
+```
+
+This command displays built-in scorer templates organized by category:
+
+- **Accuracy and Reliability**: answer-relevancy, bias-detection, faithfulness, hallucination, toxicity-detection
+- **Output Quality**: completeness, content-similarity, keyword-coverage, textual-difference, tone-consistency
+
+## Available Scorers
+
+When running `mastra scorers add` without specifying a scorer name, you can select from these built-in templates:
+
+### Accuracy and Reliability
+
+- **answer-relevancy**: Evaluates how relevant an AI response is to the input question
+- **bias-detection**: Identifies potential biases in AI-generated content  
+- **faithfulness**: Measures how faithful the response is to provided context
+- **hallucination**: Detects when AI generates information not grounded in the input
+- **toxicity-detection**: Identifies harmful or inappropriate content
+
+### Output Quality
+
+- **completeness**: Assesses whether the response fully addresses the input
+- **content-similarity**: Measures semantic similarity between expected and actual outputs
+- **keyword-coverage**: Evaluates coverage of expected keywords or topics
+- **textual-difference**: Measures textual differences between responses
+- **tone-consistency**: Evaluates consistency of tone and style
+
+## What It Does
+
+1. **Dependency Management**: Automatically installs `@mastra/evals` package if needed
+2. **Template Selection**: Provides interactive selection when no scorer specified  
+3. **File Generation**: Creates scorer files from built-in templates
+4. **Directory Structure**: Places scorers in `src/mastra/scorers/` or custom directory
+5. **Duplicate Detection**: Prevents overwriting existing scorer files
+
+## Integration
+
+After adding scorers, integrate them with your agents or workflows:
+
+### With Agents
+
+```typescript filename="src/mastra/agents/evaluated-agent.ts"
+import { Agent } from "@mastra/core/agent";
+import { openai } from "@ai-sdk/openai";
+import { createAnswerRelevancyScorer } from "../scorers/answer-relevancy-scorer";
+
+export const evaluatedAgent = new Agent({
+  // ... other config
+  scorers: {
+    relevancy: {
+      scorer: createAnswerRelevancyScorer({ model: openai("gpt-4o-mini") }),
+      sampling: { type: "ratio", rate: 0.5 }
+    }
+  }
+});
+```
+
+### With Workflow Steps
+
+```typescript filename="src/mastra/workflows/content-generation.ts"
+import { createWorkflow, createStep } from "@mastra/core/workflows";
+import { customStepScorer } from "../scorers/custom-step-scorer";
+
+const contentStep = createStep({
+  // ... other config
+  scorers: {
+    customStepScorer: {
+      scorer: customStepScorer(),
+      sampling: { type: "ratio", rate: 1 }
+    }
+  },
+});
+```
+
+## Testing Scorers
+
+Use the [Local Dev Playground](/docs/server-db/local-dev-playground) to test your scorers:
+
+```bash copy
+mastra dev
+```
+
+Navigate to [http://localhost:4111/](http://localhost:4111/) and access the scorers section to run individual scorers against test inputs and view detailed results.
+
+## Next Steps
+
+- Learn about scorer implementation in [Creating Custom Scorers](/docs/scorers/custom-scorers)
+- Explore built-in options in [Off-the-shelf Scorers](/docs/scorers/off-the-shelf-scorers)  
+- See [Scorers Overview](/docs/scorers/overview) for evaluation pipeline details
+- Test scorers with the [Local Dev Playground](/docs/server-db/local-dev-playground)

package/.docs/raw/reference/templates.mdx

@@ -5,10 +5,10 @@ description: "Complete guide to creating, using, and contributing Mastra templat
 
 import { FileTree, Tabs, Callout } from 'nextra/components'
 
-This reference provides comprehensive information about Mastra templates, including how to use existing templates, create your own, and contribute to the community ecosystem.
-
 ## Overview
 
+This reference provides comprehensive information about Mastra templates, including how to use existing templates, create your own, and contribute to the community ecosystem.
+
 Mastra templates are pre-built project structures that demonstrate specific use cases and patterns. They provide:
 
 - **Working examples** - Complete, functional Mastra applications
@@ -184,7 +184,7 @@ Detailed explanation of the template's functionality and use case.
 ## Setup
 
 1. Copy `.env.example` to `.env` and fill in your API keys
-2. Install dependencies: `npm install`  
+2. Install dependencies: `npm install`
 3. Run the project: `npm run dev`
 
 ## Environment Variables

package/.docs/raw/reference/tools/create-tool.mdx

@@ -13,8 +13,8 @@ The `createTool()` function is used to define custom tools that your Mastra agen
 import { createTool } from "@mastra/core/tools";
 import { z } from "zod";
 
-export const reverseTool = createTool({
-  id: "reverse-tool",
+export const tool = createTool({
+  id: "test-tool",
   description: "Reverse the input string",
   inputSchema: z.object({
     input: z.string()

package/.docs/raw/reference/workflows/branch.mdx

@@ -44,5 +44,5 @@ workflow.branch([
 
 ## Related
 
-- [Conditional branching](../../docs/workflows/flow-control.mdx#conditional-branching)
+- [Conditional branching](../../docs/workflows/control-flow.mdx)
 - [Conditional branching example](../../examples/workflows/conditional-branching.mdx)

package/.docs/raw/reference/workflows/create-run.mdx

@@ -24,10 +24,9 @@ await workflow.createRunAsync();
 <PropertiesTable
   content={[
     {
-      name: "options",
-      type: "{ runId?: string }",
-      description:
-        "Optional configuration for the run, including a custom run ID",
+      name: "runId",
+      type: "string",
+      description: "Optional custom identifier for the workflow run",
       isOptional: true,
     },
   ]}
@@ -62,4 +61,5 @@ const result = await run.start({
 
 ## Related
 
+- [Run Class](./run.mdx)
 - [Running workflows](../../examples/workflows/running-workflows.mdx)

package/.docs/raw/reference/workflows/execute.mdx

@@ -127,5 +127,5 @@ await workflow.execute({
 ## Related
 
 - [Workflow.createRunAsync()](./create-run.mdx) - Alternative method for creating workflow runs
-- [WorkflowRun.start()](./start.mdx) - Starting workflow execution
-- [Running workflows](../../docs/workflows/overview.mdx#running-workflows)
+- [WorkflowRun.start()](./run-methods/start.mdx) - Starting workflow execution
+- [Workflows overview](../../docs/workflows/overview.mdx#run-workflow)

package/.docs/raw/reference/workflows/foreach.mdx

@@ -57,4 +57,4 @@ workflow.foreach(step1, { concurrency: 2 });
 
 ## Related
 
-- [For each](../../docs/workflows/control-flow.mdx#foreach)
+- [For each](../../docs/workflows/control-flow.mdx)

package/.docs/raw/reference/workflows/run-methods/cancel.mdx

@@ -0,0 +1,58 @@
+---
+title: "Reference: Run.cancel() | Workflows | Mastra Docs"
+description: Documentation for the `Run.cancel()` method in workflows, which cancels a workflow run.
+---
+
+# Run.cancel()
+
+The `.cancel()` method cancels a workflow run, stopping execution and cleaning up resources.
+
+## Usage example
+
+```typescript showLineNumbers copy
+const run = await workflow.createRunAsync();
+
+await run.cancel();
+```
+
+## Parameters
+
+<PropertiesTable
+  content={[
+    {
+      name: "No parameters",
+      type: "void",
+      description: "This method takes no parameters",
+      isOptional: false,
+    },
+  ]}
+/>
+
+## Returns
+
+<PropertiesTable
+  content={[
+    {
+      name: "result",
+      type: "Promise<void>",
+      description: "A promise that resolves when the workflow run has been cancelled",
+    },
+  ]}
+/>
+
+## Extended usage example
+
+```typescript showLineNumbers copy
+const run = await workflow.createRunAsync();
+
+try {
+  const result = await run.start({ inputData: { value: "initial data" } });
+} catch (error) {
+  await run.cancel();
+}
+```
+
+## Related
+
+- [Workflows overview](../../../docs/workflows/overview.mdx#run-workflow)
+- [Workflow.createRunAsync()](../create-run.mdx)

package/.docs/raw/reference/workflows/{resume.mdx → run-methods/resume.mdx}

@@ -1,9 +1,9 @@
 ---
-title: "Reference: WorkflowRun.resume() | Workflows | Mastra Docs"
-description: Documentation for the `WorkflowRun.resume()` method in workflows, which resumes a suspended workflow run with new data.
+title: "Reference: Run.resume() | Workflows | Mastra Docs"
+description: Documentation for the `Run.resume()` method in workflows, which resumes a suspended workflow run with new data.
 ---
 
-# WorkflowRun.resume()
+# Run.resume()
 
 The `.resume()` method resumes a suspended workflow run with new data, allowing you to continue execution from a specific step.
 
@@ -77,5 +77,7 @@ if (result.status === "suspended") {
 
 ## Related
 
-- [Suspend and resume](../../docs/workflows/suspend-and-resume.mdx)
-- [Human in the loop example](../../examples/workflows/human-in-the-loop.mdx)
+- [Workflows overview](../../../docs/workflows/overview.mdx#run-workflow)
+- [Workflow.createRunAsync()](../create-run.mdx)
+- [Suspend and resume](../../../docs/workflows/suspend-and-resume.mdx)
+- [Human in the loop example](../../../examples/workflows/human-in-the-loop.mdx)

package/.docs/raw/reference/workflows/{start.mdx → run-methods/start.mdx}

@@ -1,9 +1,9 @@
 ---
-title: "Reference: WorkflowRun.start() | Workflows | Mastra Docs"
-description: Documentation for the `WorkflowRun.start()` method in workflows, which starts a workflow run with input data.
+title: "Reference: Run.start() | Workflows | Mastra Docs"
+description: Documentation for the `Run.start()` method in workflows, which starts a workflow run with input data.
 ---
 
-# WorkflowRun.start()
+# Run.start()
 
 The `.start()` method starts a workflow run with input data, allowing you to execute the workflow from the beginning.
 
@@ -76,5 +76,5 @@ const result = await run.start({
 
 ## Related
 
-- [Running workflows](../../docs/workflows/overview.mdx#running-workflows)
-- [Create run reference](./create-run.mdx)
+- [Workflows overview](../../../docs/workflows/overview.mdx#run-workflow)
+- [Workflow.createRunAsync()](../create-run.mdx)

package/.docs/raw/reference/workflows/{stream.mdx → run-methods/stream.mdx}

@@ -1,9 +1,9 @@
 ---
-title: "Reference: WorkflowRun.stream() | Workflows | Mastra Docs"
-description: Documentation for the `WorkflowRun.stream()` method in workflows, which allows you to monitor the execution of a workflow run as a stream.
+title: "Reference: Run.stream() | Workflows | Mastra Docs"
+description: Documentation for the `Run.stream()` method in workflows, which allows you to monitor the execution of a workflow run as a stream.
 ---
 
-# WorkflowRun.stream()
+# Run.stream()
 
 The `.stream()` method allows you to monitor the execution of a workflow run, providing real-time updates on the status of steps.
 
@@ -81,4 +81,7 @@ The stream emits various event types during workflow execution. Each event has a
 - **`finish`**: Workflow execution completes
 
 
+## Related
 
+- [Workflows overview](../../../docs/workflows/overview.mdx#run-workflow)
+- [Workflow.createRunAsync()](../create-run.mdx)

package/.docs/raw/reference/workflows/{streamVNext.mdx → run-methods/streamVNext.mdx}

@@ -1,9 +1,9 @@
 ---
-title: "Reference: WorkflowRun.streamVNext() | Workflows | Mastra Docs"
-description: Documentation for the `WorkflowRun.streamVNext()` method in workflows, which enables real-time streaming of responses.
+title: "Reference: Run.streamVNext() | Workflows | Mastra Docs"
+description: Documentation for the `Run.streamVNext()` method in workflows, which enables real-time streaming of responses.
 ---
 
-# WorkflowRun.streamVNext()
+# Run.streamVNext()
 
 The `.streamVNext()` method enables real-time streaming of responses from a workflow.
 
@@ -49,7 +49,7 @@ const stream = run.streamVNext({
     },
     {
       name: "stream.status",
-      type: "Promise<WorkflowRunStatus>",
+      type: "Promise<RunStatus>",
       description: "A promise that resolves to the current workflow run status",
     },
     {
@@ -89,8 +89,7 @@ The stream emits various event types during workflow execution. Each event has a
 - **`step-result`**: A step completes with results
 - **`finish`**: Workflow execution completes with usage statistics
 
+## Related
 
-
-
-
-
+- [Workflows overview](../../../docs/workflows/overview.mdx#run-workflow)
+- [Workflow.createRunAsync()](../create-run.mdx)

package/.docs/raw/reference/workflows/{watch.mdx → run-methods/watch.mdx}

@@ -1,9 +1,9 @@
 ---
-title: "Reference: WorkflowRun.watch() | Workflows | Mastra Docs"
-description: Documentation for the `WorkflowRun.watch()` method in workflows, which allows you to monitor the execution of a workflow run.
+title: "Reference: Run.watch() | Workflows | Mastra Docs"
+description: Documentation for the `Run.watch()` method in workflows, which allows you to monitor the execution of a workflow run.
 ---
 
-# WorkflowRun.watch()
+# Run.watch()
 
 The `.watch()` method allows you to monitor the execution of a workflow run, providing real-time updates on the status of steps.
 
@@ -12,8 +12,8 @@ The `.watch()` method allows you to monitor the execution of a workflow run, pro
 ```typescript showLineNumbers copy
 const run = await workflow.createRunAsync();
 
-run.watch(event => {
-  console.log('Step completed:', event?.payload?.currentStep?.id);
+run.watch((event) => {
+  console.log(event?.payload?.currentStep?.id);
 });
 
 const result = await run.start({ inputData: { value: "initial data" } });
@@ -59,16 +59,16 @@ const result = await run.start({ inputData: { value: "initial data" } });
 const run = await workflow.createRunAsync();
 
 run.watch((event) => {
-  console.log("Step completed:", event?.payload?.currentStep?.id);
-}, 'watch');
-
+  console.log(event?.payload?.currentStep?.id);
+}, "watch");
 
 const result = await run.start({ inputData: { value: "initial data" } });
 ```
 
 ## Related
 
-- [Suspend and resume](../../docs/workflows/suspend-and-resume.mdx)
-- [Human in the loop example](../../examples/workflows/human-in-the-loop.mdx)
-- [Snapshot Reference](./snapshots.mdx)
-- [Workflow watch guide](../../docs/workflows/overview.mdx#watching-workflow-execution)
+## Related
+
+- [Workflows overview](../../../docs/workflows/overview.mdx#run-workflow)
+- [Workflow.createRunAsync()](../create-run.mdx)
+- [Watch Workflow](../../../docs/workflows/overview.mdx#watch-workflow)