@mastra/mcp-docs-server 1.0.0-beta.9 → 1.0.0

package/.docs/raw/reference/evals/prompt-alignment.mdx

@@ -1,6 +1,8 @@
 ---
 title: "Reference: Prompt Alignment Scorer | Evals"
 description: Documentation for the Prompt Alignment Scorer in Mastra. Evaluates how well agent responses align with user prompt intent, requirements, completeness, and appropriateness using multi-dimensional analysis.
+packages:
+  - "@mastra/evals"
 ---
 
 import PropertiesTable from "@site/src/components/PropertiesTable";
@@ -107,7 +109,7 @@ The `createPromptAlignmentScorerLLM()` function creates a scorer that evaluates
 
 You can customize the Prompt Alignment Scorer by adjusting the scale parameter and evaluation mode to fit your scoring needs.
 
-```typescript showLineNumbers copy
+```typescript
 const scorer = createPromptAlignmentScorerLLM({
   model: "openai/gpt-5.1",
   options: {
@@ -417,7 +419,7 @@ const result = await scorer.run({
 
 In this example, the response fully addresses the user's prompt with all requirements met.
 
-```typescript title="src/example-excellent-prompt-alignment.ts" showLineNumbers copy
+```typescript title="src/example-excellent-prompt-alignment.ts"
 import { createPromptAlignmentScorerLLM } from "@mastra/evals/scorers/prebuilt";
 
 const scorer = createPromptAlignmentScorerLLM({
@@ -465,7 +467,7 @@ The output receives a high score because it perfectly addresses the intent, fulf
 
 In this example, the response addresses the core intent but misses some requirements or has format issues.
 
-```typescript title="src/example-partial-prompt-alignment.ts" showLineNumbers copy
+```typescript title="src/example-partial-prompt-alignment.ts"
 import { createPromptAlignmentScorerLLM } from "@mastra/evals/scorers/prebuilt";
 
 const scorer = createPromptAlignmentScorerLLM({
@@ -506,7 +508,7 @@ The output receives a lower score because while the content is accurate, it does
 
 In this example, the response fails to address the user's specific requirements.
 
-```typescript title="src/example-poor-prompt-alignment.ts" showLineNumbers copy
+```typescript title="src/example-poor-prompt-alignment.ts"
 import { createPromptAlignmentScorerLLM } from "@mastra/evals/scorers/prebuilt";
 
 const scorer = createPromptAlignmentScorerLLM({
@@ -552,7 +554,7 @@ The output receives a low score because it only partially fulfills the requireme
 
 Evaluates how well the response addresses the user's request, ignoring system instructions:
 
-```typescript title="src/example-user-mode.ts" showLineNumbers copy
+```typescript title="src/example-user-mode.ts"
 const scorer = createPromptAlignmentScorerLLM({
   model: "openai/gpt-5.1",
   options: { evaluationMode: "user" },
@@ -584,7 +586,7 @@ const result = await scorer.run({
 
 Evaluates compliance with system behavioral guidelines and constraints:
 
-```typescript title="src/example-system-mode.ts" showLineNumbers copy
+```typescript title="src/example-system-mode.ts"
 const scorer = createPromptAlignmentScorerLLM({
   model: "openai/gpt-5.1",
   options: { evaluationMode: "system" },
@@ -617,7 +619,7 @@ const result = await scorer.run({
 
 Evaluates both user intent fulfillment and system compliance with weighted scoring (70% user, 30% system):
 
-```typescript title="src/example-both-mode.ts" showLineNumbers copy
+```typescript title="src/example-both-mode.ts"
 const scorer = createPromptAlignmentScorerLLM({
   model: "openai/gpt-5.1",
   options: { evaluationMode: "both" }, // This is the default

package/.docs/raw/reference/evals/run-evals.mdx

@@ -1,6 +1,8 @@
 ---
 title: "Reference: runEvals | Evals"
 description: "Documentation for the runEvals function in Mastra, which enables batch evaluation of agents and workflows using multiple scorers."
+packages:
+  - "@mastra/core"
 ---
 
 # runEvals
@@ -160,7 +162,7 @@ For workflows, you can specify scorers at different levels using `WorkflowScorer
 import { createScorer, runEvals } from "@mastra/core/evals";
 
 const myScorer = createScorer({
-  name: "My Scorer",
+  id: "my-scorer",
   description: "Check if Agent's response contains ground truth",
   type: "agent",
 }).generateScore(({ run }) => {

package/.docs/raw/reference/evals/scorer-utils.mdx

@@ -1,6 +1,9 @@
 ---
 title: "Reference: Scorer Utils | Evals"
 description: Utility functions for extracting data from scorer run inputs and outputs, including text content, reasoning, system messages, and tool calls.
+packages:
+  - "@mastra/core"
+  - "@mastra/evals"
 ---
 
 # Scorer Utils

package/.docs/raw/reference/evals/textual-difference.mdx

@@ -1,6 +1,9 @@
 ---
 title: "Reference: Textual Difference Scorer | Evals"
 description: Documentation for the Textual Difference Scorer in Mastra, which measures textual differences between strings using sequence matching.
+packages:
+  - "@mastra/core"
+  - "@mastra/evals"
 ---
 
 # Textual Difference Scorer
@@ -87,7 +90,7 @@ A textual difference score between 0 and 1:
 
 Measure textual differences between expected and actual agent outputs:
 
-```typescript title="src/example-textual-difference.ts" showLineNumbers copy
+```typescript title="src/example-textual-difference.ts"
 import { runEvals } from "@mastra/core/evals";
 import { createTextualDifferenceScorer } from "@mastra/evals/scorers/prebuilt";
 import { myAgent } from "./agent";

package/.docs/raw/reference/evals/tone-consistency.mdx

@@ -1,6 +1,9 @@
 ---
 title: "Reference: Tone Consistency Scorer | Evals"
 description: Documentation for the Tone Consistency Scorer in Mastra, which evaluates emotional tone and sentiment consistency in text.
+packages:
+  - "@mastra/core"
+  - "@mastra/evals"
 ---
 
 # Tone Consistency Scorer
@@ -98,7 +101,7 @@ Object with tone metrics:
 
 Evaluate tone consistency between related agent responses:
 
-```typescript title="src/example-tone-consistency.ts" showLineNumbers copy
+```typescript title="src/example-tone-consistency.ts"
 import { runEvals } from "@mastra/core/evals";
 import { createToneScorer } from "@mastra/evals/scorers/prebuilt";
 import { myAgent } from "./agent";

package/.docs/raw/reference/evals/tool-call-accuracy.mdx

@@ -1,6 +1,8 @@
 ---
 title: "Reference: Tool Call Accuracy Scorers | Evals"
 description: Documentation for the Tool Call Accuracy Scorers in Mastra, which evaluate whether LLM outputs call the correct tools from available options.
+packages:
+  - "@mastra/evals"
 ---
 
 # Tool Call Accuracy Scorers
@@ -89,7 +91,7 @@ When `expectedToolOrder` is provided, the scorer validates tool calling sequence
 
 ### Code-Based Scorer Options
 
-```typescript showLineNumbers copy
+```typescript
 // Standard mode - passes if expected tool is called
 const lenientScorer = createCodeScorer({
   expectedTool: "search-tool",
@@ -135,14 +137,14 @@ The code-based scorer provides deterministic, binary scoring (0 or 1) based on e
 
 ### Correct tool selection
 
-```typescript title="src/example-correct-tool.ts" showLineNumbers copy
+```typescript title="src/example-correct-tool.ts"
 const scorer = createToolCallAccuracyScorerCode({
   expectedTool: "weather-tool",
 });
 
 // Simulate LLM input and output with tool call
 const inputMessages = [
-  createUIMessage({
+  createTestMessage({
     content: "What is the weather like in New York today?",
     role: "user",
     id: "input-1",
@@ -150,7 +152,7 @@ const inputMessages = [
 ];
 
 const output = [
-  createUIMessage({
+  createTestMessage({
     content: "Let me check the weather for you.",
     role: "assistant",
     id: "output-1",
@@ -177,7 +179,7 @@ console.log(result.preprocessStepResult?.correctToolCalled); // true
 
 Only passes if exactly one tool is called:
 
-```typescript title="src/example-strict-mode.ts" showLineNumbers copy
+```typescript title="src/example-strict-mode.ts"
 const strictScorer = createToolCallAccuracyScorerCode({
   expectedTool: "weather-tool",
   strictMode: true,
@@ -185,7 +187,7 @@ const strictScorer = createToolCallAccuracyScorerCode({
 
 // Multiple tools called - fails in strict mode
 const output = [
-  createUIMessage({
+  createTestMessage({
     content: "Let me help you with that.",
     role: "assistant",
     id: "output-1",
@@ -216,7 +218,7 @@ console.log(result.score); // 0 - fails because multiple tools were called
 
 Validates that tools are called in a specific sequence:
 
-```typescript title="src/example-order-validation.ts" showLineNumbers copy
+```typescript title="src/example-order-validation.ts"
 const orderScorer = createToolCallAccuracyScorerCode({
   expectedTool: "auth-tool", // ignored when order is specified
   expectedToolOrder: ["auth-tool", "fetch-tool"],
@@ -224,7 +226,7 @@ const orderScorer = createToolCallAccuracyScorerCode({
 });
 
 const output = [
-  createUIMessage({
+  createTestMessage({
     content: "I will authenticate and fetch the data.",
     role: "assistant",
     id: "output-1",
@@ -255,7 +257,7 @@ console.log(result.score); // 1 - correct order
 
 Allows extra tools as long as expected tools maintain relative order:
 
-```typescript title="src/example-flexible-order.ts" showLineNumbers copy
+```typescript title="src/example-flexible-order.ts"
 const flexibleOrderScorer = createToolCallAccuracyScorerCode({
   expectedTool: "auth-tool",
   expectedToolOrder: ["auth-tool", "fetch-tool"],
@@ -263,7 +265,7 @@ const flexibleOrderScorer = createToolCallAccuracyScorerCode({
 });
 
 const output = [
-  createUIMessage({
+  createTestMessage({
     content: "Performing comprehensive operation.",
     role: "assistant",
     id: "output-1",
@@ -346,7 +348,7 @@ The LLM-based scorer provides:
 
 ### LLM-Based Scorer Options
 
-```typescript showLineNumbers copy
+```typescript
 // Basic configuration
 const basicLLMScorer = createLLMScorer({
   model: 'openai/gpt-5.1',
@@ -387,7 +389,7 @@ The LLM-based scorer uses AI to evaluate whether tool selections are appropriate
 
 ### Basic LLM evaluation
 
-```typescript title="src/example-llm-basic.ts" showLineNumbers copy
+```typescript title="src/example-llm-basic.ts"
 const llmScorer = createToolCallAccuracyScorerLLM({
   model: "openai/gpt-5.1",
   availableTools: [
@@ -407,7 +409,7 @@ const llmScorer = createToolCallAccuracyScorerLLM({
 });
 
 const inputMessages = [
-  createUIMessage({
+  createTestMessage({
     content: "What is the weather like in San Francisco today?",
     role: "user",
     id: "input-1",
@@ -415,7 +417,7 @@ const inputMessages = [
 ];
 
 const output = [
-  createUIMessage({
+  createTestMessage({
     content: "Let me check the current weather for you.",
     role: "assistant",
     id: "output-1",
@@ -440,9 +442,9 @@ console.log(result.reason); // "The agent correctly used the weather-tool to add
 
 ### Handling inappropriate tool usage
 
-```typescript title="src/example-llm-inappropriate.ts" showLineNumbers copy
+```typescript title="src/example-llm-inappropriate.ts"
 const inputMessages = [
-  createUIMessage({
+  createTestMessage({
     content: "What is the weather in Tokyo?",
     role: "user",
     id: "input-1",
@@ -450,7 +452,7 @@ const inputMessages = [
 ];
 
 const inappropriateOutput = [
-  createUIMessage({
+  createTestMessage({
     content: "Let me search for that information.",
     role: "assistant",
     id: "output-1",
@@ -477,9 +479,9 @@ console.log(result.reason); // "The agent used search-tool when weather-tool wou
 
 The LLM scorer recognizes when agents appropriately ask for clarification:
 
-```typescript title="src/example-llm-clarification.ts" showLineNumbers copy
+```typescript title="src/example-llm-clarification.ts"
 const vagueInput = [
-  createUIMessage({
+  createTestMessage({
     content: 'I need help with something',
     role: 'user',
     id: 'input-1'
@@ -487,7 +489,7 @@ const vagueInput = [
 ];
 
 const clarificationOutput = [
-  createUIMessage({
+  createTestMessage({
     content: 'I'd be happy to help! Could you please provide more details about what you need assistance with?',
     role: 'assistant',
     id: 'output-1',
@@ -509,7 +511,7 @@ console.log(result.reason); // "The agent appropriately asked for clarification
 
 Here's an example using both scorers on the same data:
 
-```typescript title="src/example-comparison.ts" showLineNumbers copy
+```typescript title="src/example-comparison.ts"
 import {
   createToolCallAccuracyScorerCode as createCodeScorer,
   createToolCallAccuracyScorerLLM as createLLMScorer
@@ -532,14 +534,14 @@ const llmScorer = createLLMScorer({
 // Test data
 const run = createAgentTestRun({
   inputMessages: [
-    createUIMessage({
+    createTestMessage({
       content: "What is the weather?",
       role: "user",
       id: "input-1",
     }),
   ],
   output: [
-    createUIMessage({
+    createTestMessage({
       content: "Let me find that information.",
       role: "assistant",
       id: "output-1",

package/.docs/raw/reference/evals/toxicity.mdx

@@ -1,6 +1,9 @@
 ---
 title: "Reference: Toxicity Scorer | Evals"
 description: Documentation for the Toxicity Scorer in Mastra, which evaluates LLM outputs for racist, biased, or toxic elements.
+packages:
+  - "@mastra/core"
+  - "@mastra/evals"
 ---
 
 # Toxicity Scorer
@@ -123,7 +126,7 @@ A toxicity score between 0 and 1:
 
 Evaluate agent responses for toxic, biased, or harmful content:
 
-```typescript title="src/example-toxicity.ts" showLineNumbers copy
+```typescript title="src/example-toxicity.ts"
 import { runEvals } from "@mastra/core/evals";
 import { createToxicityScorer } from "@mastra/evals/scorers/prebuilt";
 import { myAgent } from "./agent";

package/.docs/raw/reference/index.mdx

@@ -1,7 +1,8 @@
 ---
 title: "Reference: Overview"
 description: "Reference documentation on Mastra's APIs and tools"
-showCopyButton: false
+packages:
+  - "@mastra/core"
 ---
 
 import { ReferenceCards } from "@site/src/components/ReferenceCards";

package/.docs/raw/reference/logging/pino-logger.mdx

@@ -1,22 +1,24 @@
 ---
 title: "Reference: PinoLogger | Observability"
 description: Documentation for PinoLogger, which provides methods to record events at various severity levels.
+packages:
+  - "@mastra/core"
+  - "@mastra/loggers"
 ---
 
 # PinoLogger
 
 A Logger instance is created using `new PinoLogger()` and provides methods to record events at various severity levels.
 
-When deploying to Mastra Cloud, logs are displayed on the [Logs](/docs/v1/deployment/mastra-cloud/dashboard#logs) page. In self-hosted or custom environments, logs can be directed to files or external services depending on the configured transports.
+When deploying to Mastra Cloud, logs are displayed on the [Logs](/docs/v1/mastra-cloud/observability#logs) page. In self-hosted or custom environments, logs can be directed to files or external services depending on the configured transports.
 
 ## Usage example
 
-```typescript title="src/mastra/index.ts" showLineNumbers copy
+```typescript title="src/mastra/index.ts"
 import { Mastra } from "@mastra/core";
 import { PinoLogger } from "@mastra/loggers";
 
 export const mastra = new Mastra({
-  // ...
   logger: new PinoLogger({
     name: "Mastra",
     level: "info",
@@ -63,7 +65,7 @@ export const mastra = new Mastra({
 
 Writes structured logs to a file using the `FileTransport`. The logger accepts a plain message as the first argument and structured metadata as the second argument. These are internally converted to a `BaseLogMessage` and persisted to the configured file path.
 
-```typescript title="src/mastra/loggers/file-transport.ts" showLineNumbers copy
+```typescript title="src/mastra/loggers/file-transport.ts"
 import { FileTransport } from "@mastra/loggers/file";
 import { PinoLogger } from "@mastra/loggers/pino";
 
@@ -76,7 +78,7 @@ export const fileLogger = new PinoLogger({
 
 ### File transport usage
 
-```typescript showLineNumbers copy
+```typescript
 fileLogger.warn("Low disk space", {
   destinationPath: "system",
   type: "WORKFLOW",
@@ -87,7 +89,7 @@ fileLogger.warn("Low disk space", {
 
 Streams structured logs to a remote Redis list using the `UpstashTransport`. The logger accepts a string message and a structured metadata object. This enables centralized logging for distributed environments, supporting filtering by `destinationPath`, `type`, and `runId`.
 
-```typescript title="src/mastra/loggers/upstash-transport.ts" showLineNumbers copy
+```typescript title="src/mastra/loggers/upstash-transport.ts"
 import { UpstashTransport } from "@mastra/loggers/upstash";
 import { PinoLogger } from "@mastra/loggers/pino";
 
@@ -106,7 +108,7 @@ export const upstashLogger = new PinoLogger({
 
 ### Upstash transport usage
 
-```typescript showLineNumbers copy
+```typescript
 upstashLogger.info("User signed in", {
   destinationPath: "auth",
   type: "AGENT",
@@ -122,7 +124,7 @@ You can create custom transports using the `createCustomTransport` utility to in
 
 Creates a custom transport using `createCustomTransport` and integrates it with a third-party logging stream such as `pino-sentry-transport`. This allows forwarding logs to an external system like Sentry for advanced monitoring and observability.
 
-```typescript title="src/mastra/loggers/sentry-transport.ts" showLineNumbers copy
+```typescript title="src/mastra/loggers/sentry-transport.ts"
 import { createCustomTransport } from "@mastra/core/loggers";
 import { PinoLogger } from "@mastra/loggers/pino";
 import pinoSentry from "pino-sentry-transport";