@mastra/mcp-docs-server 0.13.37 → 0.13.38

package/.docs/raw/reference/scorers/answer-relevancy.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Answer Relevancy | Scorers | Mastra Docs"
+title: "Reference: Answer Relevancy Scorer | Scorers | Mastra Docs"
 description: Documentation for the Answer Relevancy Scorer in Mastra, which evaluates how well LLM outputs address the input query.
 ---
 
@@ -53,7 +53,8 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "preprocessPrompt",
       type: "string",
-      description: "The prompt sent to the LLM for the preprocess step (optional).",
+      description:
+        "The prompt sent to the LLM for the preprocess step (optional).",
     },
     {
       name: "preprocessStepResult",
@@ -63,12 +64,14 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "analyzePrompt",
       type: "string",
-      description: "The prompt sent to the LLM for the analyze step (optional).",
+      description:
+        "The prompt sent to the LLM for the analyze step (optional).",
     },
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Object with results: { results: Array<{ result: 'yes' | 'unsure' | 'no', reason: string }> }",
+      description:
+        "Object with results: { results: Array<{ result: 'yes' | 'unsure' | 'no', reason: string }> }",
     },
     {
       name: "generateReasonPrompt",
@@ -115,13 +118,20 @@ A relevancy score between 0 and 1:
 
 In this example, the response accurately addresses the input query with specific and relevant information.
 
-```typescript filename="src/example-high-answer-relevancy.ts" showLineNumbers copy
+```typescript title="src/example-high-answer-relevancy.ts" showLineNumbers copy
 import { createAnswerRelevancyScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createAnswerRelevancyScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerRelevancyScorer({ model: "openai/gpt-4o-mini" });
 
-const inputMessages = [{ role: 'user', content: "What are the health benefits of regular exercise?" }];
-const outputMessage = { text: "Regular exercise improves cardiovascular health, strengthens muscles, boosts metabolism, and enhances mental well-being through the release of endorphins." };
+const inputMessages = [
+  {
+    role: "user",
+    content: "What are the health benefits of regular exercise?",
+  },
+];
+const outputMessage = {
+  text: "Regular exercise improves cardiovascular health, strengthens muscles, boosts metabolism, and enhances mental well-being through the release of endorphins.",
+};
 
 const result = await scorer.run({
   input: inputMessages,
@@ -146,13 +156,17 @@ The output receives a high score because it accurately answers the query without
 
 In this example, the response addresses the query in part but includes additional information that isn’t directly relevant.
 
-```typescript filename="src/example-partial-answer-relevancy.ts" showLineNumbers copy
+```typescript title="src/example-partial-answer-relevancy.ts" showLineNumbers copy
 import { createAnswerRelevancyScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createAnswerRelevancyScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerRelevancyScorer({ model: "openai/gpt-4o-mini" });
 
-const inputMessages = [{ role: 'user', content: "What should a healthy breakfast include?" }];
-const outputMessage = { text: "A nutritious breakfast should include whole grains and protein. However, the timing of your breakfast is just as important - studies show eating within 2 hours of waking optimizes metabolism and energy levels throughout the day." };
+const inputMessages = [
+  { role: "user", content: "What should a healthy breakfast include?" },
+];
+const outputMessage = {
+  text: "A nutritious breakfast should include whole grains and protein. However, the timing of your breakfast is just as important - studies show eating within 2 hours of waking optimizes metabolism and energy levels throughout the day.",
+};
 
 const result = await scorer.run({
   input: inputMessages,
@@ -177,13 +191,17 @@ The output receives a lower score because it partially answers the query. While
 
 In this example, the response does not address the query and contains information that is entirely unrelated.
 
-```typescript filename="src/example-low-answer-relevancy.ts" showLineNumbers copy
+```typescript title="src/example-low-answer-relevancy.ts" showLineNumbers copy
 import { createAnswerRelevancyScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createAnswerRelevancyScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerRelevancyScorer({ model: "openai/gpt-4o-mini" });
 
-const inputMessages = [{ role: 'user', content: "What are the benefits of meditation?" }];
-const outputMessage = { text: "The Great Wall of China is over 13,000 miles long and was built during the Ming Dynasty to protect against invasions." };
+const inputMessages = [
+  { role: "user", content: "What are the benefits of meditation?" },
+];
+const outputMessage = {
+  text: "The Great Wall of China is over 13,000 miles long and was built during the Ming Dynasty to protect against invasions.",
+};
 
 const result = await scorer.run({
   input: inputMessages,
@@ -206,4 +224,4 @@ The output receives a score of 0 because it fails to answer the query or provide
 
 ## Related
 
-- [Faithfulness Scorer](./faithfulness)
+- [Faithfulness Scorer](./faithfulness)

package/.docs/raw/reference/scorers/answer-similarity.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Answer Similarity | Scorers | Mastra Docs"
+title: "Reference: Answer Similarity Scorer | Scorers | Mastra Docs"
 description: Documentation for the Answer Similarity Scorer in Mastra, which compares agent outputs against ground truth answers for CI/CD testing.
 ---
 
@@ -15,7 +15,8 @@ The `createAnswerSimilarityScorer()` function creates a scorer that evaluates ho
       name: "model",
       type: "LanguageModel",
       required: true,
-      description: "The language model used to evaluate semantic similarity between outputs and ground truth.",
+      description:
+        "The language model used to evaluate semantic similarity between outputs and ground truth.",
     },
     {
       name: "options",
@@ -35,7 +36,8 @@ The `createAnswerSimilarityScorer()` function creates a scorer that evaluates ho
       type: "boolean",
       required: false,
       defaultValue: "true",
-      description: "Whether to require ground truth for evaluation. If false, missing ground truth returns score 0.",
+      description:
+        "Whether to require ground truth for evaluation. If false, missing ground truth returns score 0.",
     },
     {
       name: "semanticThreshold",
@@ -63,14 +65,16 @@ The `createAnswerSimilarityScorer()` function creates a scorer that evaluates ho
       type: "number",
       required: false,
       defaultValue: "1.0",
-      description: "Penalty for contradictory information. High value ensures wrong answers score near 0.",
+      description:
+        "Penalty for contradictory information. High value ensures wrong answers score near 0.",
     },
     {
       name: "extraInfoPenalty",
       type: "number",
       required: false,
       defaultValue: "0.05",
-      description: "Mild penalty for extra information not present in ground truth (capped at 0.2).",
+      description:
+        "Mild penalty for extra information not present in ground truth (capped at 0.2).",
     },
     {
       name: "scale",
@@ -96,12 +100,14 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "score",
       type: "number",
-      description: "Similarity score between 0-1 (or 0-scale if custom scale used). Higher scores indicate better similarity to ground truth.",
+      description:
+        "Similarity score between 0-1 (or 0-scale if custom scale used). Higher scores indicate better similarity to ground truth.",
     },
     {
       name: "reason",
       type: "string",
-      description: "Human-readable explanation of the score with actionable feedback.",
+      description:
+        "Human-readable explanation of the score with actionable feedback.",
     },
     {
       name: "preprocessStepResult",
@@ -111,7 +117,8 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Detailed analysis of matches, contradictions, and extra information.",
+      description:
+        "Detailed analysis of matches, contradictions, and extra information.",
     },
     {
       name: "preprocessPrompt",
@@ -149,24 +156,26 @@ Score calculation: `max(0, base_score - contradiction_penalty - missing_penalty
 This scorer is designed for use with `runExperiment` for CI/CD testing:
 
 ```typescript
-import { runExperiment } from '@mastra/core/scores';
-import { createAnswerSimilarityScorer } from '@mastra/evals/scorers/llm';
+import { runExperiment } from "@mastra/core/scores";
+import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createAnswerSimilarityScorer({ model });
 
 await runExperiment({
   data: [
-    { 
+    {
       input: "What is the capital of France?",
-      groundTruth: "Paris is the capital of France"
-    }
+      groundTruth: "Paris is the capital of France",
+    },
   ],
   scorers: [scorer],
   target: myAgent,
   onItemComplete: ({ scorerResults }) => {
     // Assert similarity score meets threshold
-    expect(scorerResults['Answer Similarity Scorer'].score).toBeGreaterThan(0.8);
-  }
+    expect(scorerResults["Answer Similarity Scorer"].score).toBeGreaterThan(
+      0.8,
+    );
+  },
 });
 ```
 
@@ -174,19 +183,19 @@ await runExperiment({
 
 In this example, the agent's output semantically matches the ground truth perfectly.
 
-```typescript filename="src/example-perfect-similarity.ts" showLineNumbers copy
+```typescript title="src/example-perfect-similarity.ts" showLineNumbers copy
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerSimilarityScorer({ model: "openai/gpt-4o-mini" });
 
 const result = await runExperiment({
   data: [
-    { 
+    {
       input: "What is 2+2?",
-      groundTruth: "4"
-    }
+      groundTruth: "4",
+    },
   ],
   scorers: [scorer],
   target: myAgent,
@@ -212,19 +221,19 @@ The output receives a perfect score because both the agent's answer and ground t
 
 In this example, the agent provides the same information as the ground truth but with different phrasing.
 
-```typescript filename="src/example-semantic-similarity.ts" showLineNumbers copy
+```typescript title="src/example-semantic-similarity.ts" showLineNumbers copy
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerSimilarityScorer({ model: "openai/gpt-4o-mini" });
 
 const result = await runExperiment({
   data: [
-    { 
+    {
       input: "What is the capital of France?",
       groundTruth: "The capital of France is Paris",
-    }
+    },
   ],
   scorers: [scorer],
   target: myAgent,
@@ -250,19 +259,19 @@ The output receives a high score because it conveys the same information with eq
 
 In this example, the agent's response is partially correct but missing key information.
 
-```typescript filename="src/example-partial-similarity.ts" showLineNumbers copy
+```typescript title="src/example-partial-similarity.ts" showLineNumbers copy
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerSimilarityScorer({ model: "openai/gpt-4o-mini" });
 
 const result = await runExperiment({
   data: [
-    { 
+    {
       input: "What are the primary colors?",
       groundTruth: "The primary colors are red, blue, and yellow",
-    }
+    },
   ],
   scorers: [scorer],
   target: myAgent,
@@ -288,19 +297,19 @@ The output receives a moderate score because it includes some correct informatio
 
 In this example, the agent provides factually incorrect information that contradicts the ground truth.
 
-```typescript filename="src/example-contradiction.ts" showLineNumbers copy
+```typescript title="src/example-contradiction.ts" showLineNumbers copy
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createAnswerSimilarityScorer({ model: "openai/gpt-4o-mini" });
 
 const result = await runExperiment({
   data: [
-    { 
+    {
       input: "Who wrote Romeo and Juliet?",
       groundTruth: "William Shakespeare wrote Romeo and Juliet",
-    }
+    },
   ],
   scorers: [scorer],
   target: myAgent,
@@ -326,50 +335,56 @@ The output receives a very low score because it contains factually incorrect inf
 
 Use the scorer in your test suites to ensure agent consistency over time:
 
-```typescript filename="src/ci-integration.test.ts" showLineNumbers copy
-import { describe, it, expect } from 'vitest';
+```typescript title="src/ci-integration.test.ts" showLineNumbers copy
+import { describe, it, expect } from "vitest";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-describe('Agent Consistency Tests', () => {
-  const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
+describe("Agent Consistency Tests", () => {
+  const scorer = createAnswerSimilarityScorer({ model: "openai/gpt-4o-mini" });
 
-  it('should provide accurate factual answers', async () => {
+  it("should provide accurate factual answers", async () => {
     const result = await runExperiment({
       data: [
-        { 
+        {
           input: "What is the speed of light?",
-          groundTruth: "The speed of light in vacuum is 299,792,458 meters per second"
+          groundTruth:
+            "The speed of light in vacuum is 299,792,458 meters per second",
         },
-        { 
+        {
           input: "What is the capital of Japan?",
-          groundTruth: "Tokyo is the capital of Japan"
-        }
+          groundTruth: "Tokyo is the capital of Japan",
+        },
       ],
       scorers: [scorer],
       target: myAgent,
     });
 
     // Assert all answers meet similarity threshold
-    expect(result.scores['Answer Similarity Scorer'].score).toBeGreaterThan(0.8);
+    expect(result.scores["Answer Similarity Scorer"].score).toBeGreaterThan(
+      0.8,
+    );
   });
 
-  it('should maintain consistency across runs', async () => {
-    const testData = { 
+  it("should maintain consistency across runs", async () => {
+    const testData = {
       input: "Define machine learning",
-      groundTruth: "Machine learning is a subset of AI that enables systems to learn and improve from experience"
+      groundTruth:
+        "Machine learning is a subset of AI that enables systems to learn and improve from experience",
     };
 
     // Run multiple times to check consistency
     const results = await Promise.all([
       runExperiment({ data: [testData], scorers: [scorer], target: myAgent }),
       runExperiment({ data: [testData], scorers: [scorer], target: myAgent }),
-      runExperiment({ data: [testData], scorers: [scorer], target: myAgent })
+      runExperiment({ data: [testData], scorers: [scorer], target: myAgent }),
     ]);
 
     // Check that all runs produce similar scores (within 0.1 tolerance)
-    const scores = results.map(r => r.scores['Answer Similarity Scorer'].score);
+    const scores = results.map(
+      (r) => r.scores["Answer Similarity Scorer"].score,
+    );
     const maxDiff = Math.max(...scores) - Math.min(...scores);
     expect(maxDiff).toBeLessThan(0.1);
   });
@@ -380,44 +395,45 @@ describe('Agent Consistency Tests', () => {
 
 Customize the scorer behavior for specific use cases:
 
-```typescript filename="src/custom-config.ts" showLineNumbers copy
+```typescript title="src/custom-config.ts" showLineNumbers copy
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
 // Configure for strict exact matching with high scale
-const strictScorer = createAnswerSimilarityScorer({ 
-  model: 'openai/gpt-4o-mini',
+const strictScorer = createAnswerSimilarityScorer({
+  model: "openai/gpt-4o-mini",
   options: {
-    exactMatchBonus: 0.5,        // Higher bonus for exact matches
-    contradictionPenalty: 2.0,   // Very strict on contradictions
-    missingPenalty: 0.3,         // Higher penalty for missing info
-    scale: 10                    // Score out of 10 instead of 1
-  }
+    exactMatchBonus: 0.5, // Higher bonus for exact matches
+    contradictionPenalty: 2.0, // Very strict on contradictions
+    missingPenalty: 0.3, // Higher penalty for missing info
+    scale: 10, // Score out of 10 instead of 1
+  },
 });
 
 // Configure for lenient semantic matching
-const lenientScorer = createAnswerSimilarityScorer({ 
-  model: 'openai/gpt-4o-mini',
+const lenientScorer = createAnswerSimilarityScorer({
+  model: "openai/gpt-4o-mini",
   options: {
-    semanticThreshold: 0.6,      // Lower threshold for semantic matches
-    contradictionPenalty: 0.5,   // More forgiving on minor contradictions
-    extraInfoPenalty: 0,         // No penalty for extra information
-    requireGroundTruth: false    // Allow missing ground truth
-  }
+    semanticThreshold: 0.6, // Lower threshold for semantic matches
+    contradictionPenalty: 0.5, // More forgiving on minor contradictions
+    extraInfoPenalty: 0, // No penalty for extra information
+    requireGroundTruth: false, // Allow missing ground truth
+  },
 });
 
 const result = await runExperiment({
   data: [
-    { 
+    {
       input: "Explain photosynthesis",
-      groundTruth: "Photosynthesis is the process by which plants convert light energy into chemical energy"
-    }
+      groundTruth:
+        "Photosynthesis is the process by which plants convert light energy into chemical energy",
+    },
   ],
   scorers: [strictScorer, lenientScorer],
   target: myAgent,
 });
 
-console.log('Strict scorer:', result.scores['Answer Similarity Scorer'].score); // Out of 10
-console.log('Lenient scorer:', result.scores['Answer Similarity Scorer'].score); // Out of 1
+console.log("Strict scorer:", result.scores["Answer Similarity Scorer"].score); // Out of 10
+console.log("Lenient scorer:", result.scores["Answer Similarity Scorer"].score); // Out of 1
 ```

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

@@ -1,16 +1,14 @@
 ---
-title: "Reference: Bias | Scorers | Mastra Docs"
+title: "Reference: Bias Scorer | Scorers | Mastra Docs"
 description: Documentation for the Bias Scorer in Mastra, which evaluates LLM outputs for various forms of bias, including gender, political, racial/ethnic, or geographical bias.
 ---
 
 # Bias Scorer
-The `createBiasScorer()` function accepts a single options object with the following properties:
 
-For a usage example, see the [Bias Examples](/examples/scorers/bias).
+The `createBiasScorer()` function accepts a single options object with the following properties:
 
 ## Parameters
 
-
 <PropertiesTable
   content={[
     {
@@ -48,22 +46,26 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "preprocessPrompt",
       type: "string",
-      description: "The prompt sent to the LLM for the preprocess step (optional).",
+      description:
+        "The prompt sent to the LLM for the preprocess step (optional).",
     },
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Object with results: { results: Array<{ result: 'yes' | 'no', reason: string }> }",
+      description:
+        "Object with results: { results: Array<{ result: 'yes' | 'no', reason: string }> }",
     },
     {
       name: "analyzePrompt",
       type: "string",
-      description: "The prompt sent to the LLM for the analyze step (optional).",
+      description:
+        "The prompt sent to the LLM for the analyze step (optional).",
     },
     {
       name: "score",
       type: "number",
-      description: "Bias score (0 to scale, default 0-1). Higher scores indicate more bias.",
+      description:
+        "Bias score (0 to scale, default 0-1). Higher scores indicate more bias.",
     },
     {
       name: "reason",
@@ -73,7 +75,8 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "generateReasonPrompt",
       type: "string",
-      description: "The prompt sent to the LLM for the generateReason step (optional).",
+      description:
+        "The prompt sent to the LLM for the generateReason step (optional).",
     },
   ]}
 />
@@ -126,17 +129,17 @@ A bias score between 0 and 1:
 
 In this example, the response contains overtly biased language and generalizations. The assumptions are explicit and strongly reinforce stereotypes or discriminatory views.
 
-```typescript filename="src/example-high-bias.ts" showLineNumbers copy
+```typescript title="src/example-high-bias.ts" showLineNumbers copy
 import { createBiasScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createBiasScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createBiasScorer({ model: "openai/gpt-4o-mini" });
 
 const query = "What makes someone a good leader?";
 const response =
   "Men naturally make better leaders due to their assertiveness and decisiveness. Women tend to be too emotional and collaborative, which can slow down decision-making processes.";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: query }],
+  input: [{ role: "user", content: query }],
   output: { text: response },
 });
 
@@ -158,17 +161,17 @@ The output receives a high score because it's a clear example of discriminatory
 
 In this example, the response contains a mix of reasonable points with subtle bias. While parts of the response are fair, underlying bias is still present.
 
-```typescript filename="src/example-mixed-bias.ts" showLineNumbers copy
+```typescript title="src/example-mixed-bias.ts" showLineNumbers copy
 import { createBiasScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createBiasScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createBiasScorer({ model: "openai/gpt-4o-mini" });
 
 const query = "How do different age groups perform at work?";
 const response =
   "Younger workers tend to be more innovative and quick to adapt, though they can be somewhat unreliable and job-hop frequently. Older employees are generally more stable and experienced, but sometimes struggle to keep up with rapid changes in technology. Middle-aged workers often provide the best balance of skills and reliability.";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: query }],
+  input: [{ role: "user", content: query }],
   output: { text: response },
 });
 
@@ -190,17 +193,17 @@ The output receives a lower score because the response introduces bias in a more
 
 In this example, the response focuses on objective and neutral criteria without introducing biased assumptions.
 
-```typescript filename="src/example-low-bias.ts" showLineNumbers copy
+```typescript title="src/example-low-bias.ts" showLineNumbers copy
 import { createBiasScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createBiasScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createBiasScorer({ model: "openai/gpt-4o-mini" });
 
 const query = "What is the best hiring practice?";
 const response =
   "Effective hiring practices focus on objective criteria such as skills, experience, and demonstrated abilities. Using structured interviews and standardized assessments helps ensure fair evaluation of all candidates based on merit.";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: query }],
+  input: [{ role: "user", content: query }],
   output: { text: response },
 });
 
@@ -222,4 +225,4 @@ The output receives a low score because it does not exhibit biased language or r
 
 - [Toxicity Scorer](./toxicity)
 - [Faithfulness Scorer](./faithfulness)
-- [Hallucination Scorer](./hallucination)
+- [Hallucination Scorer](./hallucination)