@mastra/mcp-docs-server 0.13.37 → 0.13.38

package/.docs/raw/reference/scorers/create-scorer.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Create Custom Scorer | Scorers | Mastra Docs"
+title: "Reference: createScorer | Scorers | Mastra Docs"
 description: Documentation for creating custom scorers in Mastra, allowing users to define their own evaluation logic using either JavaScript functions or LLM-based prompts.
 ---
 
@@ -18,15 +18,21 @@ const scorer = createScorer({
   type: "agent", // Optional: for agent evaluation with automatic typing
   judge: {
     model: myModel,
-    instructions: "You are an expert evaluator..."
-  }
+    instructions: "You are an expert evaluator...",
+  },
 })
-.preprocess({ /* step config */ })
-.analyze({ /* step config */ })
-.generateScore(({ run, results }) => {
-  // Return a number
-})
-.generateReason({ /* step config */ });
+  .preprocess({
+    /* step config */
+  })
+  .analyze({
+    /* step config */
+  })
+  .generateScore(({ run, results }) => {
+    // Return a number
+  })
+  .generateReason({
+    /* step config */
+  });
 ```
 
 ## createScorer Options
@@ -49,13 +55,15 @@ const scorer = createScorer({
       name: "judge",
       type: "object",
       required: false,
-      description: "Optional judge configuration for LLM-based steps. See Judge Object section below.",
+      description:
+        "Optional judge configuration for LLM-based steps. See Judge Object section below.",
     },
     {
       name: "type",
       type: "string",
       required: false,
-      description: "Type specification for input/output. Use 'agent' for automatic agent types. For custom types, use the generic approach instead.",
+      description:
+        "Type specification for input/output. Use 'agent' for automatic agent types. For custom types, use the generic approach instead.",
     },
   ]}
 />
@@ -90,24 +98,24 @@ You can specify input/output types when creating scorers for better type inferen
 For evaluating agents, use `type: 'agent'` to automatically get the correct types for agent input/output:
 
 ```typescript
-import { createScorer } from '@mastra/core/scorers';
+import { createScorer } from "@mastra/core/scorers";
 
 // Agent scorer with automatic typing
 const agentScorer = createScorer({
-  name: 'Agent Response Quality',
-  description: 'Evaluates agent responses',
-  type: 'agent' // Automatically provides ScorerRunInputForAgent/ScorerRunOutputForAgent
-})
-.preprocess(({ run }) => {
-  // run.input is automatically typed as ScorerRunInputForAgent
-  const userMessage = run.input.inputMessages[0]?.content;
-  return { userMessage };
+  name: "Agent Response Quality",
+  description: "Evaluates agent responses",
+  type: "agent", // Automatically provides ScorerRunInputForAgent/ScorerRunOutputForAgent
 })
-.generateScore(({ run, results }) => {
-  // run.output is automatically typed as ScorerRunOutputForAgent  
-  const response = run.output[0]?.content;
-  return response.length > 10 ? 1.0 : 0.5;
-});
+  .preprocess(({ run }) => {
+    // run.input is automatically typed as ScorerRunInputForAgent
+    const userMessage = run.input.inputMessages[0]?.content;
+    return { userMessage };
+  })
+  .generateScore(({ run, results }) => {
+    // run.output is automatically typed as ScorerRunOutputForAgent
+    const response = run.output[0]?.content;
+    return response.length > 10 ? 1.0 : 0.5;
+  });
 ```
 
 ### Custom Types with Generics
@@ -115,16 +123,15 @@ const agentScorer = createScorer({
 For custom input/output types, use the generic approach:
 
 ```typescript
-import { createScorer } from '@mastra/core/scorers';
+import { createScorer } from "@mastra/core/scorers";
 
 type CustomInput = { query: string; context: string[] };
 type CustomOutput = { answer: string; confidence: number };
 
 const customScorer = createScorer<CustomInput, CustomOutput>({
-  name: 'Custom Scorer',
-  description: 'Evaluates custom data'
-})
-.generateScore(({ run }) => {
+  name: "Custom Scorer",
+  description: "Evaluates custom data",
+}).generateScore(({ run }) => {
   // run.input is typed as CustomInput
   // run.output is typed as CustomOutput
   return run.output.confidence;
@@ -144,15 +151,14 @@ When you use `type: 'agent'`, your scorer is compatible for both adding directly
 
 ```typescript
 const agentTraceScorer = createScorer({
-  name: 'Agent Trace Length',
-  description: 'Evaluates agent response length',
-  type: 'agent'
-})
-.generateScore(({ run }) => {
+  name: "Agent Trace Length",
+  description: "Evaluates agent response length",
+  type: "agent",
+}).generateScore(({ run }) => {
   // Trace data is automatically transformed to agent format
   const userMessages = run.input.inputMessages;
   const agentResponse = run.output[0]?.content;
-  
+
   // Score based on response length
   return agentResponse?.length > 50 ? 0 : 1;
 });
@@ -160,8 +166,8 @@ const agentTraceScorer = createScorer({
 // Register with Mastra for trace scoring
 const mastra = new Mastra({
   scorers: {
-    agentTraceScorer
-  }
+    agentTraceScorer,
+  },
 });
 ```
 
@@ -180,13 +186,15 @@ Function: `({ run, results }) => any`
       name: "run.input",
       type: "any",
       required: true,
-      description: "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
+      description:
+        "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
     },
     {
       name: "run.output",
       type: "any",
       required: true,
-      description: "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
+      description:
+        "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
     },
     {
       name: "run.runId",
@@ -198,7 +206,8 @@ Function: `({ run, results }) => any`
       name: "run.runtimeContext",
       type: "object",
       required: false,
-      description: "Runtime context from the agent or workflow step being evaluated (optional).",
+      description:
+        "Runtime context from the agent or workflow step being evaluated (optional).",
     },
     {
       name: "results",
@@ -213,6 +222,7 @@ Returns: `any`
 The method can return any value. The returned value will be available to subsequent steps as `preprocessStepResult`.
 
 **Prompt Object Mode:**
+
 <PropertiesTable
   content={[
     {
@@ -231,13 +241,15 @@ The method can return any value. The returned value will be available to subsequ
       name: "createPrompt",
       type: "function",
       required: true,
-      description: "Function: ({ run, results }) => string. Returns the prompt for the LLM.",
+      description:
+        "Function: ({ run, results }) => string. Returns the prompt for the LLM.",
     },
     {
       name: "judge",
       type: "object",
       required: false,
-      description: "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
+      description:
+        "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
     },
   ]}
 />
@@ -255,13 +267,15 @@ Function: `({ run, results }) => any`
       name: "run.input",
       type: "any",
       required: true,
-      description: "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
+      description:
+        "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
     },
     {
       name: "run.output",
       type: "any",
       required: true,
-      description: "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
+      description:
+        "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
     },
     {
       name: "run.runId",
@@ -273,7 +287,8 @@ Function: `({ run, results }) => any`
       name: "run.runtimeContext",
       type: "object",
       required: false,
-      description: "Runtime context from the agent or workflow step being evaluated (optional).",
+      description:
+        "Runtime context from the agent or workflow step being evaluated (optional).",
     },
     {
       name: "results.preprocessStepResult",
@@ -288,6 +303,7 @@ Returns: `any`
 The method can return any value. The returned value will be available to subsequent steps as `analyzeStepResult`.
 
 **Prompt Object Mode:**
+
 <PropertiesTable
   content={[
     {
@@ -306,13 +322,15 @@ The method can return any value. The returned value will be available to subsequ
       name: "createPrompt",
       type: "function",
       required: true,
-      description: "Function: ({ run, results }) => string. Returns the prompt for the LLM.",
+      description:
+        "Function: ({ run, results }) => string. Returns the prompt for the LLM.",
     },
     {
       name: "judge",
       type: "object",
       required: false,
-      description: "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
+      description:
+        "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
     },
   ]}
 />
@@ -330,13 +348,15 @@ Function: `({ run, results }) => number`
       name: "run.input",
       type: "any",
       required: true,
-      description: "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
+      description:
+        "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
     },
     {
       name: "run.output",
       type: "any",
       required: true,
-      description: "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
+      description:
+        "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
     },
     {
       name: "run.runId",
@@ -348,7 +368,8 @@ Function: `({ run, results }) => number`
       name: "run.runtimeContext",
       type: "object",
       required: false,
-      description: "Runtime context from the agent or workflow step being evaluated (optional).",
+      description:
+        "Runtime context from the agent or workflow step being evaluated (optional).",
     },
     {
       name: "results.preprocessStepResult",
@@ -369,6 +390,7 @@ Returns: `number`
 The method must return a numerical score.
 
 **Prompt Object Mode:**
+
 <PropertiesTable
   content={[
     {
@@ -381,19 +403,22 @@ The method must return a numerical score.
       name: "outputSchema",
       type: "ZodSchema",
       required: true,
-      description: "Zod schema for the expected output of the generateScore step.",
+      description:
+        "Zod schema for the expected output of the generateScore step.",
     },
     {
       name: "createPrompt",
       type: "function",
       required: true,
-      description: "Function: ({ run, results }) => string. Returns the prompt for the LLM.",
+      description:
+        "Function: ({ run, results }) => string. Returns the prompt for the LLM.",
     },
     {
       name: "judge",
       type: "object",
       required: false,
-      description: "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
+      description:
+        "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
     },
   ]}
 />
@@ -406,7 +431,8 @@ When using prompt object mode, you must also provide a `calculateScore` function
       name: "calculateScore",
       type: "function",
       required: true,
-      description: "Function: ({ run, results, analyzeStepResult }) => number. Converts the LLM's structured output into a numerical score.",
+      description:
+        "Function: ({ run, results, analyzeStepResult }) => number. Converts the LLM's structured output into a numerical score.",
     },
   ]}
 />
@@ -424,13 +450,15 @@ Function: `({ run, results, score }) => string`
       name: "run.input",
       type: "any",
       required: true,
-      description: "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
+      description:
+        "Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. `[{ role: 'user', content: 'hello world' }]`. If the scorer is used in a workflow, this will be the input of the workflow.",
     },
     {
       name: "run.output",
       type: "any",
       required: true,
-      description: "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
+      description:
+        "Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.",
     },
     {
       name: "run.runId",
@@ -442,7 +470,8 @@ Function: `({ run, results, score }) => string`
       name: "run.runtimeContext",
       type: "object",
       required: false,
-      description: "Runtime context from the agent or workflow step being evaluated (optional).",
+      description:
+        "Runtime context from the agent or workflow step being evaluated (optional).",
     },
     {
       name: "results.preprocessStepResult",
@@ -469,6 +498,7 @@ Returns: `string`
 The method must return a string explaining the score.
 
 **Prompt Object Mode:**
+
 <PropertiesTable
   content={[
     {
@@ -481,15 +511,17 @@ The method must return a string explaining the score.
       name: "createPrompt",
       type: "function",
       required: true,
-      description: "Function: ({ run, results, score }) => string. Returns the prompt for the LLM.",
+      description:
+        "Function: ({ run, results, score }) => string. Returns the prompt for the LLM.",
     },
     {
       name: "judge",
       type: "object",
       required: false,
-      description: "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
+      description:
+        "(Optional) LLM judge for this step (can override main judge). See Judge Object section.",
     },
   ]}
 />
 
-All step functions can be async.
+All step functions can be async.

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

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Faithfulness | Scorers | Mastra Docs"
+title: "Reference: Faithfulness Scorer | Scorers | Mastra Docs"
 description: Documentation for the Faithfulness Scorer in Mastra, which evaluates the factual accuracy of LLM outputs compared to the provided context.
 ---
 
@@ -23,14 +23,16 @@ The `createFaithfulnessScorer()` function accepts a single options object with t
       name: "context",
       type: "string[]",
       required: true,
-      description: "Array of context chunks against which the output's claims will be verified.",
+      description:
+        "Array of context chunks against which the output's claims will be verified.",
     },
     {
       name: "scale",
       type: "number",
       required: false,
       defaultValue: "1",
-      description: "The maximum score value. The final score will be normalized to this scale.",
+      description:
+        "The maximum score value. The final score will be normalized to this scale.",
     },
   ]}
 />
@@ -54,32 +56,38 @@ 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 verdicts: { verdicts: Array<{ verdict: 'yes' | 'no' | 'unsure', reason: string }> }",
+      description:
+        "Object with verdicts: { verdicts: Array<{ verdict: 'yes' | 'no' | 'unsure', 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: "A score between 0 and the configured scale, representing the proportion of claims that are supported by the context.",
+      description:
+        "A score between 0 and the configured scale, representing the proportion of claims that are supported by the context.",
     },
     {
       name: "reason",
       type: "string",
-      description: "A detailed explanation of the score, including which claims were supported, contradicted, or marked as unsure.",
+      description:
+        "A detailed explanation of the score, including which claims were supported, contradicted, or marked as unsure.",
     },
     {
       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).",
     },
   ]}
 />
@@ -120,7 +128,7 @@ A faithfulness score between 0 and 1:
 
 In this example, the response closely aligns with the context. Each statement in the output is verifiable and supported by the provided context entries, resulting in a high score.
 
-```typescript filename="src/example-high-faithfulness.ts" showLineNumbers copy
+```typescript title="src/example-high-faithfulness.ts" showLineNumbers copy
 import { createFaithfulnessScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createFaithfulnessScorer({ model: 'openai/gpt-4o-mini', options: {
@@ -157,7 +165,7 @@ The output receives a score of 1 because all the information it provides can be
 
 In this example, there are a mix of supported and unsupported claims. Some parts of the response are backed by the context, while others introduce new information not found in the source material.
 
-```typescript filename="src/example-mixed-faithfulness.ts" showLineNumbers copy
+```typescript title="src/example-mixed-faithfulness.ts" showLineNumbers copy
 import { createFaithfulnessScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createFaithfulnessScorer({ model: 'openai/gpt-4o-mini', options: {
@@ -194,7 +202,7 @@ The score is lower because only a portion of the response is verifiable. While s
 
 In this example, the response directly contradicts the context. None of the claims are supported, and several conflict with the facts provided.
 
-```typescript filename="src/example-low-faithfulness.ts" showLineNumbers copy
+```typescript title="src/example-low-faithfulness.ts" showLineNumbers copy
 import { createFaithfulnessScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createFaithfulnessScorer({ model: 'openai/gpt-4o-mini', options: {
@@ -230,4 +238,4 @@ Each claim is inaccurate or conflicts with the context, resulting in a score of
 ## Related
 
 - [Answer Relevancy Scorer](./answer-relevancy)
-- [Hallucination Scorer](./hallucination)
+- [Hallucination Scorer](./hallucination)

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

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Hallucination | Scorers | Mastra Docs"
+title: "Reference: Hallucination Scorer | Scorers | Mastra Docs"
 description: Documentation for the Hallucination Scorer in Mastra, which evaluates the factual correctness of LLM outputs by identifying contradictions with provided context.
 ---
 
@@ -17,7 +17,8 @@ The `createHallucinationScorer()` function accepts a single options object with
       name: "model",
       type: "LanguageModel",
       required: true,
-      description: "Configuration for the model used to evaluate hallucination.",
+      description:
+        "Configuration for the model used to evaluate hallucination.",
     },
     {
       name: "scale",
@@ -48,17 +49,20 @@ 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 verdicts: { verdicts: Array<{ statement: string, verdict: 'yes' | 'no', reason: string }> }",
+      description:
+        "Object with verdicts: { verdicts: Array<{ statement: string, verdict: '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",
@@ -68,12 +72,14 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "reason",
       type: "string",
-      description: "Detailed explanation of the score and identified contradictions.",
+      description:
+        "Detailed explanation of the score and identified contradictions.",
     },
     {
       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).",
     },
   ]}
 />
@@ -131,7 +137,7 @@ A hallucination score between 0 and 1:
 
 In this example, the response is fully aligned with the provided context. All claims are factually correct and directly supported by the source material, resulting in a low hallucination score.
 
-```typescript filename="src/example-no-hallucination.ts" showLineNumbers copy
+```typescript title="src/example-no-hallucination.ts" showLineNumbers copy
 import { createHallucinationScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createHallucinationScorer({ model: 'openai/gpt-4o-mini', options: {
@@ -168,7 +174,7 @@ The response receives a score of 0 because there are no contradictions. Every st
 
 In this example, the response includes both accurate and inaccurate claims. Some details align with the context, while others directly contradict it—such as inflated numbers or incorrect locations. These contradictions increase the hallucination score.
 
-```typescript filename="src/example-mixed-hallucination.ts" showLineNumbers copy
+```typescript title="src/example-mixed-hallucination.ts" showLineNumbers copy
 import { createHallucinationScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createHallucinationScorer({ model: 'openai/gpt-4o-mini', options: {
@@ -206,7 +212,7 @@ The Scorer assigns a mid-range score because parts of the response conflict with
 
 In this example, the response contradicts every key fact in the context. None of the claims can be verified, and all presented details are factually incorrect.
 
-```typescript filename="src/example-complete-hallucination.ts" showLineNumbers copy
+```typescript title="src/example-complete-hallucination.ts" showLineNumbers copy
 import { createHallucinationScorer } from "@mastra/evals/scorers/llm";
 
 const scorer = createHallucinationScorer({ model: 'openai/gpt-4o-mini', options: {
@@ -240,8 +246,7 @@ The Scorer assigns a score of 1 because every statement in the response conflict
 }
 ```
 
-
 ## Related
 
 - [Faithfulness Scorer](./faithfulness)
-- [Answer Relevancy Scorer](./answer-relevancy)
+- [Answer Relevancy Scorer](./answer-relevancy)