@mastra/mcp-docs-server 0.13.37 → 0.13.38

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

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Toxicity | Scorers | Mastra Docs"
+title: "Reference: Toxicity Scorer | Scorers | Mastra Docs"
 description: Documentation for the Toxicity Scorer in Mastra, which evaluates LLM outputs for racist, biased, or toxic elements.
 ---
 
@@ -43,12 +43,14 @@ This function returns an instance of the MastraScorer class. The `.run()` method
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Object with verdicts: { verdicts: Array<{ verdict: 'yes' | 'no', reason: string }> }",
+      description:
+        "Object with verdicts: { verdicts: Array<{ 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",
@@ -63,7 +65,8 @@ 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).",
     },
   ]}
 />
@@ -83,7 +86,6 @@ This function returns an instance of the MastraScorer class. The `.run()` method
 }
 ```
 
-
 ## Scoring Details
 
 The scorer evaluates toxicity through multiple aspects:
@@ -123,21 +125,22 @@ A toxicity score between 0 and 1:
 
 In this example, the response contains explicit personal attacks and harmful language, resulting in a high toxicity score.
 
-```typescript filename="src/example-high-toxicity.ts" showLineNumbers copy
+```typescript title="src/example-high-toxicity.ts" showLineNumbers copy
 import { createToxicityScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createToxicityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createToxicityScorer({ model: "openai/gpt-4o-mini" });
 
-const query = 'What do you think about the new team member?';
-const response = 'That incompetent fool is a complete waste of space. They clearly bought their degree and have no business being here. Everyone hates working with them.';
+const query = "What do you think about the new team member?";
+const response =
+  "That incompetent fool is a complete waste of space. They clearly bought their degree and have no business being here. Everyone hates working with them.";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: query }],
-  output: { role: 'assistant', text: response },
+  input: [{ role: "user", content: query }],
+  output: { role: "assistant", text: response },
 });
 
-console.log('Score:', result.score);
-console.log('Reason:', result.reason);
+console.log("Score:", result.score);
+console.log("Reason:", result.reason);
 ```
 
 #### High toxicity output
@@ -155,24 +158,24 @@ The scorer returns a high score indicating severe toxic content. The `reason` fi
 
 In this example, the response combines toxic and professional elements. The scorer identifies the problematic language while acknowledging the constructive feedback, resulting in a moderate toxicity score.
 
-```typescript filename="src/example-mixed-toxicity.ts" showLineNumbers copy
+```typescript title="src/example-mixed-toxicity.ts" showLineNumbers copy
 import { createToxicityScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createToxicityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createToxicityScorer({ model: "openai/gpt-4o-mini" });
 
-const query = 'How was the meeting discussion?';
+const query = "How was the meeting discussion?";
 const response = [
-  'Half the meeting was just listening to the marketing team ramble on with their usual clueless suggestions.',
-  "At least the engineering team's presentation was focused and had some solid technical solutions we can actually use."
+  "Half the meeting was just listening to the marketing team ramble on with their usual clueless suggestions.",
+  "At least the engineering team's presentation was focused and had some solid technical solutions we can actually use.",
 ];
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: query }],
-  output: { role: 'assistant', text: response },
+  input: [{ role: "user", content: query }],
+  output: { role: "assistant", text: response },
 });
 
-console.log('Score:', result.score);
-console.log('Reason:', result.reason);
+console.log("Score:", result.score);
+console.log("Reason:", result.reason);
 ```
 
 #### Mixed toxicity output
@@ -190,21 +193,22 @@ The scorer returns a moderate score reflecting a combination of dismissive langu
 
 In this example, the response is professional and constructive, with no toxic or harmful language detected.
 
-```typescript filename="src/example-no-toxicity.ts" showLineNumbers copy
+```typescript title="src/example-no-toxicity.ts" showLineNumbers copy
 import { createToxicityScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createToxicityScorer({ model: 'openai/gpt-4o-mini' });
+const scorer = createToxicityScorer({ model: "openai/gpt-4o-mini" });
 
-const query = 'Can you provide feedback on the project proposal?';
-const response = 'The proposal has strong points in its technical approach but could benefit from more detailed market analysis. I suggest we collaborate with the research team to strengthen these sections.';
+const query = "Can you provide feedback on the project proposal?";
+const response =
+  "The proposal has strong points in its technical approach but could benefit from more detailed market analysis. I suggest we collaborate with the research team to strengthen these sections.";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: query }],
-  output: { role: 'assistant', text: response },
+  input: [{ role: "user", content: query }],
+  output: { role: "assistant", text: response },
 });
 
-console.log('Score:', result.score);
-console.log('Reason:', result.reason);
+console.log("Score:", result.score);
+console.log("Reason:", result.reason);
 ```
 
 #### No toxicity output
@@ -221,4 +225,4 @@ The scorer returns a low score indicating the response is free from toxic conten
 ## Related
 
 - [Tone Consistency Scorer](./tone-consistency)
-- [Bias Scorer](./bias)
+- [Bias Scorer](./bias)

package/.docs/raw/reference/storage/cloudflare-d1.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Cloudflare D1 Storage | Storage System | Mastra Core"
+title: "Reference: Cloudflare D1 Storage | Storage | Mastra Docs"
 description: Documentation for the Cloudflare D1 SQL storage implementation in Mastra.
 ---
 

package/.docs/raw/reference/storage/cloudflare.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Cloudflare Storage | Storage System | Mastra Core"
+title: "Reference: Cloudflare Storage | Storage | Mastra Docs"
 description: Documentation for the Cloudflare KV storage implementation in Mastra.
 ---
 

package/.docs/raw/reference/storage/dynamodb.mdx

@@ -1,5 +1,5 @@
 ---
-title: "DynamoDB Storage | Storage System | Mastra Core"
+title: "Reference: DynamoDB Storage | Storage | Mastra Docs"
 description: "Documentation for the DynamoDB storage implementation in Mastra, using a single-table design with ElectroDB."
 ---
 

package/.docs/raw/reference/storage/lance.mdx

@@ -1,5 +1,5 @@
 ---
-title: "LanceDB Storage"
+title: "Reference: LanceDB Storage | Storage | Mastra Docs"
 description: Documentation for the LanceDB storage implementation in Mastra.
 ---
 

package/.docs/raw/reference/storage/libsql.mdx

@@ -1,5 +1,5 @@
 ---
-title: "LibSQL Storage | Storage System | Mastra Core"
+title: "Reference: LibSQL Storage | Storage | Mastra Docs"
 description: Documentation for the LibSQL storage implementation in Mastra.
 ---
 
@@ -66,7 +66,7 @@ For production use cases, use a persistent database URL: `libsql://your-database
 The storage implementation handles schema creation and updates automatically. It creates the following tables:
 
 - `mastra_workflow_snapshot`: Stores workflow state and execution data
-- `mastra_evals`: Stores evaluation results and metadata  
+- `mastra_evals`: Stores evaluation results and metadata
 - `mastra_threads`: Stores conversation threads
 - `mastra_messages`: Stores individual messages
 - `mastra_traces`: Stores telemetry and tracing data

package/.docs/raw/reference/storage/mongodb.mdx

@@ -1,5 +1,5 @@
 ---
-title: "MongoDB Storage | Storage System | Mastra Core"
+title: "Reference: MongoDB Storage | Storage | Mastra Docs"
 description: Documentation for the MongoDB storage implementation in Mastra.
 ---
 
@@ -40,8 +40,7 @@ const storage = new MongoDBStore({
     {
       name: "dbName",
       type: "string",
-      description:
-        "The name of the database you want the storage to use.",
+      description: "The name of the database you want the storage to use.",
       isOptional: false,
     },
     {
@@ -50,7 +49,7 @@ const storage = new MongoDBStore({
       description:
         "MongoDB client options for advanced configuration (SSL, connection pooling, etc.). See advanced configuration [here](https://www.mongodb.com/docs/drivers/node/current/connect/connection-options/).",
       isOptional: true,
-    }
+    },
   ]}
 />
 
@@ -87,7 +86,7 @@ const store2 = new MongoDBStore({
 The storage implementation handles collection creation and management automatically. It creates the following collections:
 
 - `mastra_workflow_snapshot`: Stores workflow state and execution data
-- `mastra_evals`: Stores evaluation results and metadata  
+- `mastra_evals`: Stores evaluation results and metadata
 - `mastra_threads`: Stores conversation threads
 - `mastra_messages`: Stores individual messages
 - `mastra_traces`: Stores telemetry and tracing data

package/.docs/raw/reference/storage/mssql.mdx

@@ -1,5 +1,5 @@
 ---
-title: "MSSQL Storage | Storage System | Mastra Core"
+title: "Reference: MSSQL Storage | Storage | Mastra Docs"
 description: Documentation for the MSSQL storage implementation in Mastra.
 ---
 
@@ -89,7 +89,7 @@ const store5 = new MSSQLStore({
 The storage implementation handles schema creation and updates automatically. It creates the following tables:
 
 - `mastra_workflow_snapshot`: Stores workflow state and execution data
-- `mastra_evals`: Stores evaluation results and metadata  
+- `mastra_evals`: Stores evaluation results and metadata
 - `mastra_threads`: Stores conversation threads
 - `mastra_messages`: Stores individual messages
 - `mastra_traces`: Stores telemetry and tracing data
@@ -101,12 +101,13 @@ The storage implementation handles schema creation and updates automatically. It
 `MSSQLStore` exposes the mssql connection pool as public fields:
 
 ```typescript
-store.pool // mssql connection pool instance
+store.pool; // mssql connection pool instance
 ```
 
 This enables direct queries and custom transaction management. When using these fields:
+
 - You are responsible for proper connection and transaction handling.
 - Closing the store (`store.close()`) will destroy the associated connection pool.
 - Direct access bypasses any additional logic or validation provided by MSSQLStore methods.
 
-This approach is intended for advanced scenarios where low-level access is required. 
+This approach is intended for advanced scenarios where low-level access is required.

package/.docs/raw/reference/storage/postgresql.mdx

@@ -1,5 +1,5 @@
 ---
-title: "PostgreSQL Storage | Storage System | Mastra Core"
+title: "Reference: PostgreSQL Storage | Storage | Mastra Docs"
 description: Documentation for the PostgreSQL storage implementation in Mastra.
 ---
 
@@ -89,7 +89,7 @@ const store5 = new PostgresStore({
 The storage implementation handles schema creation and updates automatically. It creates the following tables:
 
 - `mastra_workflow_snapshot`: Stores workflow state and execution data
-- `mastra_evals`: Stores evaluation results and metadata  
+- `mastra_evals`: Stores evaluation results and metadata
 - `mastra_threads`: Stores conversation threads
 - `mastra_messages`: Stores individual messages
 - `mastra_traces`: Stores telemetry and tracing data
@@ -101,11 +101,12 @@ The storage implementation handles schema creation and updates automatically. It
 `PostgresStore` exposes both the underlying database object and the pg-promise instance as public fields:
 
 ```typescript
-store.db  // pg-promise database instance
-store.pgp // pg-promise main instance
+store.db; // pg-promise database instance
+store.pgp; // pg-promise main instance
 ```
 
 This enables direct queries and custom transaction management. When using these fields:
+
 - You are responsible for proper connection and transaction handling.
 - Closing the store (`store.close()`) will destroy the associated connection pool.
 - Direct access bypasses any additional logic or validation provided by PostgresStore methods.
@@ -121,7 +122,7 @@ PostgreSQL storage provides comprehensive index management capabilities to optim
 PostgreSQL storage automatically creates composite indexes during initialization for common query patterns:
 
 - `mastra_threads_resourceid_createdat_idx`: (resourceId, createdAt DESC)
-- `mastra_messages_thread_id_createdat_idx`: (thread_id, createdAt DESC)  
+- `mastra_messages_thread_id_createdat_idx`: (thread_id, createdAt DESC)
 - `mastra_traces_name_starttime_idx`: (name, startTime DESC)
 - `mastra_evals_agent_name_created_at_idx`: (agent_name, created_at DESC)
 
@@ -134,28 +135,29 @@ Create additional indexes to optimize specific query patterns:
 ```typescript copy
 // Basic index for common queries
 await storage.createIndex({
-  name: 'idx_threads_resource',
-  table: 'mastra_threads',
-  columns: ['resourceId']
+  name: "idx_threads_resource",
+  table: "mastra_threads",
+  columns: ["resourceId"],
 });
 
 // Composite index with sort order for filtering + sorting
 await storage.createIndex({
-  name: 'idx_messages_composite',
-  table: 'mastra_messages',
-  columns: ['thread_id', 'createdAt DESC']
+  name: "idx_messages_composite",
+  table: "mastra_messages",
+  columns: ["thread_id", "createdAt DESC"],
 });
 
 // GIN index for JSONB columns (fast JSON queries)
 await storage.createIndex({
-  name: 'idx_traces_attributes',
-  table: 'mastra_traces',
-  columns: ['attributes'],
-  method: 'gin'
+  name: "idx_traces_attributes",
+  table: "mastra_traces",
+  columns: ["attributes"],
+  method: "gin",
 });
 ```
 
 For more advanced use cases, you can also use:
+
 - `unique: true` for unique constraints
 - `where: 'condition'` for partial indexes
 - `method: 'brin'` for time-series data
@@ -181,7 +183,8 @@ For more advanced use cases, you can also use:
     {
       name: "columns",
       type: "string[]",
-      description: "Array of column names with optional sort order (e.g., ['id', 'createdAt DESC'])",
+      description:
+        "Array of column names with optional sort order (e.g., ['id', 'createdAt DESC'])",
       isOptional: false,
     },
     {
@@ -225,7 +228,7 @@ For more advanced use cases, you can also use:
       type: "string",
       description: "Tablespace name for index placement",
       isOptional: true,
-    }
+    },
   ]}
 />
 
@@ -250,10 +253,10 @@ console.log(allIndexes);
 // ]
 
 // List indexes for specific table
-const threadIndexes = await storage.listIndexes('mastra_threads');
+const threadIndexes = await storage.listIndexes("mastra_threads");
 
 // Get detailed statistics for an index
-const stats = await storage.describeIndex('idx_threads_resource');
+const stats = await storage.describeIndex("idx_threads_resource");
 console.log(stats);
 // {
 //   name: 'idx_threads_resource',
@@ -269,7 +272,7 @@ console.log(stats);
 // }
 
 // Drop an index
-await storage.dropIndex('idx_threads_status');
+await storage.dropIndex("idx_threads_status");
 ```
 
 ### Schema-Specific Indexes
@@ -279,14 +282,14 @@ When using custom schemas, indexes are created with schema prefixes:
 ```typescript copy
 const storage = new PostgresStore({
   connectionString: process.env.DATABASE_URL,
-  schemaName: 'custom_schema'
+  schemaName: "custom_schema",
 });
 
 // Creates index as: custom_schema_idx_threads_status
 await storage.createIndex({
-  name: 'idx_threads_status',
-  table: 'mastra_threads',
-  columns: ['status']
+  name: "idx_threads_status",
+  table: "mastra_threads",
+  columns: ["status"],
 });
 ```
 
@@ -294,12 +297,11 @@ await storage.createIndex({
 
 PostgreSQL offers different index types optimized for specific scenarios:
 
-| Index Type | Best For | Storage | Speed |
-|------------|----------|---------|-------|
-| **btree** (default) | Range queries, sorting, general purpose | Moderate | Fast |
-| **hash** | Equality comparisons only | Small | Very fast for `=` |
-| **gin** | JSONB, arrays, full-text search | Large | Fast for contains |
-| **gist** | Geometric data, full-text search | Moderate | Fast for nearest-neighbor |
-| **spgist** | Non-balanced data, text patterns | Small | Fast for specific patterns |
-| **brin** | Large tables with natural ordering | Very small | Fast for ranges |
-
+| Index Type          | Best For                                | Storage    | Speed                      |
+| ------------------- | --------------------------------------- | ---------- | -------------------------- |
+| **btree** (default) | Range queries, sorting, general purpose | Moderate   | Fast                       |
+| **hash**            | Equality comparisons only               | Small      | Very fast for `=`          |
+| **gin**             | JSONB, arrays, full-text search         | Large      | Fast for contains          |
+| **gist**            | Geometric data, full-text search        | Moderate   | Fast for nearest-neighbor  |
+| **spgist**          | Non-balanced data, text patterns        | Small      | Fast for specific patterns |
+| **brin**            | Large tables with natural ordering      | Very small | Fast for ranges            |

package/.docs/raw/reference/storage/upstash.mdx

@@ -1,16 +1,17 @@
 ---
-title: "Upstash Storage | Storage System | Mastra Core"
+title: "Reference: Upstash Storage | Storage | Mastra Docs"
 description: Documentation for the Upstash storage implementation in Mastra.
 ---
-import { Callout } from 'nextra/components'
 
 # Upstash Storage
 
 The Upstash storage implementation provides a serverless-friendly storage solution using Upstash's Redis-compatible key-value store.
 
-<Callout type="warning">
-  **Important:** When using Mastra with Upstash, the pay-as-you-go model can result in unexpectedly high costs due to the high volume of Redis commands generated during agent conversations. We strongly recommend using a **fixed pricing plan** for predictable costs. See [Upstash pricing](https://upstash.com/pricing/redis) for details and [GitHub issue #5850](https://github.com/mastra-ai/mastra/issues/5850) for context.
-</Callout>
+:::warning
+
+**Important:** When using Mastra with Upstash, the pay-as-you-go model can result in unexpectedly high costs due to the high volume of Redis commands generated during agent conversations. We strongly recommend using a **fixed pricing plan** for predictable costs. See [Upstash pricing](https://upstash.com/pricing/redis) for details and [GitHub issue #5850](https://github.com/mastra-ai/mastra/issues/5850) for context.
+
+:::
 
 ## Installation