@mastra/mcp-docs-server 1.0.0-beta.9 → 1.0.1

package/.docs/raw/reference/vectors/duckdb.mdx

@@ -1,6 +1,8 @@
 ---
 title: "Reference: DuckDBVector Store | Vectors"
 description: Documentation for the DuckDBVector class in Mastra, which provides embedded high-performance vector search using DuckDB with HNSW indexing.
+packages:
+  - "@mastra/duckdb"
 ---
 
 # DuckDBVector Store
@@ -11,13 +13,13 @@ It's part of the `@mastra/duckdb` package and offers efficient vector similarity
 
 ## Installation
 
-```bash copy
+```bash
 npm install @mastra/duckdb@beta
 ```
 
 ## Usage
 
-```typescript copy showLineNumbers
+```typescript
 import { DuckDBVector } from "@mastra/duckdb";
 
 // Create a new vector store instance
@@ -206,7 +208,7 @@ Gets information about an index.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -330,7 +332,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 Closes the database connection and releases resources.
 
-```typescript copy
+```typescript
 await store.close();
 ```
 
@@ -338,7 +340,7 @@ await store.close();
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -361,7 +363,7 @@ DuckDB vector store supports MongoDB-like filter operators:
 
 ### Filter Examples
 
-```typescript copy
+```typescript
 // Allegato operators
 const results = await store.query({
   indexName: "docs",
@@ -394,7 +396,7 @@ const results = await store.query({
 
 The store throws specific errors for different failure cases:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "my-collection",
@@ -425,7 +427,7 @@ Common error cases include:
 
 Build offline-capable AI applications with semantic search that runs entirely in-process:
 
-```typescript copy
+```typescript
 const store = new DuckDBVector({
   id: "offline-search",
   path: "./search.duckdb",
@@ -436,7 +438,7 @@ const store = new DuckDBVector({
 
 Process sensitive documents locally without sending data to cloud vector databases:
 
-```typescript copy
+```typescript
 const store = new DuckDBVector({
   id: "private-rag",
   path: "./confidential.duckdb",
@@ -448,7 +450,7 @@ const store = new DuckDBVector({
 
 Rapidly prototype vector search features with zero infrastructure:
 
-```typescript copy
+```typescript
 const store = new DuckDBVector({
   id: "dev-store",
   path: ":memory:", // Fast in-memory for tests

package/.docs/raw/reference/vectors/elasticsearch.mdx

@@ -1,6 +1,8 @@
 ---
 title: "Reference: ElasticSearch Vector Store | Vectors"
 description: Documentation for the ElasticSearchVector class in Mastra, which provides vector search using ElasticSearch.
+packages:
+  - "@mastra/elasticsearch"
 ---
 
 # ElasticSearch Vector Store
@@ -10,16 +12,17 @@ It's part of the `@mastra/elasticsearch` package.
 
 ## Installation
 
-```bash copy
+```bash
 npm install @mastra/elasticsearch@beta
 ```
 
 ## Usage
 
-```typescript copy showLineNumbers
+```typescript
 import { ElasticSearchVector } from "@mastra/elasticsearch";
 
 const store = new ElasticSearchVector({
+  id: "elasticsearch-vector",
   url: process.env.ELASTICSEARCH_URL,
 });
 
@@ -54,6 +57,11 @@ const results = await store.query({
 
 <PropertiesTable
   content={[
+    {
+      name: "id",
+      type: "string",
+      description: "Unique identifier for this vector store instance",
+    },
     {
       name: "url",
       type: "string",
@@ -176,7 +184,7 @@ Gets information about an index.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -296,7 +304,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;

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

@@ -1,6 +1,8 @@
 ---
 title: "Reference: Lance Vector Store | Vectors"
 description: "Documentation for the LanceVectorStore class in Mastra, which provides vector search using LanceDB, an embedded vector database based on the Lance columnar format."
+packages:
+  - "@mastra/lance"
 ---
 
 # Lance Vector Store
@@ -263,7 +265,7 @@ const s3Store = await LanceVectorStore.create("s3://bucket/db", {
 
 Returns an array of table names as strings.
 
-```typescript copy
+```typescript
 const tables = await vectorStore.listTables();
 // ['my_vectors', 'embeddings', 'documents']
 ```
@@ -316,7 +318,7 @@ Returns an array of index names as strings.
 
 Returns information about the index:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -425,7 +427,7 @@ Closes the database connection.
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -439,7 +441,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     tableName: "my_vectors",

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

@@ -1,28 +1,33 @@
 ---
-title: "Reference: LibSQLVector Store | Vectors"
-description: Documentation for the LibSQLVector class in Mastra, which provides vector search using LibSQL with vector extensions.
+title: "Reference: libSQL Vector Store | Vectors"
+description: Documentation for the LibSQLVector class in Mastra, which provides vector search using libSQL with vector extensions.
+packages:
+  - "@mastra/core"
+  - "@mastra/fastembed"
+  - "@mastra/libsql"
+  - "@mastra/memory"
 ---
 
-# LibSQLVector Store
+# libSQL Vector Store
 
-The LibSQL storage implementation provides a SQLite-compatible vector search [LibSQL](https://github.com/tursodatabase/libsql), a fork of SQLite with vector extensions, and [Turso](https://turso.tech/) with vector extensions, offering a lightweight and efficient vector database solution.
+The libSQL storage implementation provides a SQLite-compatible vector search [libSQL](https://github.com/tursodatabase/libsql), a fork of SQLite with vector extensions, and [Turso](https://turso.tech/) with vector extensions, offering a lightweight and efficient vector database solution.
 It's part of the `@mastra/libsql` package and offers efficient vector similarity search with metadata filtering.
 
 ## Installation
 
-```bash copy
+```bash
 npm install @mastra/libsql@beta
 ```
 
 ## Usage
 
-```typescript copy showLineNumbers
+```typescript
 import { LibSQLVector } from "@mastra/libsql";
 
 // Create a new vector store instance
 const store = new LibSQLVector({
   id: 'libsql-vector',
-  connectionUrl: process.env.DATABASE_URL,
+  url: process.env.DATABASE_URL,
   // Optional: for Turso cloud databases
   authToken: process.env.DATABASE_AUTH_TOKEN,
 });
@@ -60,10 +65,10 @@ const results = await store.query({
 <PropertiesTable
   content={[
     {
-      name: "connectionUrl",
+      name: "url",
       type: "string",
       description:
-        "LibSQL database URL. Use ':memory:' for in-memory database, 'file:dbname.db' for local file, or a LibSQL-compatible connection string like 'libsql://your-database.turso.io'.",
+        "libSQL database URL. Use ':memory:' for in-memory database, 'file:dbname.db' for local file, or a libSQL-compatible connection string like 'libsql://your-database.turso.io'.",
     },
     {
       name: "authToken",
@@ -111,7 +116,7 @@ Creates a new vector collection. The index name must start with a letter or unde
       isOptional: true,
       defaultValue: "cosine",
       description:
-        "Distance metric for similarity search. Note: Currently only cosine similarity is supported by LibSQL.",
+        "Distance metric for similarity search. Note: Currently only cosine similarity is supported by libSQL.",
     },
   ]}
 />
@@ -209,7 +214,7 @@ Gets information about an index.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -343,7 +348,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -356,7 +361,7 @@ interface QueryResult {
 
 The store throws specific errors for different failure cases:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "my-collection",
@@ -384,6 +389,54 @@ Common error cases include:
 - Database connection issues
 - Transaction failures during upsert
 
+## Usage Example
+
+### Local embeddings with fastembed
+
+Embeddings are numeric vectors used by memory's `semanticRecall` to retrieve related messages by meaning (not keywords). This setup uses `@mastra/fastembed` to generate vector embeddings.
+
+Install `fastembed` to get started:
+
+```bash 
+npm install @mastra/fastembed@beta
+```
+
+Add the following to your agent:
+
+```typescript title="src/mastra/agents/example-libsql-agent.ts"
+import { Memory } from "@mastra/memory";
+import { Agent } from "@mastra/core/agent";
+import { LibSQLStore, LibSQLVector } from "@mastra/libsql";
+import { fastembed } from "@mastra/fastembed";
+
+export const libsqlAgent = new Agent({
+  id: "libsql-agent",
+  name: "libSQL Agent",
+  instructions:
+    "You are an AI agent with the ability to automatically recall memories from previous interactions.",
+  model: "openai/gpt-5.1",
+  memory: new Memory({
+    storage: new LibSQLStore({
+      id: 'libsql-agent-storage',
+      url: "file:libsql-agent.db",
+    }),
+    vector: new LibSQLVector({
+      id: 'libsql-agent-vector',
+      url: "file:libsql-agent.db",
+    }),
+    embedder: fastembed,
+    options: {
+      lastMessages: 10,
+      semanticRecall: {
+        topK: 3,
+        messageRange: 2,
+      },
+      generateTitle: true, // Explicitly enable automatic title generation
+    },
+  }),
+});
+```
+
 ## Related
 
 - [Metadata Filters](../rag/metadata-filters)

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

@@ -1,6 +1,11 @@
 ---
 title: "Reference: MongoDB Vector Store | Vectors"
 description: Documentation for the MongoDBVector class in Mastra, which provides vector search using MongoDB Atlas and Atlas Vector Search.
+packages:
+  - "@mastra/core"
+  - "@mastra/fastembed"
+  - "@mastra/memory"
+  - "@mastra/mongodb"
 ---
 
 # MongoDB Vector Store
@@ -9,19 +14,34 @@ The `MongoDBVector` class provides vector search using [MongoDB Atlas Vector Sea
 
 ## Installation
 
-```bash copy
+```bash
 npm install @mastra/mongodb@beta
 ```
 
 ## Usage Example
 
-```typescript copy showLineNumbers
+```typescript
 import { MongoDBVector } from "@mastra/mongodb";
 
 const store = new MongoDBVector({
   id: 'mongodb-vector',
-  url: process.env.MONGODB_URL,
-  database: process.env.MONGODB_DATABASE,
+  uri: process.env.MONGODB_URI,
+  dbName: process.env.MONGODB_DATABASE,
+});
+```
+
+### Custom Embedding Field Path
+
+If you need to store embeddings in a nested field structure (e.g., to integrate with existing MongoDB collections), use the `embeddingFieldPath` option:
+
+```typescript
+import { MongoDBVector } from "@mastra/mongodb";
+
+const store = new MongoDBVector({
+  id: 'mongodb-vector',
+  uri: process.env.MONGODB_URI,
+  dbName: process.env.MONGODB_DATABASE,
+  embeddingFieldPath: 'text.contentEmbedding', // Store embeddings at text.contentEmbedding
 });
 ```
 
@@ -35,12 +55,12 @@ const store = new MongoDBVector({
       description: "Unique identifier for this vector store instance",
     },
     {
-      name: "url",
+      name: "uri",
       type: "string",
-      description: "MongoDB connection string (URI)",
+      description: "MongoDB connection string",
     },
     {
-      name: "database",
+      name: "dbName",
       type: "string",
       description: "Name of the MongoDB database to use",
     },
@@ -50,6 +70,13 @@ const store = new MongoDBVector({
       isOptional: true,
       description: "Optional MongoDB client options",
     },
+    {
+      name: "embeddingFieldPath",
+      type: "string",
+      isOptional: true,
+      defaultValue: "embedding",
+      description: "Path to the field that stores vector embeddings. Supports nested paths using dot notation (e.g., 'text.contentEmbedding').",
+    },
   ]}
 />
 
@@ -180,7 +207,7 @@ Returns information about the index (collection).
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -304,7 +331,7 @@ Closes the MongoDB client connection. Should be called when done using the store
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -317,7 +344,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "my_collection",
@@ -343,6 +370,59 @@ try {
 - Use consistent field naming in metadata to avoid unexpected query results.
 - Regularly monitor index and collection statistics to ensure efficient search.
 
+## Usage Example
+
+### Vector embeddings with MongoDB
+
+Embeddings are numeric vectors used by memory's `semanticRecall` to retrieve related messages by meaning (not keywords).
+
+> Note: You must use a deployment hosted on MongoDB Atlas to successfully use the MongoDB Vector database.
+
+This setup uses FastEmbed, a local embedding model, to generate vector embeddings.
+To use this, install `@mastra/fastembed`:
+
+```bash 
+npm install @mastra/fastembed@beta
+```
+
+Add the following to your agent:
+
+```typescript title="src/mastra/agents/example-mongodb-agent.ts"
+import { Memory } from "@mastra/memory";
+import { Agent } from "@mastra/core/agent";
+import { MongoDBStore, MongoDBVector } from "@mastra/mongodb";
+import { fastembed } from "@mastra/fastembed";
+
+export const mongodbAgent = new Agent({
+  id: "mongodb-agent",
+  name: "mongodb-agent",
+  instructions:
+    "You are an AI agent with the ability to automatically recall memories from previous interactions.",
+  model: "openai/gpt-5.1",
+  memory: new Memory({
+    storage: new MongoDBStore({
+      id: 'mongodb-storage',
+      uri: process.env.MONGODB_URI!,
+      dbName: process.env.MONGODB_DB_NAME!,
+    }),
+    vector: new MongoDBVector({
+      id: 'mongodb-vector',
+      uri: process.env.MONGODB_URI!,
+      dbName: process.env.MONGODB_DB_NAME!,
+    }),
+    embedder: fastembed,
+    options: {
+      lastMessages: 10,
+      semanticRecall: {
+        topK: 3,
+        messageRange: 2,
+      },
+      generateTitle: true, // generates descriptive thread titles automatically
+    },
+  }),
+});
+```
+
 ## Related
 
 - [Metadata Filters](../rag/metadata-filters)

package/.docs/raw/reference/vectors/opensearch.mdx

@@ -1,20 +1,47 @@
 ---
 title: "Reference: OpenSearch Vector Store | Vectors"
 description: Documentation for the OpenSearchVector class in Mastra, which provides vector search using OpenSearch.
+packages:
+  - "@mastra/opensearch"
 ---
 
 # OpenSearch Vector Store
 
-The OpenSearchVector class provides vector search using [OpenSearch](https://opensearch.org/), a powerful open-source search and analytics engine. It leverages OpenSearch's k-NN capabilities to perform efficient vector similarity search.
+The OpenSearchVector class provides vector search using [OpenSearch](https://opensearch.org/), an open-source search and analytics engine. It uses OpenSearch's k-NN capabilities to perform vector similarity search.
 
 ## Constructor Options
 
+The constructor accepts all [OpenSearch ClientOptions](https://opensearch.org/docs/latest/clients/javascript/index/) plus a required `id` field.
+
 <PropertiesTable
   content={[
     {
-      name: "url",
+      name: "id",
       type: "string",
-      description: "OpenSearch connection URL (e.g., 'http://localhost:9200')",
+      description: "Unique identifier for this vector store instance",
+    },
+    {
+      name: "node",
+      type: "string | string[] | NodeOptions | NodeOptions[]",
+      description: "OpenSearch node URL(s) (e.g., 'http://localhost:9200')",
+    },
+    {
+      name: "auth",
+      type: "BasicAuth | BearerAuth | AwsSigv4Auth",
+      description: "Authentication configuration",
+      isOptional: true,
+    },
+    {
+      name: "ssl",
+      type: "ConnectionOptions",
+      description: "SSL/TLS configuration",
+      isOptional: true,
+    },
+    {
+      name: "compression",
+      type: "'gzip'",
+      description: "Enable gzip compression",
+      isOptional: true,
     },
   ]}
 />

package/.docs/raw/reference/vectors/pg.mdx

@@ -1,6 +1,11 @@
 ---
 title: "Reference: PG Vector Store | Vectors"
 description: Documentation for the PgVector class in Mastra, which provides vector search using PostgreSQL with pgvector extension.
+packages:
+  - "@mastra/core"
+  - "@mastra/fastembed"
+  - "@mastra/memory"
+  - "@mastra/pg"
 ---
 
 # PG Vector Store
@@ -374,7 +379,7 @@ Returns an array of index names as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface PGIndexStats {
   dimension: number;
   count: number;
@@ -434,7 +439,7 @@ Update a single vector by ID or by metadata filter. Either `id` or `filter` must
 
 Updates an existing vector by ID or filter. At least one of vector or metadata must be provided in the update object.
 
-```typescript copy
+```typescript
 // Update by ID
 await pgVector.updateVector({
   indexName: "my_vectors",
@@ -474,7 +479,7 @@ await pgVector.updateVector({
 
 Deletes a single vector by ID from the specified index.
 
-```typescript copy
+```typescript
 await pgVector.deleteVector({ indexName: "my_vectors", id: "vector123" });
 ```
 
@@ -534,7 +539,7 @@ Closes the database connection pool. Should be called when done using the store.
 
 Builds or rebuilds an index with specified metric and configuration. Will drop any existing index before creating the new one.
 
-```typescript copy
+```typescript
 // Define HNSW index
 await pgVector.buildIndex("my_vectors", "cosine", {
   type: "hnsw",
@@ -562,7 +567,7 @@ await pgVector.buildIndex("my_vectors", "cosine", {
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -575,7 +580,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",
@@ -641,6 +646,53 @@ This enables advanced usage such as running direct SQL queries, managing transac
 
 This design supports advanced use cases but requires careful resource management by the user.
 
+## Usage Example
+
+### Local embeddings with fastembed
+
+Embeddings are numeric vectors used by memory's `semanticRecall` to retrieve related messages by meaning (not keywords). This setup uses `@mastra/fastembed` to generate vector embeddings.
+
+Install `fastembed` to get started:
+
+```bash
+npm install @mastra/fastembed@beta
+```
+
+Add the following to your agent:
+
+```typescript title="src/mastra/agents/example-pg-agent.ts"
+import { Memory } from "@mastra/memory";
+import { Agent } from "@mastra/core/agent";
+import { PostgresStore, PgVector } from "@mastra/pg";
+import { fastembed } from "@mastra/fastembed";
+
+export const pgAgent = new Agent({
+  id: "pg-agent",
+  name: "PG Agent",
+  instructions:
+    "You are an AI agent with the ability to automatically recall memories from previous interactions.",
+  model: "openai/gpt-5.1",
+  memory: new Memory({
+    storage: new PostgresStore({
+      id: 'pg-agent-storage',
+      connectionString: process.env.DATABASE_URL!,
+    }),
+    vector: new PgVector({
+      id: 'pg-agent-vector',
+      connectionString: process.env.DATABASE_URL!,
+    }),
+    embedder: fastembed,
+    options: {
+      lastMessages: 10,
+      semanticRecall: {
+        topK: 3,
+        messageRange: 2,
+      },
+    },
+  }),
+});
+```
+
 ## Related
 
 - [Metadata Filters](../rag/metadata-filters)