@mastra/mcp-docs-server 1.1.9-alpha.0 → 1.1.9-alpha.2

package/.docs/reference/vectors/pg.md

@@ -1,8 +1,8 @@
-# PG Vector Store
+# PG vector store
 
 The PgVector class provides vector search using [PostgreSQL](https://www.postgresql.org/) with [pgvector](https://github.com/pgvector/pgvector) extension. It provides robust vector similarity search capabilities within your existing PostgreSQL database.
 
-## Constructor Options
+## Constructor options
 
 **connectionString** (`string`): PostgreSQL connection URL
 
@@ -26,7 +26,7 @@ The PgVector class provides vector search using [PostgreSQL](https://www.postgre
 
 **pgPoolOptions** (`PoolConfig`): Additional pg pool configuration options
 
-## Constructor Examples
+## Constructor examples
 
 ### Connection String
 
@@ -70,7 +70,7 @@ const vectorStore = new PgVector({
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 **indexName** (`string`): Name of the index to create
 
@@ -84,7 +84,7 @@ const vectorStore = new PgVector({
 
 **metadataIndexes** (`string[]`): Array of metadata field names to create btree indexes on. Improves query performance when filtering by these metadata fields.
 
-#### IndexConfig
+#### `IndexConfig`
 
 **type** (`'flat' | 'hnsw' | 'ivfflat'`): Index type (Default: `ivfflat`)
 
@@ -114,7 +114,7 @@ HNSW indexes require significant shared memory during construction. For 100K vec
 
 Higher M values or efConstruction values will increase memory requirements significantly. Adjust your system's shared memory limits if needed.
 
-### upsert()
+### `upsert()`
 
 **indexName** (`string`): Name of the index to upsert vectors into
 
@@ -124,7 +124,7 @@ Higher M values or efConstruction values will increase memory requirements signi
 
 **ids** (`string[]`): Optional vector IDs (auto-generated if not provided)
 
-### query()
+### `query()`
 
 **indexName** (`string`): Name of the index to query
 
@@ -144,11 +144,11 @@ Higher M values or efConstruction values will increase memory requirements signi
 
 **options.probes** (`number`): IVF search parameter
 
-### listIndexes()
+### `listIndexes()`
 
 Returns an array of index names as strings.
 
-### describeIndex()
+### `describeIndex()`
 
 **indexName** (`string`): Name of the index to describe
 
@@ -169,11 +169,11 @@ interface PGIndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 **indexName** (`string`): Name of the index to delete
 
-### updateVector()
+### `updateVector()`
 
 Update a single vector by ID or by metadata filter. Either `id` or `filter` must be provided, but not both.
 
@@ -208,7 +208,7 @@ await pgVector.updateVector({
 })
 ```
 
-### deleteVector()
+### `deleteVector()`
 
 **indexName** (`string`): Name of the index containing the vector
 
@@ -220,7 +220,7 @@ Deletes a single vector by ID from the specified index.
 await pgVector.deleteVector({ indexName: 'my_vectors', id: 'vector123' })
 ```
 
-### deleteVectors()
+### `deleteVectors()`
 
 Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` must be provided, but not both.
 
@@ -230,11 +230,11 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 **filter** (`Record<string, any>`): Metadata filter to identify vectors to delete (mutually exclusive with ids)
 
-### disconnect()
+### `disconnect()`
 
 Closes the database connection pool. Should be called when done using the store.
 
-### buildIndex()
+### `buildIndex()`
 
 **indexName** (`string`): Name of the index to define
 
@@ -268,7 +268,7 @@ await pgVector.buildIndex('my_vectors', 'cosine', {
 })
 ```
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -281,7 +281,7 @@ interface QueryResult {
 }
 ```
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught:
 
@@ -299,7 +299,7 @@ try {
 }
 ```
 
-## Index Configuration Guide
+## Index configuration guide
 
 ### Performance Optimization
 
@@ -331,14 +331,14 @@ The system automatically detects configuration changes and only rebuilds indexes
 - Changed configuration: Index is dropped and rebuilt
 - This prevents the performance issues from unnecessary index recreations
 
-## Best Practices
+## Best practices
 
 - Regularly evaluate your index configuration to ensure optimal performance.
 - Adjust parameters like `lists` and `m` based on dataset size and query requirements.
 - **Monitor index performance** using `describeIndex()` to track usage
 - Rebuild indexes periodically to maintain efficiency, especially after significant data changes
 
-## Direct Pool Access
+## Direct pool access
 
 The `PgVector` class exposes its underlying PostgreSQL connection pool as a public field:
 
@@ -354,7 +354,7 @@ 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
+## Usage example
 
 ### Local embeddings with fastembed
 

package/.docs/reference/vectors/pinecone.md

@@ -1,8 +1,8 @@
-# Pinecone Vector Store
+# Pinecone vector store
 
 The PineconeVector class provides an interface to [Pinecone](https://www.pinecone.io/)'s vector database. It provides real-time vector search, with features like hybrid search, metadata filtering, and namespace management.
 
-## Constructor Options
+## Constructor options
 
 The constructor accepts all [Pinecone configuration options](https://docs.pinecone.io/reference/typescript-sdk) plus Mastra-specific fields.
 
@@ -22,7 +22,7 @@ The constructor accepts all [Pinecone configuration options](https://docs.pineco
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 **indexName** (`string`): Name of the index to create
 
@@ -30,7 +30,7 @@ The constructor accepts all [Pinecone configuration options](https://docs.pineco
 
 **metric** (`'cosine' | 'euclidean' | 'dotproduct'`): Distance metric for similarity search. Use 'dotproduct' if you plan to use hybrid search. (Default: `cosine`)
 
-### upsert()
+### `upsert()`
 
 **indexName** (`string`): Name of your Pinecone index
 
@@ -44,7 +44,7 @@ The constructor accepts all [Pinecone configuration options](https://docs.pineco
 
 **namespace** (`string`): Optional namespace to store vectors in. Vectors in different namespaces are isolated from each other.
 
-### query()
+### `query()`
 
 **indexName** (`string`): Name of the index to query
 
@@ -60,11 +60,11 @@ The constructor accepts all [Pinecone configuration options](https://docs.pineco
 
 **namespace** (`string`): Optional namespace to query vectors from. Only returns results from the specified namespace.
 
-### listIndexes()
+### `listIndexes()`
 
 Returns an array of index names as strings.
 
-### describeIndex()
+### `describeIndex()`
 
 **indexName** (`string`): Name of the index to describe
 
@@ -78,11 +78,11 @@ interface IndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 **indexName** (`string`): Name of the index to delete
 
-### updateVector()
+### `updateVector()`
 
 Update a single vector by ID or by metadata filter. Either `id` or `filter` must be provided, but not both.
 
@@ -100,13 +100,13 @@ Update a single vector by ID or by metadata filter. Either `id` or `filter` must
 
 **update.metadata** (`Record<string, any>`): New metadata to update
 
-### deleteVector()
+### `deleteVector()`
 
 **indexName** (`string`): Name of the index containing the vector
 
 **id** (`string`): ID of the vector to delete
 
-### deleteVectors()
+### `deleteVectors()`
 
 Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` must be provided, but not both.
 
@@ -118,7 +118,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 **namespace** (`string`): Optional namespace for the deletion operation
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -131,7 +131,7 @@ interface QueryResult {
 }
 ```
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught:
 
@@ -149,13 +149,13 @@ try {
 }
 ```
 
-### Environment Variables
+### Environment variables
 
 Required environment variables:
 
 - `PINECONE_API_KEY`: Your Pinecone API key
 
-## Hybrid Search
+## Hybrid search
 
 Pinecone supports hybrid search by combining dense and sparse vectors. To use hybrid search:
 

package/.docs/reference/vectors/qdrant.md

@@ -1,8 +1,8 @@
-# Qdrant Vector Store
+# Qdrant vector store
 
 The QdrantVector class provides vector search using [Qdrant](https://qdrant.tech/), a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage vectors with additional payload and extended filtering support.
 
-## Constructor Options
+## Constructor options
 
 **url** (`string`): REST URL of the Qdrant instance. Eg. https\://xyz-example.eu-central.aws.cloud.qdrant.io:6333
 
@@ -12,7 +12,7 @@ The QdrantVector class provides vector search using [Qdrant](https://qdrant.tech
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 **indexName** (`string`): Name of the index to create
 
@@ -36,7 +36,7 @@ await store.createIndex({
 })
 ```
 
-### upsert()
+### `upsert()`
 
 **indexName** (`string`): Name of the index to upsert into
 
@@ -68,7 +68,7 @@ await store.upsert({
 })
 ```
 
-### query()
+### `query()`
 
 **indexName** (`string`): Name of the index to query
 
@@ -95,11 +95,11 @@ const results = await store.query({
 })
 ```
 
-### listIndexes()
+### `listIndexes()`
 
 Returns an array of index names as strings.
 
-### describeIndex()
+### `describeIndex()`
 
 **indexName** (`string`): Name of the index to describe
 
@@ -113,11 +113,11 @@ interface IndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 **indexName** (`string`): Name of the index to delete
 
-### updateVector()
+### `updateVector()`
 
 Update a single vector by ID or by metadata filter. Either `id` or `filter` must be provided, but not both.
 
@@ -131,7 +131,7 @@ Update a single vector by ID or by metadata filter. Either `id` or `filter` must
 
 Updates a vector and/or its metadata in the specified index. If both vector and metadata are provided, both will be updated. If only one is provided, only that will be updated.
 
-### deleteVector()
+### `deleteVector()`
 
 **indexName** (`string`): Name of the index from which to delete the vector
 
@@ -139,7 +139,7 @@ Updates a vector and/or its metadata in the specified index. If both vector and
 
 Deletes a vector from the specified index by its ID.
 
-### deleteVectors()
+### `deleteVectors()`
 
 Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` must be provided, but not both.
 
@@ -149,7 +149,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 **filter** (`Record<string, any>`): Metadata filter to identify vectors to delete (mutually exclusive with ids)
 
-### createPayloadIndex()
+### `createPayloadIndex()`
 
 Creates a payload (metadata) index on a collection field to enable efficient filtering. This is **required** for Qdrant Cloud and any Qdrant instance with `strict_mode_config = true`.
 
@@ -176,7 +176,7 @@ const results = await store.query({
 })
 ```
 
-### deletePayloadIndex()
+### `deletePayloadIndex()`
 
 Removes a payload index from a collection field.
 
@@ -186,7 +186,7 @@ Removes a payload index from a collection field.
 
 **wait** (`boolean`): Whether to wait for the operation to complete (Default: `true`)
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -199,7 +199,7 @@ interface QueryResult {
 }
 ```
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught:
 

package/.docs/reference/vectors/s3vectors.md

@@ -1,4 +1,4 @@
-# Amazon S3 Vectors Store
+# Amazon S3 vectors store
 
 The `S3Vectors` class provides vector search using [Amazon S3 Vectors (Preview)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/s3-vectors.html). It stores vectors in **vector buckets** and performs similarity search in **vector indexes**, with JSON-based metadata filters.
 
@@ -30,7 +30,7 @@ yarn add @mastra/s3vectors@latest
 bun add @mastra/s3vectors@latest
 ```
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { S3Vectors } from '@mastra/s3vectors'
@@ -82,7 +82,7 @@ const results = await store.query({
 await store.disconnect()
 ```
 
-## Constructor Options
+## Constructor options
 
 **vectorBucketName** (`string`): Target S3 Vectors vector bucket name.
 
@@ -92,7 +92,7 @@ await store.disconnect()
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 Creates a new vector index in the configured vector bucket. If the index already exists, the call validates the schema and becomes a no-op (existing metric and dimension are preserved).
 
@@ -102,7 +102,7 @@ Creates a new vector index in the configured vector bucket. If the index already
 
 **metric** (`'cosine' | 'euclidean'`): Distance metric for similarity search. \`dotproduct\` is not supported by S3 Vectors. (Default: `cosine`)
 
-### upsert()
+### `upsert()`
 
 Adds or replaces vectors (full-record put). If `ids` aren't provided, UUIDs are generated.
 
@@ -114,7 +114,7 @@ Adds or replaces vectors (full-record put). If `ids` aren't provided, UUIDs are
 
 **ids** (`string[]`): Optional vector IDs (auto-generated if not provided)
 
-### query()
+### `query()`
 
 Searches for nearest neighbors with optional metadata filtering.
 
@@ -130,7 +130,7 @@ Searches for nearest neighbors with optional metadata filtering.
 
 > **Note:** Results include `score = 1/(1 + distance)` so that higher is better while preserving the underlying distance ranking.
 
-### describeIndex()
+### `describeIndex()`
 
 Returns information about the index.
 
@@ -146,19 +146,19 @@ interface IndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 Deletes an index and its data.
 
 **indexName** (`string`): Index to delete.
 
-### listIndexes()
+### `listIndexes()`
 
 Lists all indexes in the configured vector bucket.
 
 Returns: `Promise<string[]>`
 
-### updateVector()
+### `updateVector()`
 
 Updates a vector or metadata for a specific ID within an index.
 
@@ -172,7 +172,7 @@ Updates a vector or metadata for a specific ID within an index.
 
 **update.metadata** (`Record<string, any>`): New metadata to update
 
-### deleteVector()
+### `deleteVector()`
 
 Deletes a specific vector by ID.
 
@@ -180,11 +180,11 @@ Deletes a specific vector by ID.
 
 **id** (`string`): ID to delete.
 
-### disconnect()
+### `disconnect()`
 
 Closes the underlying AWS SDK HTTP handler to free sockets.
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -197,7 +197,7 @@ interface QueryResult {
 }
 ```
 
-## Filter Syntax
+## Filter syntax
 
 S3 Vectors supports a strict subset of operators and value types. The Mastra filter translator:
 
@@ -238,7 +238,7 @@ S3 Vectors supports a strict subset of operators and value types. The Mastra fil
 
 > **Note:** If you set `nonFilterableMetadataKeys` at index creation, those keys are stored but **can't** be used in filters.
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught:
 
@@ -256,7 +256,7 @@ try {
 }
 ```
 
-## Environment Variables
+## Environment variables
 
 Typical environment variables when wiring your app:
 
@@ -264,7 +264,7 @@ Typical environment variables when wiring your app:
 - `AWS_REGION`: AWS region for the S3 Vectors bucket.
 - **AWS credentials**: via the standard AWS SDK provider chain (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_PROFILE`, etc.).
 
-## Best Practices
+## Best practices
 
 - Choose the metric (`cosine` or `euclidean`) to match your embedding model; `dotproduct` isn't supported.
 - Keep **filterable** metadata small and structured (string/number/boolean). Store large text (e.g., `content`) as **non-filterable**.

package/.docs/reference/vectors/turbopuffer.md

@@ -1,8 +1,8 @@
-# Turbopuffer Vector Store
+# Turbopuffer vector store
 
 The TurbopufferVector class provides vector search using [Turbopuffer](https://turbopuffer.com/), a high-performance vector database optimized for RAG applications. Turbopuffer offers fast vector similarity search with advanced filtering capabilities and efficient storage management.
 
-## Constructor Options
+## Constructor options
 
 **apiKey** (`string`): The API key to authenticate with Turbopuffer
 
@@ -20,7 +20,7 @@ The TurbopufferVector class provides vector search using [Turbopuffer](https://t
 
 ## Methods
 
-### createIndex()
+### `createIndex()`
 
 **indexName** (`string`): Name of the index to create
 
@@ -28,7 +28,7 @@ The TurbopufferVector class provides vector search using [Turbopuffer](https://t
 
 **metric** (`'cosine' | 'euclidean' | 'dotproduct'`): Distance metric for similarity search (Default: `cosine`)
 
-### upsert()
+### `upsert()`
 
 **vectors** (`number[][]`): Array of embedding vectors
 
@@ -36,7 +36,7 @@ The TurbopufferVector class provides vector search using [Turbopuffer](https://t
 
 **ids** (`string[]`): Optional vector IDs (auto-generated if not provided)
 
-### query()
+### `query()`
 
 **indexName** (`string`): Name of the index to query
 
@@ -48,11 +48,11 @@ The TurbopufferVector class provides vector search using [Turbopuffer](https://t
 
 **includeVector** (`boolean`): Whether to include vectors in the results (Default: `false`)
 
-### listIndexes()
+### `listIndexes()`
 
 Returns an array of index names as strings.
 
-### describeIndex()
+### `describeIndex()`
 
 **indexName** (`string`): Name of the index to describe
 
@@ -66,11 +66,11 @@ interface IndexStats {
 }
 ```
 
-### deleteIndex()
+### `deleteIndex()`
 
 **indexName** (`string`): Name of the index to delete
 
-### updateVector()
+### `updateVector()`
 
 Update a single vector by ID or by metadata filter. Either `id` or `filter` must be provided, but not both.
 
@@ -82,13 +82,13 @@ Update a single vector by ID or by metadata filter. Either `id` or `filter` must
 
 **update** (`{ vector?: number[]; metadata?: Record<string, any>; }`): Object containing the vector and/or metadata to update
 
-### deleteVector()
+### `deleteVector()`
 
 **indexName** (`string`): Name of the index containing the vector
 
 **id** (`string`): ID of the vector to delete
 
-### deleteVectors()
+### `deleteVectors()`
 
 Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` must be provided, but not both.
 
@@ -98,7 +98,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 **filter** (`Record<string, any>`): Metadata filter to identify vectors to delete (mutually exclusive with ids)
 
-## Response Types
+## Response types
 
 Query results are returned in this format:
 
@@ -111,7 +111,7 @@ interface QueryResult {
 }
 ```
 
-## Schema Configuration
+## Schema configuration
 
 The `schemaConfigForIndex` option allows you to define explicit schemas for different indexes:
 
@@ -134,7 +134,7 @@ schemaConfigForIndex: (indexName: string) => {
 }
 ```
 
-## Error Handling
+## Error handling
 
 The store throws typed errors that can be caught: