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

package/.docs/reference/server/mastra-server.md

@@ -52,7 +52,7 @@ constructor(options: MastraServerOptions<TApp>)
 
 These methods must be implemented by adapters:
 
-### registerContextMiddleware()
+### `registerContextMiddleware()`
 
 Attach Mastra context to every request.
 
@@ -67,7 +67,7 @@ abstract registerContextMiddleware(): void
 - `tools` - Available tools
 - `abortSignal` - Request cancellation signal
 
-### registerAuthMiddleware()
+### `registerAuthMiddleware()`
 
 Register authentication and authorization middleware.
 
@@ -75,7 +75,7 @@ Register authentication and authorization middleware.
 abstract registerAuthMiddleware(): void
 ```
 
-### registerRoute()
+### `registerRoute()`
 
 Register a single route with the framework.
 
@@ -87,7 +87,7 @@ abstract registerRoute(
 ): Promise<void>
 ```
 
-### getParams()
+### `getParams()`
 
 Extract parameters from the request.
 
@@ -102,7 +102,7 @@ abstract getParams(
 }>
 ```
 
-### sendResponse()
+### `sendResponse()`
 
 Send response based on route type.
 
@@ -114,7 +114,7 @@ abstract sendResponse(
 ): Promise<unknown>
 ```
 
-### stream()
+### `stream()`
 
 Handle streaming responses.
 
@@ -128,7 +128,7 @@ abstract stream(
 
 ## Instance methods
 
-### init()
+### `init()`
 
 Initialize the server by registering all middleware and routes.
 
@@ -142,7 +142,7 @@ Calls in order:
 2. `registerAuthMiddleware()`
 3. `registerRoutes()`
 
-### registerRoutes()
+### `registerRoutes()`
 
 Register all Mastra routes.
 
@@ -150,7 +150,7 @@ Register all Mastra routes.
 async registerRoutes(): Promise<void>
 ```
 
-### getApp()
+### `getApp()`
 
 Get the framework app instance.
 
@@ -158,7 +158,7 @@ Get the framework app instance.
 getApp<T = TApp>(): T
 ```
 
-### parsePathParams()
+### `parsePathParams()`
 
 Validate path parameters with the route's Zod schema.
 
@@ -169,7 +169,7 @@ async parsePathParams(
 ): Promise<Record<string, unknown>>
 ```
 
-### parseQueryParams()
+### `parseQueryParams()`
 
 Validate query parameters with the route's Zod schema.
 
@@ -180,7 +180,7 @@ async parseQueryParams(
 ): Promise<Record<string, unknown>>
 ```
 
-### parseBody()
+### `parseBody()`
 
 Validate request body with the route's Zod schema.
 
@@ -191,7 +191,7 @@ async parseBody(
 ): Promise<unknown>
 ```
 
-### registerOpenAPIRoute()
+### `registerOpenAPIRoute()`
 
 Register an endpoint that serves the OpenAPI specification.
 
@@ -205,7 +205,7 @@ async registerOpenAPIRoute(
 
 ## Protected methods
 
-### mergeRequestContext()
+### `mergeRequestContext()`
 
 Merge request context from multiple sources (query params and body).
 
@@ -218,7 +218,7 @@ protected mergeRequestContext(options: {
 
 ## Types
 
-### BodyLimitOptions
+### `BodyLimitOptions`
 
 ```typescript
 interface BodyLimitOptions {
@@ -227,7 +227,7 @@ interface BodyLimitOptions {
 }
 ```
 
-### StreamOptions
+### `StreamOptions`
 
 ```typescript
 interface StreamOptions {

package/.docs/reference/server/register-api-route.md

@@ -32,7 +32,7 @@ registerApiRoute("/items/:itemId", { ... })
 
 **openapi** (`DescribeRouteOptions`): OpenAPI metadata for Swagger UI documentation
 
-## OpenAPI Options
+## OpenAPI options
 
 The `openapi` property accepts standard OpenAPI 3.1 operation fields from [hono-openapi](https://github.com/honojs/middleware/tree/main/packages/openapi). Routes without an `openapi` property aren't included in Swagger UI.
 
@@ -52,11 +52,11 @@ The `openapi` property accepts standard OpenAPI 3.1 operation fields from [hono-
 
 **security** (`SecurityRequirementObject[]`): Security requirements for the operation
 
-## Return Value
+## Return value
 
 Returns an `ApiRoute` object to be passed to `server.apiRoutes` in the Mastra configuration.
 
-## Handler Context
+## Handler context
 
 The handler receives a Hono `Context` object with access to:
 
@@ -201,7 +201,7 @@ registerApiRoute('/items/:itemId', {
 })
 ```
 
-### Using createHandler
+### Using `createHandler()`
 
 For routes that need async initialization:
 
@@ -219,7 +219,7 @@ registerApiRoute('/dynamic', {
 })
 ```
 
-## Error Handling
+## Error handling
 
 Throw errors with status codes using Hono's `HTTPException`:
 

package/.docs/reference/server/routes.md

@@ -1,4 +1,4 @@
-# Server Routes
+# Server routes
 
 Server adapters register these routes when you call `server.init()`. All routes are prefixed with the `prefix` option if configured.
 

package/.docs/reference/storage/cloudflare-d1.md

@@ -1,4 +1,4 @@
-# Cloudflare D1 Storage
+# Cloudflare D1 storage
 
 The Cloudflare D1 storage implementation provides a serverless SQL database solution using Cloudflare D1, supporting relational operations and transactional consistency.
 
@@ -139,7 +139,7 @@ Or in `wrangler.jsonc`:
 
 **tablePrefix** (`string`): Optional prefix for all table names (useful for environment isolation)
 
-## Additional Notes
+## Additional notes
 
 ### Schema Management
 

package/.docs/reference/storage/cloudflare.md

@@ -1,4 +1,4 @@
-# Cloudflare Storage
+# Cloudflare storage
 
 The Cloudflare KV storage implementation provides a globally distributed, serverless key-value store solution using Cloudflare Workers KV.
 
@@ -69,7 +69,7 @@ const storageRest = new CloudflareStore({
 
 **keyPrefix** (`string`): Optional prefix for all keys (useful for environment isolation)
 
-### Additional Notes
+### Additional notes
 
 ### Schema Management
 

package/.docs/reference/storage/composite.md

@@ -1,4 +1,4 @@
-# Composite Storage
+# Composite storage
 
 `MastraCompositeStore` can compose storage domains from different providers. Use it when you need different databases for different purposes. For example, use LibSQL for memory and PostgreSQL for workflows.
 

package/.docs/reference/storage/convex.md

@@ -1,4 +1,4 @@
-# Convex Storage
+# Convex storage
 
 The Convex storage implementation provides a serverless storage solution using [Convex](https://convex.dev), a full-stack TypeScript development platform with real-time sync and automatic caching.
 
@@ -32,7 +32,7 @@ yarn add @mastra/convex@latest
 bun add @mastra/convex@latest
 ```
 
-## Convex Setup
+## Convex setup
 
 Before using `ConvexStore`, you need to set up the Convex schema and storage handler in your Convex project.
 
@@ -103,7 +103,7 @@ const storage = new ConvexStore({
 
 **storageFunction** (`string`): Path to the storage mutation function (default: 'mastra/storage:handle') (Default: `mastra/storage:handle`)
 
-## Constructor Examples
+## Constructor examples
 
 ```ts
 import { ConvexStore } from '@mastra/convex'
@@ -124,7 +124,7 @@ const storeCustom = new ConvexStore({
 })
 ```
 
-## Additional Notes
+## Additional notes
 
 ### Schema Management
 
@@ -148,7 +148,7 @@ All typed tables include:
 
 This design ensures compatibility with Mastra's storage contract while leveraging Convex's automatic indexing and real-time capabilities.
 
-### Environment Variables
+### Environment variables
 
 Set these environment variables for your deployment:
 

package/.docs/reference/storage/dynamodb.md

@@ -1,4 +1,4 @@
-# DynamoDB Storage
+# DynamoDB storage
 
 The DynamoDB storage implementation provides a scalable and performant NoSQL database solution for Mastra, leveraging a single-table design pattern with [ElectroDB](https://electrodb.dev/).
 
@@ -120,7 +120,7 @@ For local development, you can use [DynamoDB Local](https://docs.aws.amazon.com/
 
 **config.ttl** (`object`): TTL (Time To Live) configuration for automatic data expiration. Configure per entity type: thread, message, trace, eval, workflow\_snapshot, resource, score. Each entity config includes: enabled (boolean), attributeName (string, default: 'ttl'), defaultTtlSeconds (number).
 
-## TTL (Time To Live) Configuration
+## TTL (time to live) configuration
 
 DynamoDB TTL allows you to automatically delete items after a specified time period. This is useful for:
 
@@ -216,7 +216,7 @@ aws dynamodb update-time-to-live \
 
 > **Note:** DynamoDB deletes expired items within 48 hours after expiration. Items remain queryable until actually deleted.
 
-## AWS IAM Permissions
+## AWS IAM permissions
 
 The IAM role or user executing the code needs appropriate permissions to interact with the specified DynamoDB table and its indexes. Below is a sample policy. Replace `${YOUR_TABLE_NAME}` with your actual table name and `${YOUR_AWS_REGION}` and `${YOUR_AWS_ACCOUNT_ID}` with appropriate values.
 
@@ -246,7 +246,7 @@ The IAM role or user executing the code needs appropriate permissions to interac
 }
 ```
 
-## Key Considerations
+## Key considerations
 
 Before diving into the architectural details, keep these key points in mind when working with the DynamoDB storage adapter:
 
@@ -255,7 +255,7 @@ Before diving into the architectural details, keep these key points in mind when
 - **Understanding GSIs:** Familiarity with how the GSIs are structured (as per `TABLE_SETUP.md`) is important for understanding data retrieval and potential query patterns.
 - **ElectroDB:** The adapter uses ElectroDB to manage interactions with DynamoDB, providing a layer of abstraction and type safety over raw DynamoDB operations.
 
-## Architectural Approach
+## Architectural approach
 
 This storage adapter utilizes a **single-table design pattern** leveraging [ElectroDB](https://electrodb.dev/), a common and recommended approach for DynamoDB. This differs architecturally from relational database adapters (like `@mastra/pg` or `@mastra/libsql`) that typically use multiple tables, each dedicated to a specific entity (threads, messages, etc.).
 

package/.docs/reference/storage/lance.md

@@ -1,4 +1,4 @@
-# LanceDB Storage
+# LanceDB storage
 
 The LanceDB storage implementation provides a high-performance storage solution using the LanceDB database system, which excels at handling both traditional data storage and vector operations.
 
@@ -51,7 +51,7 @@ const storage = await LanceStorage.create('my-storage', 's3://bucket/db', {
 
 ## Parameters
 
-### LanceStorage.create()
+### `LanceStorage.create()`
 
 **name** (`string`): Name identifier for the storage instance
 
@@ -59,7 +59,7 @@ const storage = await LanceStorage.create('my-storage', 's3://bucket/db', {
 
 **options** (`ConnectionOptions`): Connection options for LanceDB, such as timeout settings, authentication, etc.
 
-## Additional Notes
+## Additional notes
 
 ### Schema Management
 

package/.docs/reference/storage/libsql.md

@@ -1,4 +1,4 @@
-# libSQL Storage
+# libSQL storage
 
 [libSQL](https://docs.turso.tech/libsql) is an open-source, SQLite-compatible database that supports both local and remote deployments. It can be used to store message history, workflow snapshots, traces, and eval scores.
 

package/.docs/reference/storage/mongodb.md

@@ -1,4 +1,4 @@
-# MongoDB Storage
+# MongoDB storage
 
 The MongoDB storage implementation provides a scalable storage solution using MongoDB databases with support for both document storage and vector operations.
 
@@ -56,7 +56,7 @@ const storage = new MongoDBStore({
 
 > **Deprecation Notice:** The `url` parameter is deprecated but still supported for backward compatibility. Please use `uri` instead in all new code.
 
-## Constructor Examples
+## Constructor examples
 
 You can instantiate `MongoDBStore` in the following ways:
 
@@ -84,7 +84,7 @@ const store2 = new MongoDBStore({
 })
 ```
 
-## Additional Notes
+## Additional notes
 
 ### Collection Management
 
@@ -138,7 +138,7 @@ const thread = await memoryStore?.getThreadById({ threadId: '...' })
 
 > **Warning:** If `init()` isn't called, collections won't be created and storage operations will fail silently or throw errors.
 
-## Vector Search Capabilities
+## Vector search capabilities
 
 MongoDB storage includes built-in vector search capabilities for AI applications:
 
@@ -190,7 +190,7 @@ const results = await vectorStore.query({
 });
 ```
 
-## Usage Example
+## Usage example
 
 ### Adding memory to an agent
 

package/.docs/reference/storage/mssql.md

@@ -1,4 +1,4 @@
-# MSSQL Storage
+# MSSQL storage
 
 The MSSQL storage implementation provides a production-ready storage solution using Microsoft SQL Server databases.
 
@@ -45,7 +45,7 @@ const storage = new MSSQLStore({
 
 **schemaName** (`string`): The name of the schema you want the storage to use. Will use the default schema if not provided.
 
-## Constructor Examples
+## Constructor examples
 
 You can instantiate `MSSQLStore` in the following ways:
 
@@ -89,7 +89,7 @@ const store5 = new MSSQLStore({
 })
 ```
 
-## Additional Notes
+## Additional notes
 
 ### Schema Management
 

package/.docs/reference/storage/overview.md

@@ -1,8 +1,8 @@
-# Storage Overview
+# Storage overview
 
 Mastra requires the following tables to be present in the database.
 
-## Core Schema
+## Core schema
 
 **Messages**:
 

package/.docs/reference/storage/postgresql.md

@@ -1,4 +1,4 @@
-# PostgreSQL Storage
+# PostgreSQL storage
 
 The PostgreSQL storage implementation provides a production-ready storage solution using PostgreSQL databases.
 
@@ -71,7 +71,7 @@ const storage = new PostgresStore({
 
 **indexes** (`CreateIndexOptions[]`): Custom indexes to create during initialization.
 
-## Constructor Examples
+## Constructor examples
 
 You can instantiate `PostgresStore` in the following ways:
 
@@ -119,7 +119,7 @@ const store4 = new PostgresStore({
 })
 ```
 
-## Additional Notes
+## Additional notes
 
 ### Schema Management
 
@@ -316,7 +316,7 @@ This pattern ensures only one `PostgresStore` instance is created regardless of
 
 > **Tip:** This singleton pattern is only necessary during local development with HMR. In production builds, modules are only loaded once.
 
-## Usage Example
+## Usage example
 
 ### Adding memory to an agent
 
@@ -387,7 +387,7 @@ for await (const chunk of stream.textStream) {
 }
 ```
 
-## Index Management
+## Index management
 
 PostgreSQL storage provides index management to optimize query performance.
 

package/.docs/reference/storage/upstash.md

@@ -1,4 +1,4 @@
-# Upstash Storage
+# Upstash storage
 
 The Upstash storage implementation provides a serverless-friendly storage solution using Upstash's Redis-compatible key-value store.
 
@@ -52,7 +52,7 @@ const storage = new UpstashStore({
 
 **prefix** (`string`): Key prefix for all stored items (Default: `mastra:`)
 
-## Additional Notes
+## Additional notes
 
 ### Key Structure
 
@@ -87,7 +87,7 @@ For optimal performance:
 - Monitor Redis memory usage
 - Consider data expiration policies if needed
 
-## Usage Example
+## Usage example
 
 ### Adding memory to an agent
 

package/.docs/reference/streaming/ChunkType.md

@@ -2,7 +2,7 @@
 
 The `ChunkType` type defines the mastra format of stream chunks that can be emitted during streaming responses from agents.
 
-## Base Properties
+## Base properties
 
 All chunks include these base properties:
 
@@ -20,7 +20,7 @@ All chunks include these base properties:
 
 **from.WORKFLOW** (`'WORKFLOW'`): Chunk from workflow execution
 
-## Text Chunks
+## Text chunks
 
 ### text-start
 
@@ -60,7 +60,7 @@ Signals the end of text generation.
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-## Reasoning Chunks
+## Reasoning chunks
 
 ### reasoning-start
 
@@ -118,7 +118,7 @@ Contains the reasoning signature from models that support advanced reasoning (li
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-## Tool Chunks
+## Tool chunks
 
 ### tool-call
 
@@ -162,7 +162,7 @@ Result from a tool execution.
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-### tool-call-input-streaming-start
+### `tool-call-input-streaming-start`
 
 Signals the start of streaming tool call arguments.
 
@@ -180,7 +180,7 @@ Signals the start of streaming tool call arguments.
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-### tool-call-delta
+### `tool-call-delta`
 
 Incremental tool call arguments during streaming.
 
@@ -196,7 +196,7 @@ Incremental tool call arguments during streaming.
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-### tool-call-input-streaming-end
+### `tool-call-input-streaming-end`
 
 Signals the end of streaming tool call arguments.
 
@@ -230,7 +230,7 @@ An error occurred during tool execution.
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-## Source and File Chunks
+## Source and file chunks
 
 ### source
 
@@ -270,7 +270,7 @@ Contains file data.
 
 **payload.providerMetadata** (`SharedV2ProviderMetadata`): Provider-specific metadata
 
-## Control Chunks
+## Control chunks
 
 ### start
 
@@ -368,7 +368,7 @@ Stream was aborted.
 
 **payload.\[key: string]** (`any`): Additional abort data
 
-## Object and Output Chunks
+## Object and output chunks
 
 ### object
 
@@ -398,7 +398,7 @@ Contains output from workflow step execution, used primarily for usage tracking
 
 **payload.output** (`ChunkType`): Nested chunk data from step execution, typically containing finish events or other step results
 
-## Metadata and Special Chunks
+## Metadata and special chunks
 
 ### response-metadata
 
@@ -442,7 +442,7 @@ Emitted when the stream is forcibly terminated due to content being blocked by a
 
 **payload.processorId** (`string`): ID of the processor that triggered the tripwire
 
-## Usage Example
+## Usage example
 
 ```typescript
 const stream = await agent.stream('Hello')
@@ -477,7 +477,7 @@ for await (const chunk of stream.fullStream) {
 }
 ```
 
-## Related Types
+## Related types
 
 - [.stream()](https://mastra.ai/reference/streaming/agents/stream) - Method that returns streams emitting these chunks
 - [MastraModelOutput](https://mastra.ai/reference/streaming/agents/MastraModelOutput) - The stream object that emits these chunks

package/.docs/reference/streaming/agents/MastraModelOutput.md

@@ -9,7 +9,7 @@ const stream = await agent.stream('Hello world')
 
 For setup and basic usage, see the [.stream()](https://mastra.ai/reference/streaming/agents/stream) method documentation.
 
-## Streaming Properties
+## Streaming properties
 
 These properties provide real-time access to model outputs as they're generated:
 
@@ -25,7 +25,7 @@ These properties provide real-time access to model outputs as they're generated:
 
 **elementStream** (`ReadableStream<OUTPUT extends (infer T)[] ? T : never>`): Stream of individual array elements when the output schema defines an array type. Each element is emitted as it's completed rather than waiting for the entire array.
 
-## Promise-based Properties
+## Promise-based properties
 
 These properties resolve to final values after the stream completes:
 
@@ -95,7 +95,7 @@ These properties resolve to final values after the stream completes:
 
 **response.uiMessages** (`UIMessage[]`): Response messages in UI format, includes any metadata added by output processors
 
-## Error Properties
+## Error properties
 
 **error** (`string | Error | { message: string; stack: string; } | undefined`): Error information if the stream encountered an error. Undefined if no errors occurred. Can be a string message, Error object, or serialized error with stack trace.
 
@@ -123,7 +123,7 @@ These properties resolve to final values after the stream completes:
 
 **consumeStream.onError** (`(error: Error) => void`): Callback for handling stream errors
 
-## Usage Examples
+## Usage examples
 
 ### Basic Text Streaming
 
@@ -221,7 +221,7 @@ for await (const chunk of stream.fullStream) {
 }
 ```
 
-### Error Handling
+### Error handling
 
 ```typescript
 const stream = await agent.stream('Analyze this data')
@@ -246,7 +246,7 @@ if (stream.error) {
 }
 ```
 
-## Related Types
+## Related types
 
 - [.stream()](https://mastra.ai/reference/streaming/agents/stream) - Method that returns MastraModelOutput
 - [ChunkType](https://mastra.ai/reference/streaming/ChunkType) - All possible chunk types in the full stream

package/.docs/reference/streaming/agents/stream.md

@@ -290,7 +290,7 @@ for await (const chunk of stream.textStream) {
 }
 ```
 
-### Advanced Example with Options
+### Advanced example with Options
 
 ```ts
 import { z } from 'zod'
@@ -323,7 +323,7 @@ await agent.stream('message for agent', {
 })
 ```
 
-## OpenAI WebSocket Transport
+## OpenAI WebSocket transport
 
 Opt into OpenAI Responses WebSocket streaming via `providerOptions.openai.transport`. This only applies to streaming calls and is currently supported for direct OpenAI models (for example, `openai/gpt-4o`). If WebSocket streaming is unavailable, Mastra falls back to HTTP streaming. By default, Mastra closes the WebSocket when the stream finishes.
 

package/.docs/reference/streaming/agents/streamLegacy.md

@@ -146,7 +146,7 @@ await agent.streamLegacy('message for agent', {
 })
 ```
 
-## Migration to New API
+## Migration to new API
 
 > **Info:** The new `.stream()` method offers enhanced capabilities including AI SDK v5+ compatibility, better structured output handling, and improved callback system. See the [migration guide](https://mastra.ai/guides/migrations/vnext-to-standard-apis) for detailed migration instructions.