@mastra/mcp-docs-server 1.1.8 → 1.1.9-alpha.1

package/.docs/reference/observability/tracing/processors/sensitive-data-filter.md

@@ -8,7 +8,7 @@ A SpanOutputProcessor that redacts sensitive information from span fields.
 new SensitiveDataFilter(options?: SensitiveDataFilterOptions)
 ```
 
-## SensitiveDataFilterOptions
+## `SensitiveDataFilterOptions`
 
 ```typescript
 interface SensitiveDataFilterOptions {
@@ -38,7 +38,7 @@ interface SensitiveDataFilterOptions {
 }
 ```
 
-## RedactionStyle
+## `RedactionStyle`
 
 ```typescript
 type RedactionStyle = 'full' | 'partial'
@@ -70,7 +70,7 @@ No cleanup needed for this processor.
 readonly name = 'sensitive-data-filter';
 ```
 
-## Default Sensitive Fields
+## Default sensitive fields
 
 When no custom fields are provided:
 
@@ -94,7 +94,7 @@ When no custom fields are provided:
 ]
 ```
 
-## Processing Behavior
+## Processing behavior
 
 ### Field Matching
 
@@ -105,7 +105,7 @@ When no custom fields are provided:
 - **Exact matching**: After normalization, fields must match exactly
 
   - `token` matches `token`, `Token`, `TOKEN`
-  - `token` does NOT match `promptTokens` or `tokenCount`
+  - `token` doesn't match `promptTokens` or `tokenCount`
 
 ### Redaction Styles
 
@@ -119,7 +119,7 @@ All matched values replaced with redactionToken.
 - Values ≤ 6 characters are fully redacted
 - Non-string values are converted to strings before partial redaction
 
-### Error Handling
+### Error handling
 
 If filtering a field fails, the field is replaced with:
 

package/.docs/reference/observability/tracing/spans.md

@@ -1,6 +1,6 @@
 # Spans
 
-## BaseSpan
+## `BaseSpan`
 
 Base interface for all span types.
 
@@ -45,6 +45,8 @@ interface BaseSpan<TType extends SpanType> {
     details?: Record<string, any>
   }
 
+  /** Snapshot of the RequestContext */
+  requestContext?: Record<string, any>
   /** Is an event span? (occurs at startTime, has no endTime) */
   isEvent: boolean
 }
@@ -109,7 +111,7 @@ update(options: UpdateSpanOptions<TType>): void
 
 Updates span data while it's still active. Can modify `input`, `output`, `metadata`, and `attributes`.
 
-#### createChildSpan
+#### `createChildSpan`
 
 ```typescript
 createChildSpan<TChildType extends SpanType>(
@@ -119,7 +121,7 @@ createChildSpan<TChildType extends SpanType>(
 
 Creates a child span under this span. Child spans track sub-operations and inherit the trace context.
 
-#### createEventSpan
+#### `createEventSpan`
 
 ```typescript
 createEventSpan<TChildType extends SpanType>(
@@ -129,7 +131,7 @@ createEventSpan<TChildType extends SpanType>(
 
 Creates an event span under this span. Event spans represent point-in-time occurrences with no duration.
 
-## ExportedSpan
+## `ExportedSpan`
 
 Exported Span interface, used for tracing exporters. A lightweight version of Span without methods or circular references.
 
@@ -143,11 +145,11 @@ interface ExportedSpan<TType extends SpanType> extends BaseSpan<TType> {
 }
 ```
 
-## Span Lifecycle Events
+## Span lifecycle events
 
 Events emitted during the span lifecycle.
 
-### TracingEventType
+### `TracingEventType`
 
 ```typescript
 enum TracingEventType {
@@ -162,7 +164,7 @@ enum TracingEventType {
 }
 ```
 
-### TracingEvent
+### `TracingEvent`
 
 ```typescript
 type TracingEvent =
@@ -173,9 +175,9 @@ type TracingEvent =
 
 Exporters receive these events to process and send trace data to observability platforms.
 
-## Union Types
+## Union types
 
-### AnySpan
+### `AnySpan`
 
 ```typescript
 type AnySpan = Span<keyof SpanTypeMap>
@@ -183,7 +185,7 @@ type AnySpan = Span<keyof SpanTypeMap>
 
 Union type for cases that need to handle any span type.
 
-### AnyExportedSpan
+### `AnyExportedSpan`
 
 ```typescript
 type AnyExportedSpan = ExportedSpan<keyof SpanTypeMap>
@@ -191,11 +193,11 @@ type AnyExportedSpan = ExportedSpan<keyof SpanTypeMap>
 
 Union type for cases that need to handle any exported span type.
 
-## NO-OP Spans
+## NO-OP spans
 
 When tracing is disabled (sampling returns false), NO-OP spans are returned:
 
-### NoOpSpan
+### `NoOpSpan`
 
 ```typescript
 class NoOpSpan<TType extends SpanType> extends BaseSpan<TType>
@@ -209,7 +211,7 @@ A span that performs no operations. All methods are no-ops:
 - `end()`, `error()`, `update()` do nothing
 - `createChildSpan()` returns another NO-OP span
 
-## See Also
+## See also
 
 ### Documentation
 

package/.docs/reference/processors/message-history-processor.md

@@ -66,7 +66,7 @@ export const agent = new Agent({
 
 1. Retrieves `threadId` from the request context
 2. Fetches historical messages from storage (ordered by creation date, descending)
-3. Filters out system messages (they should not be stored in the database)
+3. Filters out system messages (they shouldn't be stored in the database)
 4. Merges historical messages with incoming messages, avoiding duplicates by ID
 5. Adds historical messages with `source: 'memory'` tag
 

package/.docs/reference/processors/processor-interface.md

@@ -1,4 +1,4 @@
-# Processor Interface
+# Processor interface
 
 The `Processor` interface defines the contract for all processors in Mastra. Processors can implement one or more methods to handle different stages of the agent execution pipeline.
 
@@ -86,15 +86,15 @@ interface Processor<TId extends string = string> {
 
 ## Methods
 
-### processInput
+### `processInput`
 
-Processes input messages before they are sent to the LLM. Runs once at the start of agent execution.
+Processes input messages before they're sent to the LLM. Runs once at the start of agent execution.
 
 ```typescript
 processInput?(args: ProcessInputArgs): Promise<ProcessInputResult> | ProcessInputResult;
 ```
 
-#### ProcessInputArgs
+#### `ProcessInputArgs`
 
 **messages** (`MastraDBMessage[]`): User and assistant messages to process (excludes system messages).
 
@@ -110,7 +110,7 @@ processInput?(args: ProcessInputArgs): Promise<ProcessInputResult> | ProcessInpu
 
 **requestContext** (`RequestContext`): Request-scoped context with execution metadata like threadId and resourceId.
 
-#### ProcessInputResult
+#### `ProcessInputResult`
 
 The method can return one of three types:
 
@@ -122,9 +122,9 @@ The method can return one of three types:
 
 ***
 
-### processInputStep
+### `processInputStep`
 
-Processes input messages at each step of the agentic loop, before they are sent to the LLM. Unlike `processInput` which runs once at the start, this runs at every step including tool call continuations.
+Processes input messages at each step of the agentic loop, before they're sent to the LLM. Unlike `processInput` which runs once at the start, this runs at every step including tool call continuations.
 
 ```typescript
 processInputStep?(args: ProcessInputStepArgs): ProcessorMessageResult;
@@ -139,7 +139,7 @@ processInputStep?(args: ProcessInputStepArgs): ProcessorMessageResult;
 5. Tool execution (if needed)
 6. Repeat from step 2 if tools were called
 
-#### ProcessInputStepArgs
+#### `ProcessInputStepArgs`
 
 **messages** (`MastraDBMessage[]`): All messages including tool calls and results from previous steps (read-only snapshot).
 
@@ -171,7 +171,7 @@ processInputStep?(args: ProcessInputStepArgs): ProcessorMessageResult;
 
 **requestContext** (`RequestContext`): Request-scoped context with execution metadata.
 
-#### ProcessInputStepResult
+#### `ProcessInputStepResult`
 
 The method can return any combination of these properties:
 
@@ -222,7 +222,7 @@ System messages are **reset to their original values** at the start of each step
 
 ***
 
-### processOutputStream
+### `processOutputStream`
 
 Processes streaming output chunks with built-in state management. Allows processors to accumulate chunks and make decisions based on larger context.
 
@@ -230,7 +230,7 @@ Processes streaming output chunks with built-in state management. Allows process
 processOutputStream?(args: ProcessOutputStreamArgs): Promise<ChunkType | null | undefined>;
 ```
 
-#### ProcessOutputStreamArgs
+#### `ProcessOutputStreamArgs`
 
 **part** (`ChunkType`): The current stream chunk being processed.
 
@@ -255,7 +255,7 @@ processOutputStream?(args: ProcessOutputStreamArgs): Promise<ChunkType | null |
 
 ***
 
-### processOutputResult
+### `processOutputResult`
 
 Processes the complete output result after streaming or generation is finished.
 
@@ -263,12 +263,16 @@ Processes the complete output result after streaming or generation is finished.
 processOutputResult?(args: ProcessOutputResultArgs): ProcessorMessageResult;
 ```
 
-#### ProcessOutputResultArgs
+#### `ProcessOutputResultArgs`
 
 **messages** (`MastraDBMessage[]`): The generated response messages.
 
 **messageList** (`MessageList`): MessageList instance for managing messages.
 
+**state** (`Record<string, unknown>`): Per-processor state that persists across all method calls within this request. Shared with processOutputStream and other methods.
+
+**result** (`OutputResult`): Resolved generation result containing \`text\` (accumulated text), \`usage\` (token usage with inputTokens, outputTokens, totalTokens), \`finishReason\` (why generation ended), and \`steps\` (all LLM step results, each with toolCalls, toolResults, reasoning, sources, files, etc.).
+
 **abort** (`(reason?: string) => never`): Function to abort processing.
 
 **tracingContext** (`TracingContext`): Tracing context for observability.
@@ -279,7 +283,7 @@ processOutputResult?(args: ProcessOutputResultArgs): ProcessorMessageResult;
 
 ***
 
-### processOutputStep
+### `processOutputStep`
 
 Processes output after each LLM response in the agentic loop, before tool execution. Unlike `processOutputResult` which runs once at the end, this runs at every step. This is the ideal method for implementing guardrails that can trigger retries.
 
@@ -287,7 +291,7 @@ Processes output after each LLM response in the agentic loop, before tool execut
 processOutputStep?(args: ProcessOutputStepArgs): ProcessorMessageResult;
 ```
 
-#### ProcessOutputStepArgs
+#### `ProcessOutputStepArgs`
 
 **messages** (`MastraDBMessage[]`): All messages including the latest LLM response.
 
@@ -388,7 +392,7 @@ export class LowercaseProcessor implements Processor {
 }
 ```
 
-### Per-step processor with processInputStep
+### Per-step processor with `processInputStep`
 
 ```typescript
 import type { Processor, ProcessInputStepArgs, ProcessInputStepResult } from '@mastra/core'
@@ -421,7 +425,7 @@ export class DynamicModelProcessor implements Processor {
 }
 ```
 
-### Message transformer with processInputStep
+### Message transformer with `processInputStep`
 
 ```typescript
 import type { Processor, MastraDBMessage } from '@mastra/core'

package/.docs/reference/processors/token-limiter-processor.md

@@ -47,8 +47,8 @@ const processor = new TokenLimiterProcessor({
 
 When used as an input processor, `TokenLimiterProcessor` throws a `TripWire` error in the following cases:
 
-- **Empty messages**: If there are no messages to process, a TripWire is thrown because you cannot send an LLM request with no messages.
-- **System messages exceed limit**: If system messages alone exceed the token limit, a TripWire is thrown because you cannot send an LLM request with only system messages and no user/assistant messages.
+- **Empty messages**: If there are no messages to process, a TripWire is thrown because you can't send an LLM request with no messages.
+- **System messages exceed limit**: If system messages alone exceed the token limit, a TripWire is thrown because you can't send an LLM request with only system messages and no user/assistant messages.
 
 ```typescript
 import { TripWire } from '@mastra/core/agent'

package/.docs/reference/rag/chunk.md

@@ -57,7 +57,7 @@ The following parameters are available for all chunking strategies. **Important:
 
 See [ExtractParams reference](https://mastra.ai/reference/rag/extract-params) for details on the `extract` parameter.
 
-## Strategy-Specific Options
+## Strategy-specific options
 
 Strategy-specific options are passed as top-level parameters alongside the strategy parameter. For example:
 
@@ -208,7 +208,7 @@ The options documented below are passed directly at the top level of the configu
 
 The Latex strategy uses only the general chunking options listed above. It provides LaTeX-aware splitting optimized for mathematical and academic documents.
 
-## Return Value
+## Return value
 
 Returns a `MDocument` instance containing the chunked documents. Each chunk includes:
 

package/.docs/reference/rag/database-config.md

@@ -2,7 +2,7 @@
 
 The `DatabaseConfig` type allows you to specify database-specific configurations when using vector query tools. These configurations enable you to leverage unique features and optimizations offered by different vector stores.
 
-## Type Definition
+## Type definition
 
 ```typescript
 export type DatabaseConfig = {
@@ -13,9 +13,9 @@ export type DatabaseConfig = {
 }
 ```
 
-## Database-Specific Types
+## Database-specific types
 
-### PineconeConfig
+### `PineconeConfig`
 
 Configuration options specific to Pinecone vector store.
 
@@ -33,7 +33,7 @@ Configuration options specific to Pinecone vector store.
 - Environment isolation (dev/staging/prod namespaces)
 - Hybrid search combining semantic and keyword matching
 
-### PgVectorConfig
+### `PgVectorConfig`
 
 Configuration options specific to PostgreSQL with pgvector extension.
 
@@ -55,7 +55,7 @@ Configuration options specific to PostgreSQL with pgvector extension.
 - Quality filtering to remove irrelevant results
 - Fine-tuning search accuracy vs speed tradeoffs
 
-### ChromaConfig
+### `ChromaConfig`
 
 Configuration options specific to Chroma vector store.
 
@@ -88,7 +88,7 @@ whereDocument: { "$contains": "API documentation" }
 - Content-based document filtering
 - Complex query combinations
 
-## Usage Examples
+## Usage examples
 
 **Basic Usage**:
 
@@ -233,7 +233,7 @@ const vectorTool = createVectorQueryTool({
 })
 ```
 
-## Best Practices
+## Best practices
 
 1. **Environment Configuration**: Use different namespaces or configurations for different environments
 2. **Performance Tuning**: Start with default values and adjust based on your specific needs
@@ -241,7 +241,7 @@ const vectorTool = createVectorQueryTool({
 4. **Runtime Flexibility**: Override configurations at runtime for dynamic scenarios
 5. **Documentation**: Document your specific configuration choices for team members
 
-## Migration Guide
+## Migration guide
 
 Existing vector query tools continue to work without changes. To add database configurations:
 

package/.docs/reference/rag/document.md

@@ -8,9 +8,9 @@ The MDocument class processes documents for RAG applications. The main methods a
 
 **type** (`'text' | 'html' | 'markdown' | 'json' | 'latex'`): Type of document content
 
-## Static Methods
+## Static methods
 
-### fromText()
+### `fromText()`
 
 Creates a document from plain text content.
 
@@ -18,7 +18,7 @@ Creates a document from plain text content.
 static fromText(text: string, metadata?: Record<string, any>): MDocument
 ```
 
-### fromHTML()
+### `fromHTML()`
 
 Creates a document from HTML content.
 
@@ -26,7 +26,7 @@ Creates a document from HTML content.
 static fromHTML(html: string, metadata?: Record<string, any>): MDocument
 ```
 
-### fromMarkdown()
+### `fromMarkdown()`
 
 Creates a document from Markdown content.
 
@@ -34,7 +34,7 @@ Creates a document from Markdown content.
 static fromMarkdown(markdown: string, metadata?: Record<string, any>): MDocument
 ```
 
-### fromJSON()
+### `fromJSON()`
 
 Creates a document from JSON content.
 
@@ -42,9 +42,9 @@ Creates a document from JSON content.
 static fromJSON(json: string, metadata?: Record<string, any>): MDocument
 ```
 
-## Instance Methods
+## Instance methods
 
-### chunk()
+### `chunk()`
 
 Splits document into chunks and optionally extracts metadata.
 
@@ -54,7 +54,7 @@ async chunk(params?: ChunkParams): Promise<Chunk[]>
 
 See [chunk() reference](https://mastra.ai/reference/rag/chunk) for detailed options.
 
-### getDocs()
+### `getDocs()`
 
 Returns array of processed document chunks.
 
@@ -62,7 +62,7 @@ Returns array of processed document chunks.
 getDocs(): Chunk[]
 ```
 
-### getText()
+### `getText()`
 
 Returns array of text strings from chunks.
 
@@ -70,7 +70,7 @@ Returns array of text strings from chunks.
 getText(): string[]
 ```
 
-### getMetadata()
+### `getMetadata()`
 
 Returns array of metadata objects from chunks.
 
@@ -78,7 +78,7 @@ Returns array of metadata objects from chunks.
 getMetadata(): Record<string, any>[]
 ```
 
-### extractMetadata()
+### `extractMetadata()`
 
 Extracts metadata using specified extractors. See [ExtractParams reference](https://mastra.ai/reference/rag/extract-params) for details.
 

package/.docs/reference/rag/embeddings.md

@@ -2,7 +2,7 @@
 
 Mastra uses the AI SDK's `embed` and `embedMany` functions to generate vector embeddings for text inputs, enabling similarity search and RAG workflows.
 
-## Single Embedding
+## Single embedding
 
 The `embed` function generates a vector embedding for a single text input:
 
@@ -29,11 +29,11 @@ const result = await embed({
 
 **headers** (`Record<string, string>`): Additional HTTP headers for the request (only for HTTP-based providers)
 
-### Return Value
+### Return value
 
 **embedding** (`number[]`): The embedding vector for the input
 
-## Multiple Embeddings
+## Multiple embeddings
 
 For embedding multiple texts at once, use the `embedMany` function:
 
@@ -59,11 +59,11 @@ const result = await embedMany({
 
 **headers** (`Record<string, string>`): Additional HTTP headers for the request (only for HTTP-based providers)
 
-### Return Value
+### Return value
 
 **embeddings** (`number[][]`): Array of embedding vectors corresponding to the input values
 
-## Example Usage
+## Example usage
 
 ```typescript
 import { embed, embedMany } from 'ai'

package/.docs/reference/rag/extract-params.md

@@ -38,9 +38,9 @@ The `extract` parameter accepts the following fields:
 
 **schema** (`SchemaExtractArgs`): Enable structured metadata extraction using a Zod schema.
 
-## Extractor Arguments
+## Extractor arguments
 
-### TitleExtractorsArgs
+### `TitleExtractorsArgs`
 
 **llm** (`MastraLanguageModel`): AI SDK language model to use for title extraction
 
@@ -50,7 +50,7 @@ The `extract` parameter accepts the following fields:
 
 **combineTemplate** (`string`): Custom prompt template for combining titles. Must include {context} placeholder
 
-### SummaryExtractArgs
+### `SummaryExtractArgs`
 
 **llm** (`MastraLanguageModel`): AI SDK language model to use for summary extraction
 
@@ -58,7 +58,7 @@ The `extract` parameter accepts the following fields:
 
 **promptTemplate** (`string`): Custom prompt template for summary generation. Must include {context} placeholder
 
-### QuestionAnswerExtractArgs
+### `QuestionAnswerExtractArgs`
 
 **llm** (`MastraLanguageModel`): AI SDK language model to use for question generation
 
@@ -68,7 +68,7 @@ The `extract` parameter accepts the following fields:
 
 **embeddingOnly** (`boolean`): If true, only generate embeddings without actual questions
 
-### KeywordExtractArgs
+### `KeywordExtractArgs`
 
 **llm** (`MastraLanguageModel`): AI SDK language model to use for keyword extraction
 
@@ -76,7 +76,7 @@ The `extract` parameter accepts the following fields:
 
 **promptTemplate** (`string`): Custom prompt template for keyword extraction. Must include both {context} and {maxKeywords} placeholders
 
-### SchemaExtractArgs
+### `SchemaExtractArgs`
 
 **schema** (`ZodType`): Zod schema defining the structure of the data to extract.
 
@@ -86,7 +86,7 @@ The `extract` parameter accepts the following fields:
 
 **metadataKey** (`string`): Key to nest extraction results under. If omitted, results are spread into the metadata object.
 
-## Advanced Example
+## Advanced example
 
 ```typescript
 import { MDocument } from '@mastra/rag'
@@ -145,7 +145,7 @@ const chunks = await doc.chunk({
 // }
 ```
 
-## Document Grouping for Title Extraction
+## Document grouping for title extraction
 
 When using the `TitleExtractor`, you can group multiple chunks together for title extraction by specifying a shared `docId` in the `metadata` field of each chunk. All chunks with the same `docId` will receive the same extracted title. If no `docId` is set, each chunk is treated as its own document for title extraction.
 

package/.docs/reference/rag/graph-rag.md

@@ -2,7 +2,7 @@
 
 The `GraphRAG` class implements a graph-based approach to retrieval augmented generation. It creates a knowledge graph from document chunks where nodes represent documents and edges represent semantic relationships, enabling both direct similarity matching and discovery of related content through graph traversal.
 
-## Basic Usage
+## Basic usage
 
 ```typescript
 import { GraphRAG } from '@mastra/rag'
@@ -24,7 +24,7 @@ const results = await graphRag.query({
 })
 ```
 
-## Constructor Parameters
+## Constructor parameters
 
 **dimension** (`number`): Dimension of the embedding vectors (Default: `1536`)
 
@@ -32,7 +32,7 @@ const results = await graphRag.query({
 
 ## Methods
 
-### createGraph
+### `createGraph`
 
 Creates a knowledge graph from document chunks and their embeddings.
 
@@ -86,7 +86,7 @@ Returns an array of `RankedNode` objects, where each node contains:
 
 **score** (`number`): Combined relevance score from graph traversal
 
-## Advanced Example
+## Advanced example
 
 ```typescript
 const graphRag = new GraphRAG({