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

package/.docs/reference/core/getServer.md

@@ -10,7 +10,7 @@ mastra.getServer()
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
 ## Returns
 

package/.docs/reference/core/getStorage.md

@@ -10,7 +10,7 @@ mastra.getStorage()
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
 ## Returns
 

package/.docs/reference/core/getStoredAgentById.md

@@ -36,7 +36,7 @@ if (storedConfig) {
 
 **result** (`Agent | StorageAgentType | null`): Returns an \`Agent\` instance by default, or \`StorageAgentType\` when \`raw: true\`. Returns \`null\` if no agent with the given ID exists.
 
-## Primitive Resolution
+## Primitive resolution
 
 When creating an `Agent` instance from stored configuration, the method resolves references to registered primitives:
 
@@ -46,9 +46,9 @@ When creating an `Agent` instance from stored configuration, the method resolves
 - **Memory**: Resolved from `memory` registered in Mastra config
 - **Scorers**: Resolved from `scorers` registered in Mastra config, including sampling configuration
 
-If a referenced primitive is not found in the registry, a warning is logged but the agent is still created.
+If a referenced primitive isn't found in the registry, a warning is logged but the agent is still created.
 
-## StorageAgentType
+## `StorageAgentType`
 
 When using `raw: true`, the returned object has the following structure:
 

package/.docs/reference/core/getTelemetry.md

@@ -10,7 +10,7 @@ mastra.getTelemetry()
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
 ## Returns
 

package/.docs/reference/core/getWorkflow.md

@@ -25,7 +25,7 @@ For best TypeScript support, use `getWorkflow()` with the workflow's **registrat
 - Output data schemas
 - Step results
 
-If you need to retrieve a workflow by its `id` property instead of its registration key, you can use `getWorkflowById()`, but note that type inference will not be as precise.
+If you need to retrieve a workflow by its `id` property instead of its registration key, you can use `getWorkflowById()`, but note that type inference won't be as precise.
 
 ## Parameters
 

package/.docs/reference/core/listAgents.md

@@ -10,7 +10,7 @@ mastra.listAgents()
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
 ## Returns
 

package/.docs/reference/core/listMCPServers.md

@@ -38,18 +38,18 @@ const servers = mastra.listMCPServers()
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
 ## Returns
 
 **servers** (`Record<string, MCPServerBase> | undefined`): A record of all registered MCP server instances, where keys are the registry keys (from mcpServers configuration) and values are MCPServerBase instances, or undefined if no servers are registered.
 
-## Related Methods
+## Related methods
 
 - [Mastra.getMCPServer()](https://mastra.ai/reference/core/getMCPServer) - Retrieve an MCP server by its registry key
 - [Mastra.getMCPServerById()](https://mastra.ai/reference/core/getMCPServerById) - Retrieve an MCP server by its intrinsic `id` property
 
-## See Also
+## See also
 
 - [MCP overview](https://mastra.ai/docs/mcp/overview)
 - [MCP server reference](https://mastra.ai/reference/tools/mcp-server)

package/.docs/reference/core/listMemory.md

@@ -20,7 +20,7 @@ This method takes no parameters.
 
 **memory** (`Record<string, MastraMemory>`): An object containing all registered memory instances, keyed by their registry keys.
 
-## Example: Checking Registered Memory
+## Example: Checking registered memory
 
 ```typescript
 import { Mastra } from '@mastra/core'

package/.docs/reference/core/listScorers.md

@@ -2,7 +2,7 @@
 
 The `listScorers()` method returns all scorers that have been registered with the Mastra instance. Scorers are used for evaluating AI outputs and can override default scorers during agent generation or workflow execution.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { mastra } from './mastra'

package/.docs/reference/core/listStoredAgents.md

@@ -53,7 +53,7 @@ for (const config of result.agents) {
 
 **hasMore** (`boolean`): Whether there are more pages available.
 
-## Primitive Resolution
+## Primitive resolution
 
 When creating `Agent` instances (default behavior), each stored agent's configuration is resolved against registered primitives:
 
@@ -63,9 +63,9 @@ When creating `Agent` instances (default behavior), each stored agent's configur
 - **Memory**: Resolved from `memory` registered in Mastra config
 - **Scorers**: Resolved from `scorers` registered in Mastra config
 
-If a referenced primitive is not found, a warning is logged but the agent is still created.
+If a referenced primitive isn't found, a warning is logged but the agent is still created.
 
-## Example: Iterating Through All Stored Agents
+## Example: Iterating through all stored agents
 
 ```typescript
 async function getAllStoredAgents(mastra: Mastra) {

package/.docs/reference/core/listVectors.md

@@ -10,7 +10,7 @@ mastra.listVectors()
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
 ## Returns
 

package/.docs/reference/core/mastra-class.md

@@ -1,4 +1,4 @@
-# Mastra Class
+# Mastra class
 
 The `Mastra` class is the central orchestrator in any Mastra application, managing agents, workflows, storage, logging, observability, and more. Typically, you create a single instance of `Mastra` to coordinate your application.
 
@@ -41,7 +41,7 @@ Visit the [Configuration reference](https://mastra.ai/reference/configuration) f
 
 **logger** (`Logger`): Logger instance created with new PinoLogger() (Default: `Console logger with INFO level`)
 
-**idGenerator** (`() => string`): Custom ID generator function. Used by agents, workflows, memory, and other components to generate unique identifiers.
+**idGenerator** (`(context?: IdGeneratorContext) => string`): Custom ID generator function. Used by agents, workflows, memory, and other components to generate unique identifiers. Receives optional context such as idType, source, entityId, and threadId to support context-aware ID formats.
 
 **workflows** (`Record<string, Workflow>`): Workflows to register. Structured as a key-value pair, with keys being the workflow name and values being the workflow instance. (Default: `{}`)
 

package/.docs/reference/core/mastra-model-gateway.md

@@ -2,7 +2,7 @@
 
 Abstract base class for implementing custom model gateways. Gateways handle provider-specific logic for accessing language models, including provider configuration, authentication, URL construction, and model instantiation.
 
-## Class Overview
+## Class overview
 
 ```typescript
 import { MastraModelGateway, type ProviderConfig } from '@mastra/core/llm'
@@ -53,15 +53,15 @@ class MyCustomGateway extends MastraModelGateway {
 }
 ```
 
-## Required Properties
+## Required properties
 
 **id** (`string`): Unique identifier for the gateway. This ID is used as the prefix for all providers from this gateway (e.g., "netlify/anthropic"). Exception: models.dev is a provider registry and doesn't use a prefix.
 
 **name** (`string`): Human-readable name for the gateway.
 
-## Required Methods
+## Required methods
 
-### fetchProviders()
+### `fetchProviders()`
 
 Fetches provider configurations from the gateway.
 
@@ -83,7 +83,7 @@ Fetches provider configurations from the gateway.
 
 **docUrl** (`string`): Optional documentation URL
 
-### buildUrl()
+### `buildUrl()`
 
 Builds the API URL for a specific model/provider combination.
 
@@ -95,7 +95,7 @@ Builds the API URL for a specific model/provider combination.
 
 **Returns:** `string | undefined | Promise<string | undefined>`
 
-### getApiKey()
+### `getApiKey()`
 
 Retrieves the API key for authentication.
 
@@ -105,7 +105,7 @@ Retrieves the API key for authentication.
 
 **Returns:** `Promise<string>`
 
-### resolveLanguageModel()
+### `resolveLanguageModel()`
 
 Creates a language model instance.
 
@@ -119,15 +119,15 @@ Creates a language model instance.
 
 **Returns:** `Promise<LanguageModelV2> | LanguageModelV2`
 
-## Instance Methods
+## Instance methods
 
-### getId()
+### `getId()`
 
 Returns the gateway's unique identifier.
 
 **Returns:** `string` - The gateway's `id` property
 
-## Model ID Format
+## Model ID format
 
 For true gateways, the gateway ID is used as a prefix and models are accessed using this format:
 
@@ -139,7 +139,7 @@ Examples:
 
 - Gateway with `id = 'custom'`: `'custom/my-provider/model-1'`
 
-## Built-in Implementations
+## Built-in implementations
 
 - **NetlifyGateway** - Netlify AI Gateway integration
 - **ModelsDevGateway** - Registry of OpenAI-compatible providers

package/.docs/reference/core/setLogger.md

@@ -16,7 +16,7 @@ mastra.setLogger({ logger: new PinoLogger({ name: 'testLogger' }) })
 
 ## Returns
 
-This method does not return a value.
+This method doesn't return a value.
 
 ## Related
 

package/.docs/reference/core/setStorage.md

@@ -19,7 +19,7 @@ mastra.setStorage(
 
 ## Returns
 
-This method does not return a value.
+This method doesn't return a value.
 
 ## Related
 

package/.docs/reference/datasets/dataset.md

@@ -1,4 +1,4 @@
-# Dataset Class
+# Dataset class
 
 **Added in:** `@mastra/core@1.4.0`
 
@@ -60,7 +60,7 @@ const history = await dataset.getItemHistory({ itemId: 'item-id' })
 
 ## Access
 
-`Dataset` is not instantiated directly. Obtain one via `DatasetsManager`:
+`Dataset` isn't instantiated directly. Obtain one via `DatasetsManager`:
 
 ```typescript
 const dataset = await mastra.datasets.get({ id: 'dataset-id' })

package/.docs/reference/datasets/datasets-manager.md

@@ -78,7 +78,7 @@ const comparison = await mastra.datasets.compareExperiments({
 
 ## Access
 
-`DatasetsManager` is not instantiated directly. Access it from a `Mastra` instance:
+`DatasetsManager` isn't instantiated directly. Access it from a `Mastra` instance:
 
 ```typescript
 const mastra = new Mastra({

package/.docs/reference/datasets/get.md

@@ -2,7 +2,7 @@
 
 **Added in:** `@mastra/core@1.4.0`
 
-Retrieves an existing dataset by ID. Throws a `MastraError` if the dataset does not exist.
+Retrieves an existing dataset by ID. Throws a `MastraError` if the dataset doesn't exist.
 
 ## Usage example
 
@@ -26,6 +26,6 @@ console.log(details.name)
 
 ## Returns
 
-Throws `MastraError` if the dataset is not found.
+Throws `MastraError` if the dataset isn't found.
 
 **result** (`Promise<Dataset>`): A Dataset instance.

package/.docs/reference/datasets/getDetails.md

@@ -26,7 +26,7 @@ This method takes no parameters.
 
 ## Returns
 
-Returns a `Promise<DatasetRecord>`. Throws `MastraError` if the dataset is not found.
+Returns a `Promise<DatasetRecord>`. Throws `MastraError` if the dataset isn't found.
 
 **id** (`string`): Unique identifier of the dataset.
 

package/.docs/reference/datasets/listItems.md

@@ -41,7 +41,7 @@ When `version` is specified:
 
 **result** (`Promise<DatasetItem[]>`): Array of all items at the specified dataset version.
 
-When `version` is not specified:
+When `version` isn't specified:
 
 **result** (`Promise<object>`): Paginated response.
 

package/.docs/reference/deployer/vercel.md

@@ -113,4 +113,4 @@ With `studio: true`:
 
 When studio is enabled, the routing is configured so that `/api/*` requests are handled by the serverless function, static assets (JS, CSS) are served from Vercel's Edge CDN with no function invocations, and all other paths fall back to `index.html` for client-side routing.
 
-This folder is generated during build and should not be committed to version control.
+This folder is generated during build and shouldn't be committed to version control.

package/.docs/reference/deployer.md

@@ -2,7 +2,7 @@
 
 The Deployer handles the deployment of standalone Mastra applications by packaging code, managing environment files, and serving applications using the Hono framework. Concrete implementations must define the deploy method for specific deployment targets.
 
-## Usage Example
+## Usage example
 
 If you want to create a custom deployer, you can extend the abstract `Deployer` class and implement the `deploy` method with your specific deployment logic. Here's an example:
 
@@ -28,7 +28,7 @@ class CustomDeployer extends Deployer {
 
 ## Parameters
 
-### Constructor Parameters
+### Constructor parameters
 
 **args** (`object`): Configuration options for the Deployer.
 
@@ -44,7 +44,7 @@ class CustomDeployer extends Deployer {
 
 **deploy** (`(outputDirectory: string) => Promise<void>`): Abstract method that must be implemented by subclasses. Handles the deployment process to the specified output directory.
 
-## Inherited Methods from Bundler
+## Inherited methods from bundler
 
 The Deployer class inherits the following key methods from the Bundler class:
 
@@ -54,7 +54,7 @@ The Deployer class inherits the following key methods from the Bundler class:
 
 **\_bundle** (`(serverFile: string, mastraEntryFile: string, outputDirectory: string, bundleLocation?: string) => Promise<void>`): Bundles the application using the specified server and Mastra entry files.
 
-## Core Concepts
+## Core concepts
 
 ### Deployment Lifecycle
 

package/.docs/reference/evals/answer-relevancy.md

@@ -1,4 +1,4 @@
-# Answer Relevancy Scorer
+# Answer relevancy scorer
 
 The `createAnswerRelevancyScorer()` function accepts a single options object with the following properties:
 
@@ -12,7 +12,7 @@ The `createAnswerRelevancyScorer()` function accepts a single options object wit
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
 
-## .run() Returns
+## `.run()` returns
 
 **runId** (`string`): The id of the run (optional).
 
@@ -30,7 +30,7 @@ This function returns an instance of the MastraScorer class. The `.run()` method
 
 **reason** (`string`): Explanation of the score.
 
-## Scoring Details
+## Scoring details
 
 The scorer evaluates relevancy through query-answer alignment, considering completeness and detail level, but not factual correctness.
 
@@ -58,7 +58,7 @@ A relevancy score between 0 and 1:
 - **0.7–0.9**: The response mostly answers the query but may include minor unrelated content.
 - **0.4–0.6**: The response partially answers the query, mixing relevant and unrelated information.
 - **0.1–0.3**: The response includes minimal relevant content and largely misses the intent of the query.
-- **0.0**: The response is entirely unrelated and does not answer the query.
+- **0.0**: The response is entirely unrelated and doesn't answer the query.
 
 ## Example
 

package/.docs/reference/evals/answer-similarity.md

@@ -1,4 +1,4 @@
-# Answer Similarity Scorer
+# Answer similarity scorer
 
 The `createAnswerSimilarityScorer()` function creates a scorer that evaluates how similar an agent's output is to a ground truth answer. This scorer is specifically designed for CI/CD testing scenarios where you have expected answers and want to ensure consistency over time.
 
@@ -24,7 +24,7 @@ The `createAnswerSimilarityScorer()` function creates a scorer that evaluates ho
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but **requires ground truth** to be provided in the run object.
 
-## .run() Returns
+## `.run()` returns
 
 **runId** (`string`): The id of the run (optional).
 
@@ -42,7 +42,7 @@ This function returns an instance of the MastraScorer class. The `.run()` method
 
 **generateReasonPrompt** (`string`): The prompt used for generating the explanation.
 
-## Scoring Details
+## Scoring details
 
 The scorer uses a multi-step process:
 

package/.docs/reference/evals/bias.md

@@ -1,4 +1,4 @@
-# Bias Scorer
+# Bias scorer
 
 The `createBiasScorer()` function accepts a single options object with the following properties:
 
@@ -10,7 +10,7 @@ The `createBiasScorer()` function accepts a single options object with the follo
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
 
-## .run() Returns
+## `.run()` returns
 
 **runId** (`string`): The id of the run (optional).
 
@@ -28,7 +28,7 @@ This function returns an instance of the MastraScorer class. The `.run()` method
 
 **generateReasonPrompt** (`string`): The prompt sent to the LLM for the generateReason step (optional).
 
-## Bias Categories
+## Bias categories
 
 The scorer evaluates several types of bias:
 
@@ -37,7 +37,7 @@ The scorer evaluates several types of bias:
 3. **Racial/Ethnic Bias**: Discrimination based on race, ethnicity, or national origin
 4. **Geographical Bias**: Prejudice based on location or regional stereotypes
 
-## Scoring Details
+## Scoring details
 
 The scorer evaluates bias through opinion analysis based on:
 

package/.docs/reference/evals/completeness.md

@@ -1,14 +1,14 @@
-# Completeness Scorer
+# Completeness scorer
 
 The `createCompletenessScorer()` function evaluates how thoroughly an LLM's output covers the key elements present in the input. It analyzes nouns, verbs, topics, and terms to determine coverage and provides a detailed completeness score.
 
 ## Parameters
 
-The `createCompletenessScorer()` function does not take any options.
+The `createCompletenessScorer()` function doesn't take any options.
 
 This function returns an instance of the MastraScorer class. See the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer) for details on the `.run()` method and its input/output.
 
-## .run() Returns
+## `.run()` returns
 
 **runId** (`string`): The id of the run (optional).
 
@@ -31,7 +31,7 @@ The `.run()` method returns a result in the following shape:
 }
 ```
 
-## Element Extraction Details
+## Element extraction details
 
 The scorer extracts and analyzes several types of elements:
 
@@ -48,7 +48,7 @@ The extraction process includes:
 - Special handling of short words (3 characters or less)
 - Deduplication of elements
 
-### extractStepResult
+### `extractStepResult`
 
 From the `.run()` method, you can get the `extractStepResult` object with the following properties:
 
@@ -57,7 +57,7 @@ From the `.run()` method, you can get the `extractStepResult` object with the fo
 - **missingElements**: Input elements not found in the output.
 - **elementCounts**: The number of elements in the input and output.
 
-## Scoring Details
+## Scoring details
 
 The scorer evaluates completeness through linguistic element coverage analysis.
 

package/.docs/reference/evals/content-similarity.md

@@ -1,4 +1,4 @@
-# Content Similarity Scorer
+# Content similarity scorer
 
 The `createContentSimilarityScorer()` function measures the textual similarity between two strings, providing a score that indicates how closely they match. It supports configurable options for case sensitivity and whitespace handling.
 
@@ -12,7 +12,7 @@ The `createContentSimilarityScorer()` function accepts a single options object w
 
 This function returns an instance of the MastraScorer class. See the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer) for details on the `.run()` method and its input/output.
 
-## .run() Returns
+## `.run()` returns
 
 **runId** (`string`): The id of the run (optional).
 
@@ -22,7 +22,7 @@ This function returns an instance of the MastraScorer class. See the [MastraScor
 
 **score** (`number`): Similarity score (0-1) where 1 indicates perfect similarity.
 
-## Scoring Details
+## Scoring details
 
 The scorer evaluates textual similarity through character-level matching and configurable text normalization.
 

package/.docs/reference/evals/context-precision.md

@@ -1,18 +1,18 @@
-# Context Precision Scorer
+# Context precision scorer
 
 The `createContextPrecisionScorer()` function creates a scorer that evaluates how relevant and well-positioned retrieved context pieces are for generating expected outputs. It uses **Mean Average Precision (MAP)** to reward systems that place relevant context earlier in the sequence.
 
-It is especially useful for these use cases:
+It's especially useful for these use cases:
 
-## RAG System Evaluation
+## RAG system evaluation
 
 Ideal for evaluating retrieved context in RAG pipelines where:
 
 - Context ordering matters for model performance
-- You need to measure retrieval quality beyond simple relevance
+- You need to measure retrieval quality beyond basic relevance
 - Early relevant context is more valuable than later relevant context
 
-## Context Window Optimization
+## Context window optimization
 
 Use when optimizing context selection for:
 
@@ -28,13 +28,13 @@ Use when optimizing context selection for:
 
 **Note**: Either `context` or `contextExtractor` must be provided. If both are provided, `contextExtractor` takes precedence.
 
-## .run() Returns
+## `.run()` returns
 
 **score** (`number`): Mean Average Precision score between 0 and scale (default 0-1)
 
 **reason** (`string`): Human-readable explanation of the context precision evaluation
 
-## Scoring Details
+## Scoring details
 
 ### Mean Average Precision (MAP)
 
@@ -77,7 +77,7 @@ The reason field explains:
 Use results to:
 
 - **Improve retrieval**: Filter out irrelevant context before ranking
-- **Optimize ranking**: Ensure relevant context appears early
+- **Optimize ranking**: Ensure relevant context surfaces early
 - **Tune chunk size**: Balance context detail vs. relevance precision
 - **Evaluate embeddings**: Test different embedding models for better retrieval
 
@@ -177,7 +177,7 @@ For more details on `runEvals`, see the [runEvals reference](https://mastra.ai/r
 
 To add this scorer to an agent, see the [Scorers overview](https://mastra.ai/docs/evals/overview) guide.
 
-## Comparison with Context Relevance
+## Comparison with context relevance
 
 Choose the right scorer for your needs:
 

package/.docs/reference/evals/context-relevance.md

@@ -1,10 +1,10 @@
-# Context Relevance Scorer
+# Context relevance scorer
 
 The `createContextRelevanceScorerLLM()` function creates a scorer that evaluates how relevant and useful provided context was for generating agent responses. It uses weighted relevance levels and applies penalties for unused high-relevance context and missing information.
 
-It is especially useful for these use cases:
+It's especially useful for these use cases:
 
-## Content Generation Evaluation
+## Content generation evaluation
 
 Best for evaluating context quality in:
 
@@ -12,7 +12,7 @@ Best for evaluating context quality in:
 - RAG pipelines needing nuanced relevance assessment
 - Systems where missing context affects quality
 
-## Context Selection Optimization
+## Context selection optimization
 
 Use when optimizing for:
 
@@ -28,13 +28,13 @@ Use when optimizing for:
 
 Note: Either `context` or `contextExtractor` must be provided. If both are provided, `contextExtractor` takes precedence.
 
-## .run() Returns
+## `.run()` returns
 
 **score** (`number`): Weighted relevance score between 0 and scale (default 0-1)
 
 **reason** (`string`): Human-readable explanation of the context relevance evaluation
 
-## Scoring Details
+## Scoring details
 
 ### Weighted Relevance Scoring
 
@@ -512,7 +512,7 @@ const evaluateRAG = async testCases => {
 }
 ```
 
-## Comparison with Context Precision
+## Comparison with context precision
 
 Choose the right scorer for your needs: