@mastra/mcp-docs-server 1.2.16-alpha.3 → 1.2.16-alpha.6

package/.docs/reference/tools/task-tools.md

@@ -25,7 +25,7 @@ const agent = new Agent({
 })
 ```
 
-Or import the tools directly:
+Or import the tools directly. `taskWriteTool`, `taskUpdateTool`, `taskCompleteTool`, and `taskCheckTool` are the export names; `task_write`, `task_update`, `task_complete`, and `task_check` are the tool IDs the model sees in tool calls and traces:
 
 ```typescript
 import { taskWriteTool, taskUpdateTool, taskCompleteTool, taskCheckTool } from '@mastra/core/tools'

package/.docs/reference/tools/vector-query-tool.md

@@ -353,7 +353,7 @@ const response = await agent.generate('Find information about deployment', {
 })
 ```
 
-This approach allows you to:
+Runtime configuration supports these use cases:
 
 - Switch between environments (dev/staging/prod)
 - Adjust performance parameters based on load

package/.docs/reference/vectors/chroma.md

@@ -56,7 +56,7 @@ Otherwise, you have several options for setting up your single-node Chroma serve
 
 Note: Forking is only supported on Chroma Cloud, or if you deploy your own OSS **distributed** Chroma.
 
-`forkIndex` lets you fork an existing Chroma index instantly. Operations on the forked index don't affect the original one. Learn more on the [Chroma docs](https://docs.trychroma.com/cloud/collection-forking).
+`forkIndex` instantly forks an existing Chroma index without affecting the original index. Learn more on the [Chroma docs](https://docs.trychroma.com/cloud/collection-forking).
 
 **indexName** (`string`): Name of the index to fork
 

package/.docs/reference/vectors/convex.md

@@ -4,7 +4,7 @@
 
 The `ConvexVector` class provides vector storage and similarity search using [Convex](https://convex.dev). It stores embeddings inside Convex and performs cosine similarity search in the Mastra adapter.
 
-> **Development-scale search:** `ConvexVector` reads matching vectors through the Mastra storage handler, filters in JavaScript, computes cosine similarity, sorts results, and returns the top matches. Use it for local development, tests, and small datasets.
+> **Development-scale search:** `ConvexVector` reads matching vectors through the Mastra storage handler and filters them in JavaScript. It then computes cosine similarity and sorts the results before returning the top matches. Use it for local development, tests, and small datasets.
 >
 > For production vector search on Convex, use `ConvexNativeVector`. It uses the Convex native `vectorSearch` API, which requires a deployed Convex vector index and a Convex action.
 

package/.docs/reference/vectors/couchbase.md

@@ -101,7 +101,7 @@ Adds or updates vectors and their metadata in the collection.
 
 Searches for similar vectors.
 
-> **Warning:** The `filter` and `includeVector` parameters aren't currently supported. Filtering must be performed client-side after retrieving results, or by using the Couchbase SDK's Search capabilities directly. To retrieve the vector embedding, fetch the full document by ID using the Couchbase SDK.
+> **Warning:** The `filter` and `includeVector` parameters aren't currently supported. Filtering must be performed client-side after retrieving results or through the Couchbase SDK's Search capabilities. Retrieve the vector embedding by fetching the full document by ID with the Couchbase SDK.
 
 **indexName** (`string`): Name of the index to search in
 

package/.docs/reference/vectors/mongodb.md

@@ -220,7 +220,7 @@ const results = await store.textQuery({
 
 ### `hybridQuery()`
 
-Runs a hybrid search that fuses vector similarity and full-text results using MongoDB's server-side `$rankFusion`. It requires MongoDB >= 8.0 and is generally available from 8.1. On 8.0.x, it may need a MongoDB support case to enable, and it runs where enabled, such as Atlas 8.0.x. A full-text search index must exist: it's auto-created for managed indexes, but for a bring-your-own collection you must call `createSearchIndex()` first (opt-in).
+Runs a hybrid search that fuses vector similarity and full-text results using MongoDB's server-side `$rankFusion`. It requires MongoDB >= 8.0 and is generally available from 8.1. On 8.0.x, it may require a MongoDB support case for enablement. It runs where enabled, including Atlas 8.0.x. A full-text search index must exist: it's auto-created for managed indexes, but for a bring-your-own collection you must call `createSearchIndex()` first (opt-in).
 
 **indexName** (`string`): Name of the Mastra index to search
 
@@ -276,7 +276,7 @@ interface IndexStats {
 Deletes a vector index. Behavior depends on how the index was created:
 
 - **Managed index** (created without `collectionName`): drops the entire collection and all its data.
-- **Bring-your-own index** (created with `collectionName`): drops the Atlas vectorSearch index and, if one was provisioned via `createSearchIndex()`, the companion full-text search index. The caller's operational collection and its documents are preserved. This store never drops a collection it didn't create.
+- **Bring-your-own index** (created with `collectionName`): drops the Atlas vectorSearch index. If `createSearchIndex()` provisioned a companion full-text search index, it drops that index too. The caller's operational collection and its documents are preserved. This store never drops a collection it didn't create.
 
 The BYO classification is recorded durably when the index is created, so it's applied correctly even by a different process (e.g. an index created by a setup job and later deleted by a long-lived service). Always pass the **logical index name** (the `indexName` used at `createIndex`), not the physical collection name.
 

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

@@ -350,7 +350,7 @@ The `PgVector` class exposes its underlying PostgreSQL connection pool as a publ
 pgVector.pool // instance of pg.Pool
 ```
 
-This enables advanced usage such as running direct SQL queries, managing transactions, or monitoring pool state. When using the pool directly:
+Direct pool access supports advanced operations such as direct SQL queries, transactions, or pool-state monitoring. When using the pool directly:
 
 - You are responsible for releasing clients (`client.release()`) after use.
 - The pool remains accessible after calling `disconnect()`, but new queries will fail.

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

@@ -24,7 +24,7 @@ The QdrantVector class provides vector search using [Qdrant](https://qdrant.tech
 
 **namedVectors** (`Record<string, { size: number; distance: 'cosine' | 'euclidean' | 'dotproduct' }>`): Configuration for named vector spaces. When provided, creates a collection with multiple named vector fields.
 
-#### Creating a Named Vectors Collection
+#### Creating a `named vectors` Collection
 
 ```typescript
 // Create a collection with multiple named vector spaces
@@ -84,7 +84,7 @@ await store.upsert({
 
 **using** (`string`): Name of the vector field to query when using named vectors. Use this when your collection has multiple named vector fields.
 
-#### Named Vectors
+#### `named vectors`
 
 Qdrant supports [multiple vectors per collection](https://qdrant.tech/documentation/concepts/vectors/#named-vectors), with a name assigned to each vector field. Use the `using` parameter to select the vector field to query:
 

package/.docs/reference/voice/overview.md

@@ -748,7 +748,7 @@ Visit the [xAI Realtime Voice Reference](https://mastra.ai/integrations/voice/xa
 
 ### Realtime voice
 
-Run live calls a user can talk over, in the browser or over the phone. Mastra hands the audio loop to LiveKit, which covers voice activity detection, semantic turn detection, and barge-in, while your agent generates each reply with its own model, tools, and memory. For setup and configuration options, check out [Realtime voice](https://mastra.ai/integrations/voice/livekit).
+Run live calls that a user can talk over in a browser or by phone. Mastra hands the audio loop to LiveKit for voice activity and semantic turn detection, plus barge-in. Your agent generates each reply with its own model, tools, and memory. For setup and configuration options, check out [Realtime voice](https://mastra.ai/integrations/voice/livekit).
 
 ## Voice configuration
 

package/.docs/reference/voice/speech-to-speech.md

@@ -80,7 +80,7 @@ export const agent = new Agent({
 
 ## Listen for realtime events
 
-Realtime voice providers emit events you can use to update your UI, play assistant audio, log transcriptions, and handle errors:
+Realtime voice providers emit events you can use to update your UI and play assistant audio, while logging transcriptions and handling errors:
 
 ```typescript
 agent.voice.on('speaking', ({ audio }) => {

package/.docs/reference/voice/speech-to-text.md

@@ -35,7 +35,7 @@ Mastra supports several Speech-to-Text providers, each with their own capabiliti
 - [**ElevenLabs**](https://mastra.ai/integrations/voice/elevenlabs): Advanced speech recognition with support for multiple languages
 - [**Google**](https://mastra.ai/integrations/voice/google): Google's speech recognition with extensive language support
 - [**Cloudflare**](https://mastra.ai/integrations/voice/cloudflare): Edge-optimized speech recognition for low-latency applications
-- [**Deepgram**](https://mastra.ai/integrations/voice/deepgram): AI-powered speech recognition with high accuracy for various accents
+- [**Deepgram**](https://mastra.ai/integrations/voice/deepgram): AI-powered speech recognition with high accuracy for multiple accents
 - [**Sarvam**](https://mastra.ai/integrations/voice/sarvam): Specialized in Indic languages and accents
 
 Each provider is implemented as a separate package that you can install as needed:

package/.docs/reference/voice/voice.on.md

@@ -2,7 +2,7 @@
 
 # voice.on()
 
-The `on()` method registers event listeners for voice events. This is particularly important for real-time voice providers, where events are used to communicate transcribed text, audio responses, and other state changes.
+The `on()` method registers event listeners for voice events. This is particularly important for real-time voice providers, where events are used to communicate transcribed text and audio responses, as well as other state changes.
 
 ## Usage example
 

package/.docs/reference/voice/voice.updateConfig.md

@@ -2,7 +2,7 @@
 
 # voice.updateConfig()
 
-The `updateConfig()` method allows you to update the configuration of a voice provider at runtime. This is useful for changing voice settings, API keys, or other provider-specific options without creating a new instance.
+The `updateConfig()` method allows you to update the configuration of a voice provider at runtime. This is useful for changing voice settings and API keys, along with other provider-specific options without creating a new instance.
 
 ## Usage example
 

package/.docs/reference/workspace/local-sandbox.md

@@ -146,7 +146,7 @@ const detection = LocalSandbox.detectIsolation()
 
 ## Environment isolation
 
-By default, `LocalSandbox` only includes `PATH` in the environment. This allows commands to run while preventing accidental exposure of API keys and secrets.
+By default, `LocalSandbox` only includes `PATH` in the environment. Commands can run without accidental exposure of API keys and secrets.
 
 ```typescript
 // Default: only PATH is available (commands work, secrets protected)

package/.docs/reference/workspace/workspace-class.md

@@ -278,7 +278,7 @@ const instructions = workspace.getInstructions({ requestContext })
 
 #### `getInstructionsAsync(opts?)`
 
-Returns combined workspace instructions. Use this when the workspace uses resolver-backed providers. A runtime-defined filesystem is resolved per request; a runtime-defined sandbox contributes stable placeholder text unless `instructions.dynamicSandbox` is set to `'resolve'`.
+Returns combined workspace instructions. Use this when the workspace uses resolver-backed providers. A runtime-defined filesystem is resolved per request. A runtime-defined sandbox contributes stable placeholder text unless `instructions.dynamicSandbox` is set to `'resolve'`.
 
 ```typescript
 const instructions = await workspace.getInstructionsAsync({ requestContext })

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @mastra/mcp-docs-server
 
+## 1.2.16-alpha.5
+
+### Patch Changes
+
+- Updated dependencies [[`d118873`](https://github.com/mastra-ai/mastra/commit/d118873cfd5074b1f814a1c169a97ca7a3a29174), [`161258b`](https://github.com/mastra-ai/mastra/commit/161258b3473a6d0fce00a43cab59d119a49a232f), [`8ea8038`](https://github.com/mastra-ai/mastra/commit/8ea80386fde53d26e2c0b2060c53bc9bd9be10f3)]:
+  - @mastra/core@1.59.0-alpha.3
+
+## 1.2.16-alpha.4
+
+### Patch Changes
+
+- Updated dependencies [[`898bba4`](https://github.com/mastra-ai/mastra/commit/898bba46d4806dd255a44e5dc3a3d5827eaefdfe), [`f9aab1c`](https://github.com/mastra-ai/mastra/commit/f9aab1cfc3fda03238a7fd7bd8b794e07497878c), [`e31421b`](https://github.com/mastra-ai/mastra/commit/e31421bc9c11c03c6e74f447ecb5820000e2b9d7), [`aece0e7`](https://github.com/mastra-ai/mastra/commit/aece0e7cb124ae1eb1230689b887f5554b9a0bf0)]:
+  - @mastra/core@1.59.0-alpha.2
+
 ## 1.2.16-alpha.2
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.2.16-alpha.3",
+  "version": "1.2.16-alpha.6",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -28,8 +28,8 @@
     "jsdom": "^26.1.0",
     "local-pkg": "^1.1.2",
     "zod": "^4.4.3",
-    "@mastra/core": "1.59.0-alpha.1",
-    "@mastra/mcp": "^1.16.0"
+    "@mastra/mcp": "^1.16.0",
+    "@mastra/core": "1.59.0-alpha.3"
   },
   "devDependencies": {
     "@hono/node-server": "^2.0.0",
@@ -45,9 +45,9 @@
     "tsx": "^4.23.1",
     "typescript": "^6.0.3",
     "vitest": "4.1.10",
-    "@internal/lint": "0.0.122",
     "@internal/types-builder": "0.0.97",
-    "@mastra/core": "1.59.0-alpha.1"
+    "@mastra/core": "1.59.0-alpha.3",
+    "@internal/lint": "0.0.122"
   },
   "homepage": "https://mastra.ai",
   "repository": {

package/.docs/docs/browser/recording.md

@@ -1,120 +0,0 @@
-> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
-
-# Browser recording
-
-**Added in:** `@mastra/core@1.43.0`
-
-Browser recording adds two opt-in tools that let an agent save a browser session as a Motion-JPEG AVI video. The agent can also add short captions while it works.
-
-> **Beta:** Breaking changes may occur without a major version bump until the API is stable.
-
-## When to use browser recording
-
-Use browser recording when you need to:
-
-- Review what an agent did in a browser
-- Share a short browser automation run with a teammate
-- Debug missed actions, slow page loads, or unexpected navigation
-- Add short captions that explain each major step
-
-Recording tools are disabled by default. Enable them only for agents that need to write video files.
-
-## Enable recording
-
-Pass a `recording` object to `AgentBrowser` or `StagehandBrowser`. The only required field is `outputDir`. You can also set `maxDurationMs`, `maxWidth`, and `maxHeight` as defaults for every recording started by this browser.
-
-The following example enables recording for `AgentBrowser`:
-
-```typescript
-import { join } from 'node:path'
-import { AgentBrowser } from '@mastra/agent-browser'
-
-export const browser = new AgentBrowser({
-  headless: false,
-  recording: {
-    outputDir: join(process.cwd(), 'browser-recordings'),
-    maxDurationMs: 60_000,
-    maxWidth: 1280,
-    maxHeight: 720,
-  },
-})
-```
-
-The same option works with `StagehandBrowser`:
-
-```typescript
-import { join } from 'node:path'
-import { StagehandBrowser } from '@mastra/stagehand'
-
-export const browser = new StagehandBrowser({
-  headless: false,
-  recording: {
-    outputDir: join(process.cwd(), 'browser-recordings'),
-    maxDurationMs: 60_000,
-    maxWidth: 1280,
-    maxHeight: 720,
-  },
-})
-```
-
-The agent can still override these defaults per-recording by passing `maxDurationMs`, `maxWidth`, or `maxHeight` to the `browser_record` tool at start time.
-
-## Recording tools
-
-Enabling recording adds these tools:
-
-| Tool                     | Description                                                  |
-| ------------------------ | ------------------------------------------------------------ |
-| `browser_record`         | Starts, stops, or checks the status of a recording.          |
-| `browser_record_caption` | Adds a short caption at the current moment in the recording. |
-
-`browser_record` accepts an `action` field:
-
-- `start`: Start recording the current browser session.
-- `status`: Check whether a recording is active.
-- `stop`: Stop recording and write the `.avi` file.
-
-The `outputPath` option for `browser_record` must be an absolute path inside the configured `recording.outputDir`. If you omit it, Mastra creates a file in `outputDir`.
-
-## Example agent instructions
-
-Tell the agent when to record and when to add captions:
-
-```typescript
-import { Agent } from '@mastra/core/agent'
-import { browser } from '../browsers'
-
-export const browserAgent = new Agent({
-  id: 'browser-agent',
-  name: 'Browser Agent',
-  model: 'openai/gpt-5.6-sol',
-  browser,
-  instructions: `Use browser tools to complete the requested task.
-
-When the user asks for a recording:
-1. Call browser_record with action="start" before browser work begins.
-2. After each major action, call browser_record_caption with a caption of about six words.
-3. Call browser_record with action="stop" as soon as the task is complete.
-4. Return the saved video path to the user.`,
-})
-```
-
-## Output format and limits
-
-Recordings are saved as Motion-JPEG AVI files. This format is encoded in JavaScript and doesn't require `ffmpeg` or native dependencies.
-
-Default limits:
-
-- Maximum duration: 30 seconds
-- Hard duration cap: 120 seconds
-- Maximum frame size: 1024 × 720
-- Captions: 80 characters each
-- One active recording per process
-
-Use shorter recordings when possible. Long browser sessions produce larger files and are harder to review.
-
-## Next steps
-
-- [AgentBrowser](https://mastra.ai/integrations/browsers/agent-browser)
-- [Stagehand](https://mastra.ai/integrations/browsers/stagehand)
-- [Browser overview](https://mastra.ai/docs/browser/overview)

package/.docs/reference/processors/cost-guard-processor.md

@@ -1,115 +0,0 @@
-> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
-
-# CostGuardProcessor
-
-The `CostGuardProcessor` enforces monetary cost limits across the agentic loop, blocking or warning when a configurable cost threshold is exceeded.
-
-It uses `processInputStep` to check the cost limit before each LLM call. Cost data is queried from the observability storage APIs (`getMetricAggregate`) for all scopes. For `resource` and `thread` scopes, it aggregates cost across runs within a configurable time window (defaults to 7 days). For `run` scope, it queries cost for the current trace.
-
-For token-based limits, use `TokenLimiterProcessor` instead.
-
-Supports three scoping modes:
-
-- **Run scope**: Tracks cost within a single agent run via trace ID
-- **Resource scope** (default): Tracks cumulative cost per `resourceId` across runs
-- **Thread scope**: Tracks cumulative cost per `threadId` across runs
-
-> **Approximate cost guard.** Cost data is persisted asynchronously via buffered exporters in the observability pipeline. Fast-running agents may exceed the configured limit before metrics are available for query. Treat `maxCost` as an approximate threshold that fast-running agents may exceed.
-
-## Usage example
-
-Track cumulative cost per resource (default scope):
-
-```typescript
-import { CostGuardProcessor } from '@mastra/core/processors'
-
-const costGuard = new CostGuardProcessor({
-  maxCost: 1.0,
-})
-```
-
-Track cumulative cost per thread with a 24-hour window:
-
-```typescript
-import { CostGuardProcessor } from '@mastra/core/processors'
-
-const costGuard = new CostGuardProcessor({
-  maxCost: 5.0,
-  scope: 'thread',
-  window: '24h',
-})
-```
-
-Attach to an agent with an `onViolation` callback:
-
-```typescript
-import { Agent } from '@mastra/core/agent'
-import { CostGuardProcessor } from '@mastra/core/processors'
-
-const costGuard = new CostGuardProcessor({
-  maxCost: 5.0,
-  scope: 'resource',
-  window: '30d',
-})
-
-costGuard.onViolation = ({ detail }) => {
-  console.log(`Cost exceeded for ${detail.scopeKey}: $${detail.usage}/$${detail.limit}`)
-}
-
-const agent = new Agent({
-  id: 'my-agent',
-  name: 'my-agent',
-  model: 'openai/gpt-5-nano',
-  processors: {
-    input: [costGuard],
-  },
-})
-```
-
-## Constructor parameters
-
-**maxCost** (`number`): Maximum estimated cost allowed (e.g. 0.50 for $0.50 USD). Must be a positive number. Uses cost data from observability metrics. This is an approximate limit due to metric persistence delays.
-
-**scope** (`'run' | 'resource' | 'thread'`): Scope for cost tracking. 'run' tracks cost within the current agent run via trace ID. 'resource' tracks cumulative cost per resourceId across runs (default). 'thread' tracks cumulative cost per threadId across runs. All scopes require observability storage with getMetricAggregate support. (Default: `'resource'`)
-
-**window** (`'1h' | '6h' | '24h' | '7d' | '30d' | '365d'`): Time window for cost aggregation when using 'resource' or 'thread' scope. Only applicable to non-run scopes. (Default: `'7d'`)
-
-**strategy** (`'block' | 'warn'`): Strategy when the cost limit is exceeded. 'block' aborts with a TripWire error. 'warn' logs a warning but allows the step to proceed. (Default: `'block'`)
-
-**message** (`string`): Custom message template for the abort reason. Supports {usage} and {limit} placeholders. (Default: `'Cost guard: cost limit exceeded ({usage}/{limit})'`)
-
-## Instance properties
-
-**id** (`'cost-guard'`): Processor identifier.
-
-**name** (`'Cost Guard'`): Processor display name.
-
-**onViolation** (`(violation: ProcessorViolation) => void | Promise<void>`): Callback invoked when a cost violation is detected, regardless of strategy. Part of the generalized Processor interface. Use for side effects like alerting, logging to external systems, or emailing users. Errors thrown by this callback are silently caught.
-
-**processInputStep** (`(args: ProcessInputStepArgs) => Promise<void>`): Checks cumulative estimated cost against maxCost before each LLM call. Queries observability storage for cost data: run scope filters by trace ID, resource/thread scopes filter by their respective IDs with a time window. Calls abort() when the limit is exceeded (block strategy) or logs a warning (warn strategy). Cost checks are approximate due to metric persistence delays.
-
-## Error behavior
-
-When the `block` strategy is active (default), `CostGuardProcessor` calls `abort()` with `retry: false` when the cost limit is exceeded. The TripWire metadata includes:
-
-- `processorId`: `'cost-guard'`
-- `usage`: Current cumulative usage (`estimatedCost`, `costUnit`)
-- `maxCost`: The configured cost limit
-- `scope`: The active scope (`'run'`, `'resource'`, or `'thread'`)
-- `scopeKey`: The scope identifier for resource/thread scopes (if applicable)
-
-## Scoping behavior
-
-| Scope      | Tracks across runs | Filter                      | Requires context                 |
-| ---------- | ------------------ | --------------------------- | -------------------------------- |
-| `run`      | No                 | `traceId` from current span | Tracing context (automatic)      |
-| `resource` | Yes                | `resourceId` + time window  | `resourceId` in `RequestContext` |
-| `thread`   | Yes                | `threadId` + time window    | `threadId` in `RequestContext`   |
-
-All scopes require observability storage with `getMetricAggregate` support. If the Mastra instance doesn't have observability storage configured, an error is thrown at registration time.
-
-For `run` scope, the processor reads the trace ID from the current span's tracing context. If no tracing context is available, the check is skipped (fail-open).
-
-For `resource` and `thread` scopes, if the required context ID is missing at runtime, the check is skipped. Observability query failures are handled with a fail-open strategy: if a query fails, cost is treated as zero.
-
-> **Note on metric persistence delay.** The observability pipeline uses buffered exporters that flush metrics asynchronously. A short delay exists between when an LLM call completes and when its cost metrics are available for query. During high-frequency agent execution, the cost guard may not detect a limit breach until one or more steps after the actual cost exceeded the threshold.