@mastra/mcp-docs-server 1.0.0-beta.5 → 1.0.0-beta.7

package/.docs/raw/memory/memory-processors.mdx

@@ -5,132 +5,318 @@ description: "Learn how to use memory processors in Mastra to filter, trim, and
 
 # Memory Processors
 
-Memory Processors allow you to modify the list of messages retrieved from memory _before_ they are added to the agent's context window and sent to the LLM. This is useful for managing context size, filtering content, and optimizing performance.
+Memory processors transform and filter messages as they pass through an agent with memory enabled. They manage context window limits, remove unnecessary content, and optimize the information sent to the language model.
 
-Processors operate on the messages retrieved based on your memory configuration (e.g., `lastMessages`, `semanticRecall`). They do **not** affect the new incoming user message.
+When memory is enabled on an agent, Mastra adds memory processors to the agent's processor pipeline. These processors retrieve conversation history, working memory, and semantically relevant messages, then persist new messages after the model responds.
 
-## Built-in Processors
+Memory processors are [processors](/docs/v1/agents/processors) that operate specifically on memory-related messages and state.
 
-Mastra provides built-in processors:
+## Built-in Memory Processors
 
-### `TokenLimiter`
+Mastra automatically adds these processors when memory is enabled:
 
-This processor is used to prevent errors caused by exceeding the LLM's context window limit. It counts the tokens in the retrieved memory messages and removes the oldest messages until the total count is below the specified `limit`.
+### MessageHistory
 
-```typescript copy showLineNumbers {9-12}
-import { Memory } from "@mastra/memory";
-import { TokenLimiter } from "@mastra/memory/processors";
+Retrieves conversation history and persists new messages.
+
+**When you configure:**
+
+```typescript
+memory: new Memory({
+  lastMessages: 10,
+});
+```
+
+**Mastra internally:**
+
+1. Creates a `MessageHistory` processor with `limit: 10`
+2. Adds it to the agent's input processors (runs before the LLM)
+3. Adds it to the agent's output processors (runs after the LLM)
+
+**What it does:**
+
+- **Input**: Fetches the last 10 messages from storage and prepends them to the conversation
+- **Output**: Persists new messages to storage after the model responds
+
+**Example:**
+
+```typescript copy showLineNumbers
 import { Agent } from "@mastra/core/agent";
+import { Memory } from "@mastra/memory";
+import { LibSQLStore } from "@mastra/libsql";
+import { openai } from "@ai-sdk/openai";
 
 const agent = new Agent({
   id: "test-agent",
   name: "Test Agent",
-  model: "openai/gpt-5.1",
+  instructions: "You are a helpful assistant",
+  model: 'openai/gpt-4o',
   memory: new Memory({
-    processors: [
-      // Ensure the total tokens from memory don't exceed ~127k
-      new TokenLimiter(127000),
-    ],
+    storage: new LibSQLStore({
+      id: "memory-store",
+      url: "file:memory.db",
+    }),
+    lastMessages: 10, // MessageHistory processor automatically added
   }),
 });
 ```
 
-The `TokenLimiter` uses the `o200k_base` encoding by default (suitable for GPT-4o). You can specify other encodings if needed for different models:
+### SemanticRecall
 
-```typescript copy showLineNumbers {6-9}
-// Import the encoding you need (e.g., for older OpenAI models)
-import cl100k_base from "js-tiktoken/ranks/cl100k_base";
+Retrieves semantically relevant messages based on the current input and creates embeddings for new messages.
 
-const memoryForOlderModel = new Memory({
-  processors: [
-    new TokenLimiter({
-      limit: 16000, // Example limit for a 16k context model
-      encoding: cl100k_base,
-    }),
-  ],
+**When you configure:**
+
+```typescript
+memory: new Memory({
+  semanticRecall: { enabled: true },
+  vector: myVectorStore,
+  embedder: myEmbedder,
 });
 ```
 
-See the [OpenAI cookbook](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken#encodings) or [`js-tiktoken` repo](https://github.com/dqbd/tiktoken) for more on encodings.
+**Mastra internally:**
+
+1. Creates a `SemanticRecall` processor
+2. Adds it to the agent's input processors (runs before the LLM)
+3. Adds it to the agent's output processors (runs after the LLM)
+4. Requires both a vector store and embedder to be configured
 
-### `ToolCallFilter`
+**What it does:**
 
-This processor removes tool calls from the memory messages sent to the LLM. It saves tokens by excluding potentially verbose tool interactions from the context, which is useful if the details aren't needed for future interactions. It's also useful if you always want your agent to call a specific tool again and not rely on previous tool results in memory.
+- **Input**: Performs vector similarity search to find relevant past messages and prepends them to the conversation
+- **Output**: Creates embeddings for new messages and stores them in the vector store for future retrieval
 
-```typescript copy showLineNumbers {5-14}
+**Example:**
+
+```typescript copy showLineNumbers
+import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { ToolCallFilter, TokenLimiter } from "@mastra/memory/processors";
+import { LibSQLStore } from "@mastra/libsql";
+import { PineconeVector } from "@mastra/pinecone";
+import { OpenAIEmbedder } from "@mastra/openai";
+import { openai } from "@ai-sdk/openai";
 
-const memoryFilteringTools = new Memory({
-  processors: [
-    // Example 1: Remove all tool calls/results
-    new ToolCallFilter(),
+const agent = new Agent({
+  name: "semantic-agent",
+  instructions: "You are a helpful assistant with semantic memory",
+  model: 'openai/gpt-4o',
+  memory: new Memory({
+    storage: new LibSQLStore({
+      id: "memory-store",
+      url: "file:memory.db",
+    }),
+    vector: new PineconeVector({
+      id: "memory-vector",
+      apiKey: process.env.PINECONE_API_KEY!,
+      environment: "us-east-1",
+    }),
+    embedder: new OpenAIEmbedder({
+      model: "text-embedding-3-small",
+      apiKey: process.env.OPENAI_API_KEY!,
+    }),
+    semanticRecall: { enabled: true }, // SemanticRecall processor automatically added
+  }),
+});
+```
 
-    // Example 2: Remove only noisy image generation tool calls/results
-    new ToolCallFilter({ exclude: ["generateImageTool"] }),
+### WorkingMemory
 
-    // Always place TokenLimiter last
-    new TokenLimiter(127000),
-  ],
+Manages working memory state across conversations.
+
+**When you configure:**
+
+```typescript
+memory: new Memory({
+  workingMemory: { enabled: true },
 });
 ```
 
-## Applying Multiple Processors
+**Mastra internally:**
+
+1. Creates a `WorkingMemory` processor
+2. Adds it to the agent's input processors (runs before the LLM)
+3. Requires a storage adapter to be configured
 
-You can chain multiple processors. They execute in the order they appear in the `processors` array. The output of one processor becomes the input for the next.
+**What it does:**
 
-**Order matters!** It's generally best practice to place `TokenLimiter` **last** in the chain. This ensures it operates on the final set of messages after other filtering has occurred, providing the most accurate token limit enforcement.
+- **Input**: Retrieves working memory state for the current thread and prepends it to the conversation
+- **Output**: No output processing
 
-```typescript copy showLineNumbers {7-14}
+**Example:**
+
+```typescript copy showLineNumbers
+import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
-import { ToolCallFilter, TokenLimiter } from "@mastra/memory/processors";
-// Assume a hypothetical 'PIIFilter' custom processor exists
-// import { PIIFilter } from './custom-processors';
-
-const memoryWithMultipleProcessors = new Memory({
-  processors: [
-    // 1. Filter specific tool calls first
-    new ToolCallFilter({ exclude: ["verboseDebugTool"] }),
-    // 2. Apply custom filtering (e.g., remove hypothetical PII - use with caution)
-    // new PIIFilter(),
-    // 3. Apply token limiting as the final step
-    new TokenLimiter(127000),
+import { LibSQLStore } from "@mastra/libsql";
+import { openai } from "@ai-sdk/openai";
+
+const agent = new Agent({
+  name: "working-memory-agent",
+  instructions: "You are an assistant with working memory",
+  model: 'openai/gpt-4o',
+  memory: new Memory({
+    storage: new LibSQLStore({
+      id: "memory-store",
+      url: "file:memory.db",
+    }),
+    workingMemory: { enabled: true }, // WorkingMemory processor automatically added
+  }),
+});
+```
+
+## Manual Control and Deduplication
+
+If you manually add a memory processor to `inputProcessors` or `outputProcessors`, Mastra will **not** automatically add it. This gives you full control over processor ordering:
+
+```typescript copy showLineNumbers
+import { Agent } from "@mastra/core/agent";
+import { Memory } from "@mastra/memory";
+import { MessageHistory } from "@mastra/memory/processors";
+import { TokenLimiter } from "@mastra/core/processors";
+import { LibSQLStore } from "@mastra/libsql";
+import { openai } from "@ai-sdk/openai";
+
+// Custom MessageHistory with different configuration
+const customMessageHistory = new MessageHistory({
+  storage: new LibSQLStore({ id: "memory-store", url: "file:memory.db" }),
+  lastMessages: 20,
+});
+
+const agent = new Agent({
+  name: "custom-memory-agent",
+  instructions: "You are a helpful assistant",
+  model: 'openai/gpt-4o',
+  memory: new Memory({
+    storage: new LibSQLStore({ id: "memory-store", url: "file:memory.db" }),
+    lastMessages: 10, // This would normally add MessageHistory(10)
+  }),
+  inputProcessors: [
+    customMessageHistory, // Your custom one is used instead
+    new TokenLimiter({ limit: 4000 }), // Runs after your custom MessageHistory
   ],
 });
 ```
 
-## Creating Custom Processors
+## Processor Execution Order
+
+Understanding the execution order is important when combining guardrails with memory:
+
+### Input Processors
+
+```
+[Memory Processors] → [Your inputProcessors]
+```
+
+1. **Memory processors run FIRST**: `WorkingMemory`, `MessageHistory`, `SemanticRecall`
+2. **Your input processors run AFTER**: guardrails, filters, validators
+
+This means memory loads conversation history before your processors can validate or filter the input.
+
+### Output Processors
+
+```
+[Your outputProcessors] → [Memory Processors]
+```
+
+1. **Your output processors run FIRST**: guardrails, filters, validators
+2. **Memory processors run AFTER**: `SemanticRecall` (embeddings), `MessageHistory` (persistence)
+
+This ordering is designed to be **safe by default**: if your output guardrail calls `abort()`, the memory processors never run and **no messages are saved**.
 
-You can create custom logic by extending the base `MemoryProcessor` class.
+## Guardrails and Memory
 
-```typescript copy showLineNumbers {5-20,24-27}
-import { Memory, MemoryProcessorOpts, MemoryProcessor } from "@mastra/memory";
-import { CoreMessage } from "@mastra/core/llm";
+The default execution order provides safe guardrail behavior:
 
-class ConversationOnlyFilter extends MemoryProcessor {
-  constructor() {
-    // Provide a name for easier debugging if needed
-    super({ name: "ConversationOnlyFilter" });
-  }
+### Output guardrails (recommended)
 
-  process(
-    messages: CoreMessage[],
-    _opts: MemoryProcessorOpts = {}, // Options passed during memory retrieval, rarely needed here
-  ): CoreMessage[] {
-    // Filter messages based on role
-    return messages.filter(
-      (msg) => msg.role === "user" || msg.role === "assistant",
+Output guardrails run **before** memory processors save messages. If a guardrail aborts:
+
+- The tripwire is triggered
+- Memory processors are skipped
+- **No messages are persisted to storage**
+
+```typescript copy showLineNumbers
+import { Agent } from "@mastra/core/agent";
+import { Memory } from "@mastra/memory";
+import { openai } from "@ai-sdk/openai";
+
+// Output guardrail that blocks inappropriate content
+const contentBlocker = {
+  id: "content-blocker",
+  processOutputResult: async ({ messages, abort }) => {
+    const hasInappropriateContent = messages.some((msg) =>
+      containsBadContent(msg)
     );
-  }
+    if (hasInappropriateContent) {
+      abort("Content blocked by guardrail");
+    }
+    return messages;
+  },
+};
+
+const agent = new Agent({
+  name: "safe-agent",
+  instructions: "You are a helpful assistant",
+  model: 'openai/gpt-4o',
+  memory: new Memory({ lastMessages: 10 }),
+  // Your guardrail runs BEFORE memory saves
+  outputProcessors: [contentBlocker],
+});
+
+// If the guardrail aborts, nothing is saved to memory
+const result = await agent.generate("Hello");
+if (result.tripwire) {
+  console.log("Blocked:", result.tripwireReason);
+  // Memory is empty - no messages were persisted
 }
+```
 
-// Use the custom processor
-const memoryWithCustomFilter = new Memory({
-  processors: [
-    new ConversationOnlyFilter(),
-    new TokenLimiter(127000), // Still apply token limiting
-  ],
+### Input guardrails
+
+Input guardrails run **after** memory processors load history. If a guardrail aborts:
+
+- The tripwire is triggered
+- The LLM is never called
+- Output processors (including memory persistence) are skipped
+- **No messages are persisted to storage**
+
+```typescript copy showLineNumbers
+// Input guardrail that validates user input
+const inputValidator = {
+  id: "input-validator",
+  processInput: async ({ messages, abort }) => {
+    const lastUserMessage = messages.findLast((m) => m.role === "user");
+    if (isInvalidInput(lastUserMessage)) {
+      abort("Invalid input detected");
+    }
+    return messages;
+  },
+};
+
+const agent = new Agent({
+  name: "validated-agent",
+  instructions: "You are a helpful assistant",
+  model: 'openai/gpt-4o',
+  memory: new Memory({ lastMessages: 10 }),
+  // Your guardrail runs AFTER memory loads history
+  inputProcessors: [inputValidator],
 });
 ```
 
+### Summary
+
+| Guardrail Type | When it runs | If it aborts |
+| -------------- | ------------ | ------------ |
+| Input | After memory loads history | LLM not called, nothing saved |
+| Output | Before memory saves | Nothing saved to storage |
+
+Both scenarios are safe - guardrails prevent inappropriate content from being persisted to memory
+
+## Related documentation
+
+- [Processors](/docs/v1/agents/processors) - General processor concepts and custom processor creation
+- [Guardrails](/docs/v1/agents/guardrails) - Security and validation processors
+- [Memory Overview](/docs/v1/memory/overview) - Memory types and configuration
+
 When creating custom processors avoid mutating the input `messages` array or its objects directly.

package/.docs/raw/memory/working-memory.mdx

@@ -131,6 +131,7 @@ Resource-scoped working memory requires specific storage adapters that support t
 - **LibSQL** (`@mastra/libsql`)
 - **PostgreSQL** (`@mastra/pg`)
 - **Upstash** (`@mastra/upstash`)
+- **MongoDB** (`@mastra/mongodb`)
 
 ## Custom Templates
 
@@ -267,10 +268,18 @@ When a schema is provided, the agent receives the working memory as a JSON objec
 }
 ```
 
+### Merge Semantics for Schema-Based Memory
+
+Schema-based working memory uses **merge semantics**, meaning the agent only needs to include fields it wants to add or update. Existing fields are preserved automatically.
+
+- **Object fields are deep merged:** Only provided fields are updated; others remain unchanged
+- **Set a field to `null` to delete it:** This explicitly removes the field from memory
+- **Arrays are replaced entirely:** When an array field is provided, it replaces the existing array (arrays are not merged element-by-element)
+
 ## Choosing Between Template and Schema
 
-- Use a **template** (Markdown) if you want the agent to maintain memory as a free-form text block, such as a user profile or scratchpad.
-- Use a **schema** if you need structured, type-safe data that can be validated and programmatically accessed as JSON.
+- Use a **template** (Markdown) if you want the agent to maintain memory as a free-form text block, such as a user profile or scratchpad. Templates use **replace semantics** — the agent must provide the complete memory content on each update.
+- Use a **schema** if you need structured, type-safe data that can be validated and programmatically accessed as JSON. Schemas use **merge semantics** — the agent only provides fields to update, and existing fields are preserved.
 - Only one mode can be active at a time: setting both `template` and `schema` is not supported.
 
 ## Example: Multi-step Retention

package/.docs/raw/observability/overview.mdx

@@ -49,5 +49,4 @@ We also support various external tracing providers like MLflow, Langfuse, Braint
 
 - **[Set up Tracing](/docs/v1/observability/tracing/overview)**: Configure tracing for your application
 - **[Configure Logging](/docs/v1/observability/logging)**: Add structured logging
-- **[View Examples](/examples/v1/observability/basic-ai-tracing)**: See observability in action
 - **[API Reference](/reference/v1/observability/tracing/instances)**: Detailed configuration options

package/.docs/raw/observability/tracing/bridges/otel.mdx

@@ -0,0 +1,200 @@
+---
+title: "OpenTelemetry Bridge | Tracing | Observability"
+description: "Integrate Mastra tracing with existing OpenTelemetry infrastructure"
+---
+
+# OpenTelemetry Bridge
+
+:::warning
+
+The OpenTelemetry Bridge is currently **experimental**. APIs and configuration options may change in future releases.
+
+:::
+
+The OpenTelemetry (OTEL) Bridge enables bidirectional integration between Mastra's tracing system and existing OpenTelemetry infrastructure. Unlike exporters that send trace data to external platforms, the bridge creates native OTEL spans that participate in your distributed tracing context.
+
+:::info Looking to send traces without existing OTEL infrastructure?
+
+If you don't have existing OpenTelemetry instrumentation, the [OpenTelemetry Exporter](/docs/v1/observability/tracing/exporters/otel) may be simpler — it sends traces directly without requiring an OTEL SDK setup.
+
+:::
+
+## When to Use the Bridge
+
+Use the OtelBridge when you:
+
+- Have existing OTEL instrumentation in your application (HTTP servers, database clients, etc.)
+- Want Mastra operations to appear as child spans of your existing OTEL traces
+- Need OTEL-instrumented code inside Mastra tools to maintain proper parent-child relationships
+- Are building a distributed system where trace context must propagate across services
+
+## How It Works
+
+The OtelBridge provides two-way integration:
+
+**From OTEL to Mastra:**
+- Reads from OTEL ambient context (AsyncLocalStorage) automatically
+- Inherits trace ID and parent span ID from active OTEL spans
+- Respects OTEL sampling decisions — if a trace is not sampled, Mastra won't create spans for it
+- No manual trace ID passing required when OTEL auto-instrumentation is active
+
+**From Mastra to OTEL:**
+- Creates native OTEL spans for Mastra operations (agents, LLM calls, tools, workflows)
+- Maintains proper parent-child relationships in distributed traces
+- Allows OTEL-instrumented code (HTTP clients, database calls) within Mastra operations to nest correctly
+
+## Installation
+
+```bash npm2yarn
+npm install @mastra/otel-bridge
+```
+
+The bridge works with your existing OpenTelemetry setup. Depending on your configuration, you may also need some of these packages:
+
+- `@opentelemetry/sdk-node` - Core Node.js SDK for OTEL
+- `@opentelemetry/auto-instrumentations-node` - Auto-instrumentation for common libraries
+- `@opentelemetry/exporter-trace-otlp-proto` - OTLP exporter (Protobuf over HTTP)
+- `@opentelemetry/exporter-trace-otlp-http` - OTLP exporter (JSON over HTTP)
+- `@opentelemetry/exporter-trace-otlp-grpc` - OTLP exporter (gRPC)
+- `@opentelemetry/sdk-trace-base` - Base tracing SDK (for BatchSpanProcessor, etc.)
+- `@opentelemetry/core` - Core utilities (for W3CTraceContextPropagator, etc.)
+
+## Configuration
+
+Using the OtelBridge requires two steps:
+
+1. Configure OpenTelemetry instrumentation in your application
+2. Add the OtelBridge to your Mastra observability config
+
+### Step 1: OpenTelemetry Instrumentation
+
+Create an instrumentation file that initializes OTEL. This must run before your application code:
+
+```typescript title="instrumentation.ts" showLineNumbers copy
+import { NodeSDK } from "@opentelemetry/sdk-node";
+import { getNodeAutoInstrumentations } from "@opentelemetry/auto-instrumentations-node";
+import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-proto";
+import { BatchSpanProcessor } from "@opentelemetry/sdk-trace-base";
+import { W3CTraceContextPropagator } from "@opentelemetry/core";
+
+const sdk = new NodeSDK({
+  serviceName: "my-service",
+  spanProcessors: [
+    new BatchSpanProcessor(
+      new OTLPTraceExporter({
+        url: process.env.OTEL_EXPORTER_OTLP_ENDPOINT || "http://localhost:4318/v1/traces",
+      })
+    ),
+  ],
+  instrumentations: [getNodeAutoInstrumentations()],
+  textMapPropagator: new W3CTraceContextPropagator(),
+});
+
+sdk.start();
+
+export { sdk };
+```
+
+### Step 2: Mastra Configuration
+
+Add the OtelBridge to your Mastra observability config:
+
+```typescript title="src/mastra/index.ts" showLineNumbers copy
+import { Mastra } from "@mastra/core";
+import { Observability } from "@mastra/observability";
+import { OtelBridge } from "@mastra/otel-bridge";
+
+export const mastra = new Mastra({
+  observability: new Observability({
+    configs: {
+      default: {
+        serviceName: "my-service",
+        bridge: new OtelBridge(),
+      },
+    },
+  }),
+  agents: {
+    /* your agents */
+  },
+});
+```
+
+No Mastra exporters are required when using the bridge — traces are sent via your OTEL SDK configuration. You can optionally add Mastra exporters if you want to send traces to additional destinations.
+
+### Running Your Application
+
+Use the `--import` flag to ensure instrumentation loads before your application:
+
+```bash
+tsx --import ./instrumentation.ts ./src/index.ts
+```
+
+## Semantic Conventions
+
+The OtelBridge exports Mastra spans using [OpenTelemetry Semantic Conventions for GenAI v1.38.0](https://github.com/open-telemetry/semantic-conventions/tree/v1.38.0/docs/gen-ai). This includes standardized span names (`chat {model}`, `execute_tool {tool_name}`, etc.) and attributes (`gen_ai.usage.input_tokens`, `gen_ai.request.model`, etc.).
+
+For details on span naming and attributes, see the [OpenTelemetry Exporter semantic conventions](/docs/v1/observability/tracing/exporters/otel#opentelemetry-semantic-conventions).
+
+## Trace Hierarchy
+
+With the OtelBridge, your traces maintain proper hierarchy across OTEL and Mastra boundaries:
+
+```
+HTTP POST /api/chat (from Hono middleware)
+└── agent.assistant (from Mastra via OtelBridge)
+    ├── chat gpt-4o (LLM call)
+    ├── tool.execute search (tool execution)
+    │   └── HTTP GET api.example.com (from OTEL auto-instrumentation)
+    └── chat gpt-4o (follow-up LLM call)
+```
+
+## Multi-Service Distributed Tracing
+
+The OtelBridge enables trace propagation across service boundaries. When Service A calls Service B via HTTP, trace context propagates automatically:
+
+```
+Service A: HTTP POST /api/process
+└── HTTP POST service-b/api/analyze (outgoing call)
+
+Service B: HTTP POST /api/analyze (incoming call - same trace!)
+└── agent.analyzer (Mastra agent inherits trace context)
+    └── chat gpt-4o
+```
+
+Both services must have:
+1. OTEL instrumentation configured
+2. W3C Trace Context propagator enabled
+3. Mastra with OtelBridge configured
+
+## Using Tags
+
+Tags help you categorize and filter traces in your OTEL backend. Add tags when executing agents or workflows:
+
+```typescript
+const result = await agent.generate({
+  messages: [{ role: "user", content: "Hello" }],
+  tracingOptions: {
+    tags: ["production", "experiment-v2", "user-request"],
+  },
+});
+```
+
+Tags are exported as a JSON string in the `mastra.tags` span attribute for broad backend compatibility. Common use cases include:
+
+- Environment labels: `"production"`, `"staging"`
+- Experiment tracking: `"experiment-v1"`, `"control-group"`
+- Priority levels: `"priority-high"`, `"batch-job"`
+
+## Troubleshooting
+
+If traces aren't appearing or connecting as expected:
+
+- Verify OTEL SDK is initialized before Mastra (use `--import` flag or import at top of entry point)
+- Ensure the OtelBridge is added to your observability config
+- Check that your OTEL backend is running and accessible
+
+## Related
+
+- [Tracing Overview](/docs/v1/observability/tracing/overview)
+- [OpenTelemetry Exporter](/docs/v1/observability/tracing/exporters/otel) - For sending traces to OTEL backends
+- [OtelBridge Reference](/reference/v1/observability/tracing/bridges/otel) - API documentation