Guardrails

Agents use processors to apply guardrails to inputs and outputs. They run before or after each interaction, giving you a way to review, transform, or block information as it passes between the user and the agent.

Processors can be configured as:

• inputProcessors: Applied before messages reach the language model.
• outputProcessors: Applied to responses before they're returned to users.

Some processors are hybrid, meaning they can be used with either inputProcessors or outputProcessors, depending on where the logic should be applied.

When to use processors

Use processors for content moderation, prompt injection prevention, response sanitization, message transformation, and other security-related controls. Mastra provides several built-in input and output processors for common use cases.

Adding processors to an agent

Import and instantiate the relevant processor class, and pass it to your agent’s configuration using either the inputProcessors or outputProcessors option:

src/mastra/agents/moderated-agent.ts

import { Agent } from "@mastra/core/agent";
import { ModerationProcessor } from "@mastra/core/processors";

export const moderatedAgent = new Agent({
  id: "moderated-agent",
  name: "Moderated Agent",
  instructions: "You are a helpful assistant",
  model: "openai/gpt-5.1",
  inputProcessors: [
    new ModerationProcessor({
      model: "openrouter/openai/gpt-oss-safeguard-20b",
      categories: ["hate", "harassment", "violence"],
      threshold: 0.7,
      strategy: "block",
      instructions: "Detect and flag inappropriate content in user messages",
    }),
  ],
});

Input processors

Input processors are applied before user messages reach the language model. They are useful for normalization, validation, content moderation, prompt injection detection, and security checks.

Normalizing user messages

The UnicodeNormalizer is an input processor that cleans and normalizes user input by unifying Unicode characters, standardizing whitespace, and removing problematic symbols, allowing the LLM to better understand user messages.

src/mastra/agents/normalized-agent.ts

import { UnicodeNormalizer } from "@mastra/core/processors";

export const normalizedAgent = new Agent({
  id: "normalized-agent",
  name: "Normalized Agent",
  // ...
  inputProcessors: [
    new UnicodeNormalizer({
      stripControlChars: true,
      collapseWhitespace: true,
    }),
  ],
});

See UnicodeNormalizer for a full list of configuration options.

Preventing prompt injection

The PromptInjectionDetector is an input processor that scans user messages for prompt injection, jailbreak attempts, and system override patterns. It uses an LLM to classify risky input and can block or rewrite it before it reaches the model.

src/mastra/agents/secure-agent.ts

import { PromptInjectionDetector } from "@mastra/core/processors";

export const secureAgent = new Agent({
  id: "secure-agent",
  name: "Secure Agent",
  // ...
  inputProcessors: [
    new PromptInjectionDetector({
      model: "openrouter/openai/gpt-oss-safeguard-20b",
      threshold: 0.8,
      strategy: "rewrite",
      detectionTypes: ["injection", "jailbreak", "system-override"],
    }),
  ],
});

See PromptInjectionDetector for a full list of configuration options.

Detecting and translating language

The LanguageDetector is an input processor that detects and translates user messages into a target language, enabling multilingual support while maintaining consistent interaction. It uses an LLM to identify the language and perform the translation.

src/mastra/agents/multilingual-agent.ts

import { LanguageDetector } from "@mastra/core/processors";

export const multilingualAgent = new Agent({
  id: "multilingual-agent",
  name: "Multilingual Agent",
  // ...
  inputProcessors: [
    new LanguageDetector({
      model: "openrouter/openai/gpt-oss-safeguard-20b",
      targetLanguages: ["English", "en"],
      strategy: "translate",
      threshold: 0.8,
    }),
  ],
});

See LanguageDetector for a full list of configuration options.

Output processors

Output processors are applied after the language model generates a response, but before it is returned to the user. They are useful for response optimization, moderation, transformation, and applying safety controls.

Batching streamed output

The BatchPartsProcessor is an output processor that combines multiple stream parts before emitting them to the client. This reduces network overhead and improves the user experience by consolidating small chunks into larger batches.

src/mastra/agents/batched-agent.ts

import { BatchPartsProcessor } from "@mastra/core/processors";

export const batchedAgent = new Agent({
  id: "batched-agent",
  name: "Batched Agent",
  // ...
  outputProcessors: [
    new BatchPartsProcessor({
      batchSize: 5,
      maxWaitTime: 100,
      emitOnNonText: true,
    }),
  ],
});

See BatchPartsProcessor for a full list of configuration options.

Limiting token usage

The TokenLimiterProcessor is an output processor that limits the number of tokens in model responses. It helps manage cost and performance by truncating or blocking messages when the limit is exceeded.

src/mastra/agents/limited-agent.ts

import { TokenLimiterProcessor } from "@mastra/core/processors";

export const limitedAgent = new Agent({
  id: "limited-agent",
  name: "Limited Agent",
  // ...
  outputProcessors: [
    new TokenLimiterProcessor({
      limit: 1000,
      strategy: "truncate",
      countMode: "cumulative",
    }),
  ],
});

See TokenLimiterProcessor for a full list of configuration options.

Scrubbing system prompts

The SystemPromptScrubber is an output processor that detects and redacts system prompts or other internal instructions from model responses. It helps prevent unintended disclosure of prompt content or configuration details that could introduce security risks. It uses an LLM to identify and redact sensitive content based on configured detection types.

src/mastra/agents/scrubbed-agent.ts

import { SystemPromptScrubber } from "@mastra/core/processors";

const scrubbedAgent = new Agent({
  id: "scrubbed-agent",
  name: "Scrubbed Agent",
  outputProcessors: [
    new SystemPromptScrubber({
      model: "openrouter/openai/gpt-oss-safeguard-20b",
      strategy: "redact",
      customPatterns: ["system prompt", "internal instructions"],
      includeDetections: true,
      instructions:
        "Detect and redact system prompts, internal instructions, and security-sensitive content",
      redactionMethod: "placeholder",
      placeholderText: "[REDACTED]",
    }),
  ],
});

See SystemPromptScrubber for a full list of configuration options.

note

When streaming responses over HTTP, Mastra redacts sensitive request data (system prompts, tool definitions, API keys) from stream chunks at the server level by default. See Stream data redaction for details.

Hybrid processors

Hybrid processors can be applied either before messages are sent to the language model or before responses are returned to the user. They are useful for tasks like content moderation and PII redaction.

Moderating input and output

The ModerationProcessor is a hybrid processor that detects inappropriate or harmful content across categories like hate, harassment, and violence. It can be used to moderate either user input or model output, depending on where it's applied. It uses an LLM to classify the message and can block or rewrite it based on your configuration.

src/mastra/agents/moderated-agent.ts

import { ModerationProcessor } from "@mastra/core/processors";

export const moderatedAgent = new Agent({
  id: "moderated-agent",
  name: "Moderated Agent",
  // ...
  inputProcessors: [
    new ModerationProcessor({
      model: "openrouter/openai/gpt-oss-safeguard-20b",
      threshold: 0.7,
      strategy: "block",
      categories: ["hate", "harassment", "violence"],
    }),
  ],
  outputProcessors: [
    new ModerationProcessor({
      // ...
    }),
  ],
});

See ModerationProcessor for a full list of configuration options.

Detecting and redacting PII

The PIIDetector is a hybrid processor that detects and removes personally identifiable information such as emails, phone numbers, and credit cards. It can redact either user input or model output, depending on where it's applied. It uses an LLM to identify sensitive content based on configured detection types.

src/mastra/agents/private-agent.ts

import { PIIDetector } from "@mastra/core/processors";

export const privateAgent = new Agent({
  id: "private-agent",
  name: "Private Agent",
  // ...
  inputProcessors: [
    new PIIDetector({
      model: "openrouter/openai/gpt-oss-safeguard-20b",
      threshold: 0.6,
      strategy: "redact",
      redactionMethod: "mask",
      detectionTypes: ["email", "phone", "credit-card"],
      instructions: "Detect and mask personally identifiable information.",
    }),
  ],
  outputProcessors: [
    new PIIDetector({
      // ...
    }),
  ],
});

See PIIDetector for a full list of configuration options.

Applying multiple processors

You can apply multiple processors by listing them in the inputProcessors or outputProcessors array. They run in sequence, with each processor receiving the output of the one before it.

A typical order might be:

1. Normalization: Standardize input format (UnicodeNormalizer).
2. Security checks: Detect threats or sensitive content (PromptInjectionDetector, PIIDetector).
3. Filtering: Block or transform messages (ModerationProcessor).

The order affects behavior, so arrange processors to suit your goals.

src/mastra/agents/test-agent.ts

import {
  UnicodeNormalizer,
  ModerationProcessor,
  PromptInjectionDetector,
  PIIDetector,
} from "@mastra/core/processors";

export const testAgent = new Agent({
  id: "test-agent",
  name: "Test Agent",
  // ...
  inputProcessors: [
    new UnicodeNormalizer({
      //...
    }),
    new PromptInjectionDetector({
      // ...
    }),
    new PIIDetector({
      // ...
    }),
    new ModerationProcessor({
      // ...
    }),
  ],
});

Processor strategies

Many of the built-in processors support a strategy parameter that controls how they handle flagged input or output. Supported values may include: block, warn, detect, or redact.

Most strategies allow the request to continue without interruption. When block is used, the processor calls its internal abort() function, which immediately stops the request and prevents any subsequent processors from running.

src/mastra/agents/private-agent.ts

import { PIIDetector } from "@mastra/core/processors";

export const privateAgent = new Agent({
  id: "private-agent",
  name: "Private Agent",
  // ...
  inputProcessors: [
    new PIIDetector({
      // ...
      strategy: "block",
    }),
  ],
});

Handling blocked requests

When a processor blocks a request, the agent will still return successfully without throwing an error. To handle blocked requests, check for tripwire in the response.

For example, if an agent uses the PIIDetector with strategy: "block" and the request includes a credit card number, it will be blocked and the response will include tripwire information.

.generate() example

const result = await agent.generate(
  "Is this credit card number valid?: 4543 1374 5089 4332",
);

if (result.tripwire) {
  console.error("Blocked:", result.tripwire.reason);
  console.error("Processor:", result.tripwire.processorId);
  // Optional: check if retry was requested
  console.error("Retry requested:", result.tripwire.retry);
  // Optional: access additional metadata
  console.error("Metadata:", result.tripwire.metadata);
}

.stream() example

const stream = await agent.stream(
  "Is this credit card number valid?: 4543 1374 5089 4332",
);

for await (const chunk of stream.fullStream) {
  if (chunk.type === "tripwire") {
    console.error("Blocked:", chunk.payload.reason);
    console.error("Processor:", chunk.payload.processorId);
  }
}

In this case, the reason indicates that a credit card number was detected:

PII detected. Types: credit-card

Requesting retries

Processors can request that the LLM retry its response with feedback. This is useful for implementing quality checks:

export class QualityChecker implements Processor {
  id = "quality-checker";

  async processOutputStep({ text, abort, retryCount }) {
    const score = await evaluateQuality(text);

    if (score < 0.7 && retryCount < 3) {
      // Request retry with feedback for the LLM
      abort("Response quality too low. Please be more specific.", {
        retry: true,
        metadata: { score },
      });
    }

    return [];
  }
}

The abort() function accepts an optional second parameter with:

• retry: true - Request the LLM retry the step
• metadata: unknown - Attach additional data for debugging/logging

Use retryCount to track retry attempts and prevent infinite loops.

Custom processors

If the built-in processors don’t cover your needs, you can create your own by extending the Processor class.

Available examples:

• Message Length Limiter
• Response Length Limiter
• Response Validator