---
schema_version: "1"
id: d0736740f61356e1afefb6ab3b5d959c82920b4532505052eb55e0387d582f1e
title: Omni Gateway Agent Policies
collection: mulesoft
version: current
locale: en-us
portal_url: https://docs.salesforce.com/mulesoft/current/en-us/gateway/1.13/agent-policies.md
canonical_url: https://docs.mulesoft.com/gateway/1.13/agent-policies
source_site: docs.mulesoft.com
content_type: documentation
content_hash: 6010abdee5c3d0cebf78a5c845978886fe71926688110fcdde8c8e3f04130718
description: MuleSoft Documentation Site
release: "1.13"
latest: false
---
---
product: Omni Gateway
version: 1.13
---

# Omni Gateway Agent Policies

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Policies enforce rules when Omni Gateway processes requests, enabling you to secure and govern your
server instances. Omni Gateway includes A2A and MCP specific policies that provide enhanced security
and control over agent interactions.

To apply a policy, see
[Applying Policies for Managed Omni Gateways and Connected Mode](https://docs.mulesoft.com/gateway/1.13/gateway-secure-conn).

Omni Gateway MCP and A2A server instances also support other Omni Gateway policies to protect server
instances through rate limiting, authentication, authorization, threat protection, monitoring, and
logging. For more information about MuleSoft-provided policies, see the
[Inbound Policies Directory](https://docs.mulesoft.com/gateway/1.13/policies-included-directory) and
[Outbound Policies Directory](https://docs.mulesoft.com/gateway/1.13/policies-outbound-directory).

To extend existing functionality or define new functionality, create custom policies based on your
specific business requirements. For information about creating custom policies, see
[Omni Gateway Policy Development Kit (PDK) Overview](https://docs.mulesoft.com/pdk/latest/policies-pdk-overview).

## SSE Policies

Both A2A and MCP support the following policies for Server-Sent Events (SSE) streaming:

<table><colgroup><col> <col></colgroup><thead><tr><th>Policy</th><th>Summary</th></tr></thead><tbody><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-sse-logging">SSE Logging</a></p></td><td><p>Logs every SSE event while streaming</p></td></tr></tbody></table>

## A2A Policies

<table><colgroup><col> <col></colgroup><thead><tr><th>Policy</th><th>Summary</th></tr></thead><tbody><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-agent-card">A2A Agent Card</a></p></td><td><p>Rewrites the Agent Card URL to match the server instance public URL</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-pii-detector">A2A PII Detector</a></p></td><td><p>Detects personally identifiable information (PII) in requests sent to the agent</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-prompt-decorator">A2A Prompt Decorator</a></p></td><td><p>Decorates prompts with context information</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-schema-validation">A2A Schema Validation</a></p></td><td><p>Validates agent requests to ensure they conform to the A2A specification</p></td></tr></tbody></table>

## A2A v1 Policies

<table><colgroup><col> <col></colgroup><thead><tr><th>Policy</th><th>Summary</th></tr></thead><tbody><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-quality-evaluation">A2A Quality Evaluation</a></p></td><td><p>Evaluates completed A2A agent task responses using an LLM to score quality and completeness</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-agent-card">A2A v1 Agent Card</a></p></td><td><p>Rewrites interface URLs in the A2A v1.0 agent card to match the gateway’s public address</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-azure-guardrails">A2A v1 Azure Content Guardrails</a></p></td><td><p>Evaluates A2A v1 agent messages against Azure AI Content Safety for harmful content, jailbreak attempts, hallucinations, and copyrighted material</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-bedrock-guardrails">A2A v1 Bedrock Guardrails</a></p></td><td><p>Evaluates A2A v1.0 agent requests and responses against Amazon Bedrock guardrails for content safety, PII detection, and contextual grounding</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-pii-detector">A2A v1 PII Detector</a></p></td><td><p>Detects personally identifiable information (PII) in A2A v1 requests across all transports</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-prompt-decorator">A2A v1 Prompt Decorator</a></p></td><td><p>Decorates A2A v1 prompts with additional context information</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-schema-validation">A2A v1 Schema Validation</a></p></td><td><p>Verifies that requests to the agent are compliant with the A2A v1.0 specification</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-outbound-a2a-v1-to-v03-transcoder">A2A v1 to v0.3 Transcoder</a></p></td><td><p>Transcodes protocol messages bidirectionally between A2A v1.0 JSON-RPC clients and A2A v0.3 backend servers</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-a2a-v1-token-rate-limit">A2A v1 Token Based Rate Limit</a></p></td><td><p>Rate limits v1 A2A agent usage of upstream resources</p></td></tr></tbody></table>

## MCP Policies

<table><colgroup><col> <col></colgroup><thead><tr><th>Policy</th><th>Summary</th></tr></thead><tbody><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-attribute-access-control">MCP Attribute-Based Access Control</a></p></td><td><p>Controls access to tools, resources, and prompts based on user information such as Tiers, IP, Headers, or Claims</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-global-access">MCP Global Access</a></p></td><td><p>Restricts which MCP tools are exposed by defining Allow and Block rules</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-pii-detector">MCP PII Detector</a></p></td><td><p>Detects personally identifiable information (PII) in Model Context Protocol (MCP) JSON-RPC traffic on both the request and response sides</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-payload-optimization">MCP Payload Optimization</a></p></td><td><p>Reduces tool response token consumption using one or more configurable methods: remove structural noise, trim oversized responses to match agent intent, or compress repeated structures into TOON</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-progressive-disclosure">MCP Tools Progressive Disclosure</a></p></td><td><p>Reduces context window token cost by exposing tools on-demand through search</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-schema-validation">MCP Schema Validation</a></p></td><td><p>Validates MCP requests to ensure they conform to the MCP specification</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-support">MCP Support</a></p></td><td><p>Adds MCP support to an Omni Gateway MCP server instance. This policy is required for your MCP server instance to function properly.</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-mcp-tool-mapping">MCP Tool Mapping</a></p></td><td><p>Redefines tool names and descriptions to reduce prompt complexity and improve LLM comprehension</p></td></tr></tbody></table>

## LLM Policies

<table><colgroup><col> <col></colgroup><thead><tr><th>Policy</th><th>Summary</th></tr></thead><tbody><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-azure-content-safety">Azure Content Safety</a></p></td><td><p>Evaluates LLM prompts and responses against Azure AI Content Safety for harmful content, jailbreak attempts, hallucinations, and copyrighted material</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-bedrock-guardrails">Amazon Bedrock Guardrails</a></p></td><td><p>Evaluates LLM prompts and responses against Amazon Bedrock guardrails for content safety, PII detection, and contextual grounding</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-llm-pii-detection">LLM PII Detection</a></p></td><td><p>Detects personally identifiable information (PII) in OpenAI and Anthropic format LLM requests and responses</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-llm-token-rate-limit">LLM Token Based Rate Limit</a></p></td><td><p>Limits Model Proxy usage based on the number of tokens consumed</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-llm-proxy-request-compression">Model Proxy Request Compression</a></p></td><td><p>Compresses message content and replayed tool results in Model Proxy request bodies before they reach the upstream provider, reducing billed tokens</p></td></tr><tr><td><p><a href="https://docs.mulesoft.com/gateway/1.13/policies-included-regex-prompt-guard">Regex Prompt Guard</a></p></td><td><p>Blocks LLM requests that match deny-list regex patterns</p></td></tr></tbody></table>

## See Also

- [Ordering Policies](https://docs.mulesoft.com/gateway/1.13/policies-reorder)

- [DataWeave Support in Omni Gateway Policies](https://docs.mulesoft.com/gateway/1.13/policies-dataweave-support)