--- schema_version: "1" id: 804f529280ed88e9c09f856ca4bdb6942069bf52efe75eac81834460906384b8 title: Inbound Policies Directory collection: mulesoft version: current locale: en-us portal_url: https://docs.salesforce.com/mulesoft/current/en-us/gateway/1.13/policies-included-directory.md canonical_url: https://docs.mulesoft.com/gateway/1.13/policies-included-directory source_site: docs.mulesoft.com content_type: documentation content_hash: 12ec8e346c1c942f02191239f17d5752d66f84d993d9272842f916358b85934e description: MuleSoft Documentation Site release: "1.13" latest: false --- # Inbound Policies Directory ## [](#inbound-policies-included-in-omni-gateway)Inbound Policies Included in Omni Gateway

Policy Category Summary

Policy	Category	Summary
A2A Agent Card	A2A	Rewrites the Agent Card URL to match the server instance public URL
A2A PII Detector	A2A	Detects personally identifiable information (PII) in requests sent to the agent
A2A Prompt Decorator	A2A	Decorates prompts with context information
A2A Quality Evaluation	A2A	Evaluates completed A2A agent task responses using an LLM to score quality and completeness
A2A Schema Validation	A2A	Validates Agent requests to ensure they conform to the A2A specification
A2A Token Based Rate Limit	A2A	Limits API usage based on the number of GPT-4o-mini tokens consumed by the agents
A2A v1 Agent Card	A2A	Rewrites interface URLs in the A2A v1.0 agent card to match the gateway’s public address
A2A v1 Azure Content Guardrails	A2A	Evaluates A2A v1 agent messages against Azure AI Content Safety for harmful content, jailbreak attempts, hallucinations, and copyrighted material
A2A v1 Bedrock Guardrails	A2A	Evaluates A2A v1.0 agent requests and responses against Amazon Bedrock guardrails for content safety, PII detection, and contextual grounding
A2A v1 PII Detector	A2A	Detects personally identifiable information (PII) in A2A v1 requests across all transports
A2A v1 Prompt Decorator	A2A	Decorates A2A v1 prompts with additional context information
A2A v1 Schema Validation	A2A	Verifies that requests to the agent are compliant with the A2A v1.0 specification
A2A v1 Token Based Rate Limit	A2A	Controls API usage by enforcing token-based rate limits
Agent Connection Telemetry	A2A and MCP	Tracks the number of requests made to agent or MCP server instances
Amazon Bedrock Guardrails	LLM	Evaluates LLM prompts and responses against Amazon Bedrock guardrails for content safety, PII detection, and contextual grounding
API Security-Identification Header	Security	Adds API instance identifiers as response headers for external security platform correlation
Azure Content Safety	LLM	Evaluates LLM prompts and responses against Azure AI Content Safety for harmful content, jailbreak attempts, hallucinations, and copyrighted material
Basic Authentication: LDAP	Security	Allows access based on the basic authorization mechanism, with user-password defined on LDAP
Basic Authentication: Simple	Security	Allows access based on the basic authorization mechanism, with a single user-password
Client ID Enforcement	Compliance	Allows access only to authorized client applications
Cross-Origin Resource Sharing (CORS)	Compliance	Enables access to resources residing in external domains
DataWeave Body Transformation	Transformation	Transforms request or response body content with a DataWeave script
DataWeave Headers Transformation	Transformation	Transforms request or response headers with a DataWeave script
DataWeave Request Filter	Transformation	Filters requests by using a DataWeave script
External Authorization	Security	Authenticates requests with an external gRPC or HTTP authorization service
External Processing	Transformation	Sends the incoming HTTP requests or outgoing HTTP responses to an external gRPC service for additional processing
GraphQL Introspection Control	GraphQL	Blocks or allows requests that access the `schema`, `type`, and `__typename` GraphQL meta fields
GraphQL Operation Limits	GraphQL	Limits GraphQL operation depth, aliases, root fields, and directives
GraphQL Schema Validation	GraphQL	Validates incoming GraphQL operations against a GraphQL schema definition
GraphQL Static Query Complexity	GraphQL	Calculates query complexity and blocks requests that exceed the defined budget
Header Injection	Transformation	Adds headers to a request or a response
Header Removal	Transformation	Removes headers from a request or a response
Health Check	Quality of Service	Monitors API upstream health at specific intervals
HTTP Caching	Quality of Service	Caches HTTP responses from an API implementation
Injection Protection	Security	Scans request headers, path, query, and body to protect against SQL, XSS, and custom injection attacks in incoming requests
IP Allowlist	Security	Allows a list or range of specified IP addresses to request access
IP Blocklist	Security	Blocks a single IP address or a range of IP addresses from accessing an API endpoint
JSON Threat Protection	Security	Protects against malicious JSON in API requests
JWT Validation	Security	Validates a JWT
LLM PII Detection	LLM	Detects personally identifiable information (PII) in OpenAI and Anthropic format LLM requests and responses
LLM Token Based Rate Limit	LLM	Limits Model Proxy usage based on the number of tokens consumed (OpenAI-format APIs)
MCP Attribute-Based Access Control	MCP	Controls access to tools, resources, and prompts based on user information such as Tiers, IP, Headers, or Claims
MCP Global Access	MCP	Restricts which MCP tools are exposed by defining Allow and Block rules
MCP PII Detector	MCP	Detects personally identifiable information (PII) in Model Context Protocol (MCP) JSON-RPC traffic on both the request and response sides
MCP Payload Optimization	MCP	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
MCP Tools Progressive Disclosure	MCP	Reduces context window token cost by exposing tools on-demand through search
MCP Schema Validation	MCP	Validates MCP requests to ensure they conform to the MCP specification
MCP Support	MCP	Adds MCP support to an Omni Gateway MCP server instance. This policy is required for your MCP server instance to function properly.
MCP Tool Mapping	MCP	Redefines tool names and descriptions to reduce prompt complexity and improve LLM comprehension
Message Logging	Troubleshooting	Logs custom messages using information from incoming requests, responses from the backend, or information from other policies applied to the same API endpoint
Model Proxy Request Compression	LLM	Compresses message content and replayed tool results in Model Proxy request bodies before they reach the upstream provider, reducing billed tokens
OAuth 2.0 Protected Resource Metadata	Security	Serves OAuth 2.0 Protected Resource Metadata at the well-known endpoint
OAuth 2.0 Token Introspection	Security	Allows access only to authorized client applications
OpenID Connect OAuth 2.0 Access Token Enforcement	Security	Allows access only to authorized client applications
Rate Limiting	Quality of Service	Monitors access to an API by defining the maximum number of requests processed within a period of time
Rate Limiting: SLA-based	Quality of Service	Monitors access to an API by defining the maximum number of requests processed within a timespan, based on SLAs
Regex Prompt Guard	LLM	Blocks LLM requests that match deny-list regex patterns
Response Idle Timeout	Quality of Service	Set a maximum duration Omni Gateway waits for a response from an upstream service
Schema Validation	Security	Validates incoming traffic against a supplied OAS3 schema
SOAP Schema Validation	Security	Validates incoming traffic against a specified WSDL schema
Spike Control	Quality of Service	Regulates API traffic
SSE Logging	SSE	Logs every SSE event while streaming
Stream Idle Timeout	Quality of Service	Set a maximum duration a stream can remain idle without receiving a request or response
Tracing	Troubleshooting	Configure OpenTelemetry distributed tracing for an API
Traffic Management for Multiple Upstream Services	Quality of Service	Manages API instance traffic to multiple upstream services from a single consumer endpoint
Traffic Management for Multiple Upstream Services (Weighted)	Quality of Service	Manages API instance traffic to multiple upstream services from a single consumer endpoint, using weighted percentages
Transport Layer Security (TLS) - Inbound	Security	Enables authentication between a client and the API proxy
WebSocket Connection Limit	Quality of Service	Limits the number of simultaneous WebSocket connections that each API instance allows
XML Threat Protection	Security	Protects against malicious XML in API requests

A2A

Rewrites the Agent Card URL to match the server instance public URL

A2A PII Detector

A2A

Detects personally identifiable information (PII) in requests sent to the agent

A2A Prompt Decorator

A2A

Decorates prompts with context information

A2A Quality Evaluation

A2A

Evaluates completed A2A agent task responses using an LLM to score quality and completeness

A2A Schema Validation

A2A

Validates Agent requests to ensure they conform to the A2A specification

A2A Token Based Rate Limit

A2A

Limits API usage based on the number of GPT-4o-mini tokens consumed by the agents

A2A v1 Agent Card

A2A

Rewrites interface URLs in the A2A v1.0 agent card to match the gateway’s public address

A2A v1 Azure Content Guardrails

A2A

Evaluates A2A v1 agent messages against Azure AI Content Safety for harmful content, jailbreak attempts, hallucinations, and copyrighted material

A2A v1 Bedrock Guardrails

A2A

Evaluates A2A v1.0 agent requests and responses against Amazon Bedrock guardrails for content safety, PII detection, and contextual grounding

A2A v1 PII Detector

A2A

Detects personally identifiable information (PII) in A2A v1 requests across all transports

A2A v1 Prompt Decorator

A2A

Decorates A2A v1 prompts with additional context information

A2A v1 Schema Validation

A2A

Verifies that requests to the agent are compliant with the A2A v1.0 specification

A2A v1 Token Based Rate Limit

A2A

Controls API usage by enforcing token-based rate limits

Agent Connection Telemetry

A2A and MCP

Tracks the number of requests made to agent or MCP server instances

Amazon Bedrock Guardrails

LLM

Evaluates LLM prompts and responses against Amazon Bedrock guardrails for content safety, PII detection, and contextual grounding

API Security-Identification Header

Security

Adds API instance identifiers as response headers for external security platform correlation

Azure Content Safety

LLM

Evaluates LLM prompts and responses against Azure AI Content Safety for harmful content, jailbreak attempts, hallucinations, and copyrighted material

Basic Authentication: LDAP

Security

Allows access based on the basic authorization mechanism, with user-password defined on LDAP

Basic Authentication: Simple

Security

Allows access based on the basic authorization mechanism, with a single user-password

Client ID Enforcement

Compliance

Allows access only to authorized client applications

Cross-Origin Resource Sharing (CORS)

Compliance

Enables access to resources residing in external domains

DataWeave Body Transformation

Transformation

Transforms request or response body content with a DataWeave script

DataWeave Headers Transformation

Transformation

Transforms request or response headers with a DataWeave script

DataWeave Request Filter

Transformation

Filters requests by using a DataWeave script

External Authorization

Security

Authenticates requests with an external gRPC or HTTP authorization service

External Processing

Transformation

Sends the incoming HTTP requests or outgoing HTTP responses to an external gRPC service for additional processing

GraphQL Introspection Control

GraphQL

Blocks or allows requests that access the schema, type, and __typename GraphQL meta fields

GraphQL Operation Limits

GraphQL

Limits GraphQL operation depth, aliases, root fields, and directives

GraphQL Schema Validation

GraphQL

Validates incoming GraphQL operations against a GraphQL schema definition

GraphQL Static Query Complexity

GraphQL

Calculates query complexity and blocks requests that exceed the defined budget

Header Injection

Transformation

Adds headers to a request or a response

Header Removal

Transformation

Removes headers from a request or a response

Health Check

Quality of Service

Monitors API upstream health at specific intervals

HTTP Caching

Quality of Service

Caches HTTP responses from an API implementation

Injection Protection

Security

Scans request headers, path, query, and body to protect against SQL, XSS, and custom injection attacks in incoming requests

IP Allowlist

Security

Allows a list or range of specified IP addresses to request access

IP Blocklist

Security

Blocks a single IP address or a range of IP addresses from accessing an API endpoint

JSON Threat Protection

Security

Protects against malicious JSON in API requests

JWT Validation

Security

Validates a JWT

LLM PII Detection

LLM

Detects personally identifiable information (PII) in OpenAI and Anthropic format LLM requests and responses

LLM Token Based Rate Limit

LLM

Limits Model Proxy usage based on the number of tokens consumed (OpenAI-format APIs)

MCP Attribute-Based Access Control

MCP

Controls access to tools, resources, and prompts based on user information such as Tiers, IP, Headers, or Claims

MCP Global Access

MCP

Restricts which MCP tools are exposed by defining Allow and Block rules

MCP PII Detector

MCP

Detects personally identifiable information (PII) in Model Context Protocol (MCP) JSON-RPC traffic on both the request and response sides

MCP Payload Optimization

MCP

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

MCP Tools Progressive Disclosure

MCP

Reduces context window token cost by exposing tools on-demand through search

MCP Schema Validation

MCP

Validates MCP requests to ensure they conform to the MCP specification

MCP Support

MCP

Adds MCP support to an Omni Gateway MCP server instance. This policy is required for your MCP server instance to function properly.

MCP Tool Mapping

MCP

Redefines tool names and descriptions to reduce prompt complexity and improve LLM comprehension

Message Logging

Troubleshooting

Logs custom messages using information from incoming requests, responses from the backend, or information from other policies applied to the same API endpoint

Model Proxy Request Compression

LLM

Compresses message content and replayed tool results in Model Proxy request bodies before they reach the upstream provider, reducing billed tokens

OAuth 2.0 Protected Resource Metadata

Security

Serves OAuth 2.0 Protected Resource Metadata at the well-known endpoint

OAuth 2.0 Token Introspection

Security

Allows access only to authorized client applications

OpenID Connect OAuth 2.0 Access Token Enforcement

Security

Allows access only to authorized client applications

Rate Limiting

Quality of Service

Monitors access to an API by defining the maximum number of requests processed within a period of time

Rate Limiting: SLA-based

Quality of Service

Monitors access to an API by defining the maximum number of requests processed within a timespan, based on SLAs

Regex Prompt Guard

LLM

Blocks LLM requests that match deny-list regex patterns

Response Idle Timeout

Quality of Service

Set a maximum duration Omni Gateway waits for a response from an upstream service

Schema Validation

Security

Validates incoming traffic against a supplied OAS3 schema

SOAP Schema Validation

Security

Validates incoming traffic against a specified WSDL schema

Spike Control

Quality of Service

Regulates API traffic

SSE Logging

SSE

Logs every SSE event while streaming

Stream Idle Timeout

Quality of Service

Set a maximum duration a stream can remain idle without receiving a request or response

Tracing

Troubleshooting

Configure OpenTelemetry distributed tracing for an API

Traffic Management for Multiple Upstream Services

Quality of Service

Manages API instance traffic to multiple upstream services from a single consumer endpoint

Traffic Management for Multiple Upstream Services (Weighted)

Quality of Service

Manages API instance traffic to multiple upstream services from a single consumer endpoint, using weighted percentages

Transport Layer Security (TLS) - Inbound

Security

Enables authentication between a client and the API proxy

WebSocket Connection Limit

Quality of Service

Limits the number of simultaneous WebSocket connections that each API instance allows

XML Threat Protection

Security

Protects against malicious XML in API requests

## [](#see-also)See Also - [Policy Availability by Gateway](https://docs.mulesoft.com/gateway-home/#policy-availability-by-gateway)