---
schema_version: "1"
id: 31029802bfcfea0869fe547c0b2d36bb9011758dc9f7cbeb0dbed99e760b59b5
title: Securing Agent Interactions with Omni Gateway
collection: mulesoft
version: current
locale: en-us
portal_url: https://docs.salesforce.com/mulesoft/current/en-us/gateway/1.13/agent-secure.md
canonical_url: https://docs.mulesoft.com/gateway/1.13/agent-secure
source_site: docs.mulesoft.com
content_type: documentation
content_hash: ad9a7bb64c96f116e56fd7d7b5558ab48fae695c8db8ee770452f3fdc9dac6db
description: MuleSoft Documentation Site
release: "1.13"
latest: false
---
---
product: Omni Gateway
version: 1.13
---

# Securing Agent Interactions with Omni Gateway

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

Omni Gateway supports both the Model Context Protocol (MCP) and the Agent2Agent (A2A) Protocol,
enabling you to protect your agents, brokers, LLM, and MCP servers. Omni Gateway provides
centralized oversight, agent visibility, logging, and valuable insights, ensuring effective
governance and security for your agent-based architecture. Omni Gateway secures agent interactions
by enforcing policies across agent connections and by monitoring agent activities for enhanced
visibility.

## Omni Gateway A2A Support

A2A is an open standard that defines how agents interact with each other, enabling interoperability
for agents built by different teams, using different technologies and hosted by different
organizations.

Omni Gateway protects agent A2A interactions by requiring appropriate authentication and
authorization for agent requests, rewriting Agent Card URLs, logging or blocking sensitive
information in messages, and logging Server-Sent Events (SSE) content for compliance audits. You can
enhance agent requests by modifying incoming prompts with additional context to improve server-agent
execution.

## Omni Gateway MCP Support

MCP is an open protocol that defines how agents interact with tools or external context, enabling
agents to connect to the data and tools they need.

Omni Gateway secures MCP connections by restricting MCP endpoint access to authorized agents only
and by simplifying governance through centralized visibility and control over all interactions.

## Securing Agent Interactions with Policies

Omni Gateway includes A2A and MCP specific policies that provide enhanced security and control over
agent interactions. Omni Gateway A2A policies enable you to protect agent endpoints by rewriting
Agent Card URLs, logging or blocking sensitive information in messages, modifying prompt behavior,
and logging Server-Sent Events (SSE) content for compliance audits. Omni Gateway MCP policies enable
you to use attribute-based access control to manage access to MCP servers.

Omni Gateway MCP and A2A server instances also support Omni Gateway’s other policies. For example,
use policies such as [Rate Limiting Policy](https://docs.mulesoft.com/gateway/1.13/policies-included-rate-limiting) or
[Spike Control Policy](https://docs.mulesoft.com/gateway/1.13/policies-included-spike-control) to manage the number of requests to MCP and
A2A servers or use the [Message Logging Policy](https://docs.mulesoft.com/gateway/1.13/policies-included-message-logging) to monitor agent
interactions.

See [Omni Gateway Agent Policies](https://docs.mulesoft.com/gateway/1.13/agent-policies) to learn about included A2A and MCP policies.

## See Also

- [Introducing Governance for Agent Interactions With Support for A2A & MCP](https://blogs.mulesoft.com/news/mulesoft-governance-for-agent-interactions/)

- [A2A Protocol spec](https://a2a-protocol.org/latest/topics/what-is-a2a/)

- [MCP Protocol spec](https://modelcontextprotocol.io/introduction)

- [Streaming & Asynchronous Operations in A2A](https://a2a-protocol.org/latest/topics/streaming-and-async/)