MuleSoft announces Omni Gateway

MuleSoft announces Omni Gateway, a new solution built for the agent control plane to provide a unified governance and visibility layer for enterprise AI. Manage API, MCP, LLM, and agent traffic with consistent policies across every platform, gateway and asset you already run.

–

Your AI program is probably further along than your governance is.

AI has moved from experiment to production, which means autonomous agents are operating across critical business systems right now. But the infrastructure underneath them -- the APIs, gateways, and policies -- was designed for a world where humans, and the applications they built, were the only consumers. When agents start calling those same tools at runtime, the gaps that were manageable before start to matter in ways they didn't previously. Token spend climbs faster than cost visibility, security policies don't extend cleanly to LLM interactions, and new agents go live on infrastructure the platform team never reviewed.

Building on our position as the market-leading API management platform, we're introducing MuleSoft Omni Gateway -- a new solution built for the agent control plane to provide a governance and visibility layer from a single place, wherever your APIs, MCPs, agents, and LLMs already run.

The Shift to Autonomous Agents: Autonomous agents are rapidly moving from experimentation to production, requiring direct access to enterprise systems to take action. However, companies are deploying these agents faster than they can govern them. Without proper oversight, AI initiatives stall and nearly half are abandoned before they even reach production .

The Cost of Fragmented Tools: Engineering teams originally built today’s underlying integration infrastructure—the APIs, gateways, and policy layers—exclusively for application consumption. As autonomous agents hit these same systems at scale, previously manageable blind spots immediately escalate into critical security vulnerabilities, shadow assets, and inconsistent compliance. To address these new vulnerabilities, teams reflexively add isolated controls, such as a standalone AI gateway or a custom policy layer. While this closes individual gaps, it fragments the control plane. API teams manage one set of policies, AI teams manage another, and the business loses a single, unified view of what autonomous agents are actually doing across the enterprise.

Ultimately, the enterprises getting AI to production fastest have figured out that the answer isn't more coverage, it's consistency: extending the governance disciplines that already work across the full stack rather than rebuilding from scratch for every new surface. That's the premise behind MuleSoft Omni Gateway: trusted governance is what makes it safe to go faster.

Getting AI to production safely requires governance at every layer of the stack, applied consistently whether you built the infrastructure or inherited it– complemented by tools for developers and agents to work together. No matter if a developer is working in an agent-augmented experience or whether an agent is operating autonomously, they can find and consume any API or AI asset they need, apply the right policies for their context, and ship with confidence that governance is already working underneath.

Federated Visibility: A single catalog brings consistent visibility and runtime policy enforcement across MuleSoft, Kong, Apigee, Azure and AWS gateways.

API-to-MCP conversion: Convert OpenAPI (REST) to govern MCP tools in minutes. Authentication policies inherit automatically from the source API across every protocol surface, so governance travels with the tool before it reaches an agent or enters a registry.

Centralized Token Management & LLM Routing: The gateway tracks token consumption in real time. Token limits, rate limits, and safety guardrails are enforced through the same policy layer, giving IT visibility into spend and AI teams immediate feedback on token usage per request.

End-to-End Monitoring & Auditing: Runtime enforcement generates a complete trace across every interaction in a chain: API call, tool invocation, agent delegation. Correlation IDs carry through each step, giving operations teams a single thread to pull when something goes wrong, rather than disconnected logs across systems.

Embedded Compliance & Identity Propagation: Security and compliance policies apply to agent-to-agent and agent-to-tool interactions, with identity propagation throughout. Policy definition, prompt safety, and compliance attestations are embedded at the design phase and enforced through runtime, on every gateway in scope.

For the platform team: Federation means one visibility and governance layer across a mixed gateway environment -- policies applied from one tool, consistently, regardless of which underlying gateway is handling the traffic. No parallel governance stacks, no manual reconciliation across vendors.

For the AI architect: Omni Gateway removes the custom integration work that's historically been required to make APIs accessible to agents. Now an API can become a governed, agent-ready tool in minutes.

For the FinOps and security teams: token consumption and prompt guardrails sit in a shared interface. The visibility that makes joint accountability practical is there by default rather than built separately by each team.

For the operations team: Full-chain visibility means a single place to trace any interaction: human or agent. When something fails or behaves unexpectedly, the audit trail is already in place.

--

Our vision is to make it as convenient as possible for you to govern at speed. Stay tuned for an exciting announcement later this month, where we will be unveiling a new way to work with MuleSoft, adding expanded headless functionality to manage Omni Gateway directly in Claude, Slack and Microsoft Teams).

“At AT&T, we've built our integration strategy on MuleSoft's platform — and the scale and reliability it has delivered across our API ecosystem has been a true differentiator. The launch of MuleSoft Omni Gateway represents a fundamentally new way to think about AI connectivity — one that gives enterprises like ours the control, visibility, and agility to bring intelligent agents into our operations with confidence. As we continue pushing the boundaries of what's possible in telecommunications, having Omni Gateway in our toolkit means that as AI becomes central to how we serve our customers, we have the infrastructure and the right partner to make it real.”
-Brad Ringer, AT&T, Principal System Engineer

“Enterprises are building AI agents faster than they can govern them, and that gap is becoming a material risk. MuleSoft is strongly positioned to close it: Omni Gateway provides a unified control plane that lets IT manage APIs, LLMs, and autonomous agents from a single platform, directly addressing the runaway token costs and security gaps that plague ungoverned agentic deployments. As enterprises aggressively expand their AI footprint, the ability to prevent context bloat, enforce policy guardrails, and track ROI across the business is now table stakes. MuleSoft has the integration footprint and platform depth to lead this shift. Organizations that lack this level of centralized orchestration will find themselves spending more, seeing less, and exposing more."
— Mitch Ashley, VP & Practice Lead, Software Lifecycle Engineering and AI-Native Software Engineering, Futurum Group

“The enterprises reshaping their industries aren't choosing between speed and control — they're demanding both. MuleSoft Omni Gateway was built on a simple conviction: governance isn't the brake on AI innovation, it's the engine. When every agent, every API, every integration is managed through a single, consistent control plane from day one, you don't just move faster — you move with confidence. That's the future we're building.”
- Andrew Comstock, SVP & GM, MuleSoft

The ability to get to production at speed, with confidence, is the crux of scaling AI.

Getting there means building the governance foundation early enough to stop operational risk from accumulating. When every API and MCP interaction is governed, every LLM call is accountable, every agent action is traceable, and policy applies consistently across the full stack. The friction that typically forces teams to slow down stops compounding.

That's what MuleSoft Omni Gateway is built to provide. And for MuleSoft customers, it's already here.

To learn more about the state of agentic transformation and the future of AI, download this year's Connectivity Benchmark Report and subscribe to our newsletter, Technically Speaking .