AI Infrastructure

Secure MCP Migration with Edge Protection | Du’An Lightfoot, Akamai | TFiR

0

The new Model Context Protocol drops the legacy transport layer in favor of HTTP, which closes one set of problems and opens another. Organizations migrating MCP servers now route AI agent traffic through the same HTTP paths as their APIs, but most teams have not extended their existing security controls to cover that traffic. Rate limiting, header validation, and malicious request filtering all need to be in place before the migration completes, not after an incident.

In this interview on TFiR, Du’An Lightfoot, Sr. Developer Advocate – AI Engineering at Akamai, walks through how Akamai’s edge infrastructure already sits in front of API traffic for most enterprises, what that means for MCP server protection, and what infrastructure teams must prepare before migrating.

Guest: Du’An Lightfoot, Senior Developer Advocate for AI Engineering at Akamai
Show: The Agentic Enterprise
LinkedIn: Du’An Lightfoot
Watch the discussion on YouTube

Here is what every platform engineer and AI infrastructure team needs to know.

Technical Deep Dive

Q: How does Akamai protect MCP server traffic during a migration to the new HTTP-based protocol?

Du’An Lightfoot, Sr. Developer Advocate – AI Engineering at Akamai, explains that because Akamai already sits in front of API traffic for most enterprises running it today, that same edge position extends naturally to the new MCP protocol. Since the new MCP version uses HTTP, Akamai’s web application firewall and load balancer tools can be placed in front of MCP servers without additional onboarding. Lightfoot notes that this allows teams to monitor MCP traffic, inspect headers, identify and separate old-version traffic from new, and apply existing protections including rate limiting and malicious attack mitigation at the edge.

“Since we’re already protecting your API traffic, this new version of MCP aligns with that because it uses HTTP. We can put our web application firewall and tools in front of your MCP servers.”

Du’An Lightfoot, Sr. Developer Advocate – AI Engineering, Akamai

Q: What infrastructure preparation should teams do before migrating to the new MCP architecture?

Lightfoot outlines a pre-migration audit focused on four areas: identifying workloads connected to the MCP server, understanding the tools those workloads use, determining rate limiting requirements, and measuring token volume being sent from the MCP server. Beyond the server itself, teams need to map what applications are connected and how they will handle the different request flows the new MCP version introduces. He specifically calls out long-running tasks as a case that requires extra planning, since teams must define how they will identify and verify a task when it returns, including how the request and confirmation check are handled under the new protocol.

“If you’re handling a long-running task, you need to figure out how to identify and verify it when it comes back, including the request and the subsequent check.”

Du’An Lightfoot, Sr. Developer Advocate – AI Engineering, Akamai

Resources & Documentation

  • Akamai App and API Protector, web application firewall and API security at the edge
  • Akamai, edge platform for API traffic protection, rate limiting, and DDoS mitigation

***

👇 Click to Read Full Raw Transcript

Swapnil Bhartiya: As organizations make this transition, how can Akamai help them migrate to the new MCP architecture more securely?

Du’An Lightfoot: I mentioned when you have a web application firewall and you have a load balancer and you have these different network tools and resources within your organization, often those that are watching this and they’ve heard of Akamai and they’re familiar with Akamai, they’re probably running it in organization. So that means we’re already protecting their API traffic. So since we’re protecting your API traffic, this new version of MCP is in line with that, right? Because it’s using HTTP. So now since we’re already in front of that, we can put the web application firewall and our tools in front of your MCP servers, and then we can monitor those traffic, check the headers, help you with that mitigation or that migration from the old version to the new version, identify that traffic, and also protect you at that edge when it comes to malicious attacks or that rate limiting and everything that you’re used to when you use Akamai.

Swapnil Bhartiya: And while Akamai is there to help, for those teams who are just starting to plan their migration, what are the things that they should do at their end? What kind of homework, how they should prepare their infrastructure, their tools, their server for this migration?

Du’An Lightfoot: Yeah, I mentioned this before, but when it comes to preparing your service, identify what your workloads are, right? Identify the tools, identify the workloads, identify the rate limiting that you may need, identify how many tokens that are being sent from your MCP server. These are things that you can do to identify. But when it comes to your application, what’s actually connected to it, what’s being served, how are you going to handle the different types of flows that come through MCP, right? If you’re doing a long running task, well, now you need to figure out how do you identify and verify that task when it comes back, right? That request and that check. So these are some of the things that you have to think about when you’re moving to the new version of MCP.

How to Stop Shadow AI Data Leaks at the Endpoint | Dr. Darren Williams, BlackFog | TFiR

Previous article