Understanding MCP security implications

Bill Doerrfeld | May 21, 2025

My talk at APISEC|CON 2025 covered agentic AI and MCP security risks and mitigations

Today I presented at APIsec University's APISEC|CON event, sharing my (limited) knowledge about MCP security implications. Since some attendees asked for them, here are my slides:

SLIDES: Understanding MCP Security Implications [PDF]

As I covered on The New Stack recently, researchers have discovered that MCP is not secure by default. It's prone to vulnerabilities such as tool poisoning, rug pulls, tool shadowing, and remote control execution (RCE).


My presentation covered the hype around agentic AI and the excitement around MCP. It then looks at these risks and suggests some mitigations.


It was very helpful for me to put this together, and I'll post the recording of the session once it's out.


 I'm looking forward to closely following autonomous AI, MCP, and related standards, and what all this means for protecting access to underlying APIs. 


Watch: Understanding MCP security risks (recording coming soon)
Knowing when to use AI coding assistants Doerrfeld InfoWorld

When should you use AI coding assistants?

By Bill Doerrfeld • May 6, 2025
AI coding assistants are a productivity dream in some cases — and a debugging nightmare in others. So, where’s the line?
How semantic caching reduces LLM API calls

How semantic caching reduces LLM API calls

By Bill Doerrfeld • May 5, 2025
Semantic caching is like typical caching, but for AI. It could eliminate a lot of redundant API calls to LLMs, reducing costs and improving performance.
Using agentic AI for business workflows

Using agentic AI for business workflows

By Bill Doerrfeld • April 30, 2025
For CIO.com, leading executives shared with me how they're actively utilizing agentic AI to enhance core business workflows.
Making developer productivity metrics actionable LeadDev DirectorPlus

Making developer productivity metrics actionable

By Bill Doerrfeld • April 25, 2025
Developer productivity metrics are useless if they're just sitting in dashboards. So, how can we use them to direct positive, real-world action?
New study reveals what really drives revenue per engineer

New study reveals what really drives revenue per engineer

By Bill Doerrfeld • April 10, 2025
What leads to a higher revenue per engineer? New benchmarking from DX reveals how areas like R&D spend, org size, and growth rate move the needle.
LLMs can now cite their sources

LLMs can now cite their sources

By Bill Doerrfeld • April 9, 2025
My latest post on The New Stack reveals how researchers pinpoint the exact sources behind chatbot responses.
Exploring alternative managed Kubernetes platforms

Exploring alternative managed Kubernetes platforms

By Bill Doerrfeld • March 31, 2025
The Kubernetes ecosystem has exploded with managed platforms tailored to multi-cloud, edge, on-prem, and regional deployments.
Bringing internal engineering gems into the light

Bringing internal engineering gems into the light

By Bill Doerrfeld • March 28, 2025
Some internal projects are too good to stay hidden. For DirectorPlus, Spotify's Pia Nilsson shares how to identify and externalize internal platforms — like they did with Backstage.
Why AI-generated code is not enough

Why AI-generated code is not enough

By Bill Doerrfeld • March 17, 2025
My latest feature for InfoWorld looks into the gaps surrounding AI-generated code and what leaders believe we need to improve the status quo.
Can LLMs accelerate requirements engineering?

Can LLMs accelerate software requirements engineering?

By Bill Doerrfeld • March 6, 2025
New research shows LLMs outperform humans in software requirements engineering, reducing weeks of work to seconds while improving completeness by 10.2%.
More Posts