As AI agents become more sophisticated, the need for secure, structured communication between agents and systems has never been more important. Enter Model Context Protocol (MCP) – a new approach that’s redefining how AI agents interact with external systems while maintaining strict security boundaries.

While traditional APIs have served machine-to-machine communication well, they now fall short when it comes to agentic AI interactions. MCP fills this gap by providing a specialized protocol designed specifically for AI agents, complete with built-in security features that help prevent data spillage and reduce hallucinations.

What is Model Context Protocol (MCP)?

Model Context Protocol is a new standard for connecting AI models to external tools, data sources, and services, so they can more effectively communicate. Essentially, it functions as an API designed specifically for AI agents. Developed by Anthropic as an open source protocol in late 2024, MCP has quickly gained traction across the industry, despite being less than a year old.

Think of MCP as the evolution of how systems communicate. Where REST APIs and GraphQL handle traditional machine-to-machine interactions, MCP creates a structured pathway for agents to access system capabilities without compromising security or data integrity.

The protocol operates on a simple but powerful premise: instead of giving agents direct database access or unlimited system permissions, MCP creates a controlled interface that defines exactly what an agent can and cannot do. This approach fundamentally changes how we think about agent-system integration.

What are the Three Pillars of MCP?

MCP architecture consists of three core components that work together to create a comprehensive communication framework:

Pillar #1 Tools (The Agent’s Capabilities)

Tools represent the specific actions an agent can perform within a system. These are discrete functions that agents can call to interact with external services. Each tool has a defined scope and purpose. An agent cannot perform actions beyond its available toolset, creating natural boundaries around what’s possible during any interaction.

For healthcare applications, tools might include:

• Finding open appointment slots for rescheduling
• Booking new appointments
• Processing referrals
• Triaging patients to appropriate care levels
• Canceling or confirming existing appointments
• Escalating complex cases to human staff

Pillar #2 Resources: Static Information Repository

Resources encompass all the static information an agent needs to function effectively. This includes structured data like databases, documents, and reference materials that don’t change frequently. Resources provide agents with the contextual knowledge they need, without requiring real-time database queries for every piece of static information.

Common examples of resources include:

• Provider directories with doctor locations, specialties, and working hours
• Facility information like building locations and available services
• Parking and navigation details
• FAQ databases
• Policy documents and care recommendations

Pillar #3 Prompts: Contextual Communication Guidelines

Tied to the available resources and tools, prompts define how agents should respond in specific situations. They’re pre-written response templates that ensure consistent, appropriate communication based on the context of the interaction.

For instance, when an appointment scheduling tool returns no available slots, the associated prompt might guide the agent to say: “I couldn’t find any available appointments for your preferred time. Would you like to adjust your date range?”

This component ensures that agents maintain professional, helpful communication even when systems return unexpected results or errors.

These three pillars of MCP architecture (tools, resources, and prompts) create a comprehensive framework that addresses the key challenges of agent deployment: capability definition, information access, and response consistency. This structured approach not only enhances security but also improves the reliability and predictability of agent interactions.

Security Through Structure: How MCP Protects Data

One of MCP’s most significant advantages is its approach to security, which operates on multiple levels to protect sensitive information and prevent unauthorized access.

Hallucination Mitigation

Traditional agent implementations often gave AI systems direct database access, creating opportunities for hallucinations when agents generated plausible-sounding but incorrect information. MCP addresses this by normalizing data exchange and reducing ambiguity.

For example, when an MCP server receives a specific date from an agent, like “September 26, 2025,” (rather than sharing the numbers in a different order, such as 26-09-25), there’s little to no room for misinterpretation. The MCP can translate the data into its own specification for the agent, providing structured, verified responses, rather than constructing replies from raw database queries. This structured approach significantly reduces the likelihood of agents fabricating information (hallucinations).

The protocol also limits agents to only the information explicitly provided by the tools they call. If a tool is designed to verify patient appointments, it returns only verification status – nothing more. This prevents agents from accessing or inferring additional data beyond their designated scope.

Data Containment and Access Control

MCP creates strict boundaries around data access through its tool-based architecture. Agents can only access information through predefined tools, and each tool has specific parameters and return values.

This approach prevents data spillage in several ways:

• Limited scope: Tools only return the specific information they’re designed to provide
• No direct database access: Agents cannot make arbitrary queries or access raw data
• Structured responses: All information comes through controlled, formatted channels

If someone attempts to trick an agent into providing unauthorized information – like requesting a patient’s social security number – the agent simply has no tool capable of retrieving that data. The response would be: “I don’t have the capability to access that information. Would you like me to forward you to a human to answer that?”

Preventing Jailbreaking Attempts

Jailbreaking occurs when users try to manipulate agents into providing information or performing actions they shouldn’t. Classic examples include convincing an AI that harmful requests are actually for fictional purposes or creative projects.

MCP’s architecture makes jailbreaking significantly more difficult because agents physically cannot access information beyond their tool capabilities. Even if an agent were somehow convinced to attempt unauthorized data access, the underlying system simply doesn’t provide that pathway.

For healthcare applications, this is particularly crucial. Even if an agent hallucinates and generates a fake social security number or medical record number, that information isn’t sourced from actual patient data – it’s purely fabricated and can be detected and flagged by monitoring systems, like Judge LLMs.

The Future of Agent-System Communication

Model Context Protocol represents a fundamental shift in how we architect AI agent interactions. By providing structured, secure communication channels, MCP enables more sophisticated agent capabilities while maintaining strict security boundaries.

Many tech companies, including Artera, are already implementing MCP servers to integrate agent interactions with their platforms. This growing adoption suggests that MCP is on track to become a standard protocol across the tech industry, similar to how REST APIs became ubiquitous for web services.

While MCP shows great promise, we’re prioritizing security as the protocol continues to mature. For example, our MCP server operates within a controlled environment, accessible only to authorized agents, rather than being publicly available on the internet. 

As the protocol matures, we anticipate enhanced security standards, broader industry adoption, and more sophisticated toolsets that enable agents to handle increasingly complex workflows. I believe that organizations – such as Artera – which adopt MCP early are well-positioned to leverage these advances in agentic AI while maintaining robust security practices.

Today’s healthcare market is saturated with AI agent solutions, making vendor evaluation difficult for healthcare providers amidst similar claims and significant costs.

To simplify your evaluation, we’ve identified the top five factors that distinguish Artera’s AI agents today. Whether you’re new to AI agents or well into your research for a partner, we hope this distillation proves valuable.

Artera’s blog posts and press releases are for informational purposes only and are not legal advice. Artera assumes no responsibility for the accuracy, completeness, or timeliness of blogs and non-legally required press releases. Claims for damages arising from decisions based on this release are expressly disclaimed, to the extent permitted by law.

The post Model Context Protocol Explained: The Key to Agentic Healthcare appeared first on Artera.

I love the energy and challenge of working with startups, which is why I feel so fortunate to join Artera. While I’ve recently been working at a large business following an acquisition, my background includes helping to build three consecutive startups to successful exits. I recently felt the pull to get back into the exciting startup space, and I’m thrilled to answer that call by joining Artera. 

As I jump back into the startup world for the fourth time, I wanted to reflect on what I’ve learned about building a diverse, empowered engineering function. What kind of empowerment models need to be created in the organization in order to not just scale the software, but scale the engineering function itself?

Of course, every engineering leader is going to say they want to partner with the organization to create a world-class engineering team. But I’ve found that it’s important to have a clear vision for what that really means in a hyper-growth environment. 

Empowered Organization

Everyone must feel like they have ownership over the decisions that are being made. They also need to be able to feel free to try things without fear of failure – this is essential for innovation. 

When teams have this kind of agency, it creates a pride and sense of true ownership that promotes enthusiasm and excitement in the team. True agency is highly motivating, and motivated teams simply do better work!

Engineering Excellence 

As we scale the software and the engineering organization, we also need to define our bar for excellence moving forward, and hold ourselves accountable. That includes elevating our practices and how we get things done, not just the technology and quality of the end product. 

Outstanding Culture

The last and perhaps most important piece is culture, which is the glue that holds it all together. Culture is what keeps us moving forward even when our work is challenging. Every company will have its ups and downs, but through it all we must remain dedicated to sustaining a truly outstanding culture in order to meet our ambitious goals as a team. It’s an implied contract between all the members of a team, and when done right, great things can happen.

I’m excited to bring what I’ve learned about building a great engineering team to Artera, a fast-growing company with ambitious tech and innovation goals. I’m confident that we will play a key role in engineering solutions that help power the rise of the patient and make healthcare #1 in customer service. 

The post Leadership Voices: Ashu Agte on How to Build a World-Class Engineering Function appeared first on Artera.

Here, we get to know him a little better with 10 quick questions on his background and plans for the future: 

What is your professional background? 

I was born in India, and came to the U.S. for college. If you were to summarize my 20-plus years of experience, you could simply say “three startups and three exits.” The last startup I was at was acquired by Autodesk around three years ago. 

After helping integrate the company, I got a chance to lead their flagship product, AutoCAD. I felt like it was a super cool opportunity to lead a large distributed multi-platform engineering organization, so that’s what I’ve been doing for the past two years. 

What made you want to explore new opportunities?

Earlier this year, as I approached my three-year anniversary at Autodesk, I started to feel a pull to go back to the startup world. At the same time, I was introduced to Artera’s founder and CEO, Guillaume de Zwirek, and the rest is history!

What made you decide to join Artera?

Since this was my fourth time getting into the startup world, I was very deliberate and very selective. There were basically three boxes I wanted to check.

First, I wanted to make a positive impact on the world and improve people’s lives. 

Second, I really wanted to work with fantastic people who were supportive, collaborative, and set a high bar that would help me elevate my own way of operating. Finally, I wanted the opportunity to experience the period between Series C and IPO, since I hadn’t yet had that experience at previous startups. 

Artera overwhelmingly exceeded my expectations in all three areas, and it was a no-brainer after meeting everyone and learning more about the mission to make healthcare number one in customer service. 

How has the ramp-up period been so far? 

Before officially joining full-time, I started as an advisor so I could get involved right away. While I’m not fully ramped up yet, everyone has been really great in helping me get onboarded. Everyone is really collaborative, and I’m excited to hit the ground running – particularly since Artera has such ambitious goals for technological innovation in Healthcare. 

What’s your first impression of Artera now that you’re getting up to speed?

I believe we are at an inflection point in terms of scaling. By scaling I don’t only mean software, but the entire engineering team. We need to set the stage for a team of, say, 300 engineers, and lay the foundation for what our culture will be. What will be our best practices? What is the bar for engineering excellence, and what processes will get us there?

What’s your vision for scaling the engineering function?

Like any engineering leader, I want to partner with everybody to build a world-class engineering organization. There’s a lot that goes into successfully scaling an engineering function, and I plan to write a blog soon on my philosophy and approach when it comes to achieving excellence in a growing engineering team. 

Getting more personal, can you tell us about your family?

We are a family of three. I have one daughter, who is 11 years old, and my wife of 16 years, who is also a software engineer – so we are kind of a techie family. We live in the Bay Area. 

Are there any tv shows or books that have captured your attention recently?

The last show I really liked is called The Witcher, and maybe I liked it a little more than others because I’ve read the books it is based on. As for books, in keeping with the sci-fi/fantasy theme, I recently enjoyed a book called Dark Matter by Blake Crouch. 

What are your favorite mobile apps?

During the week, it’s Slack. On the weekends, however, I prefer YouTube. 

What are your proudest moments, both personally and professionally?

My proudest professional moment would have to be the state of the engineering organization that I built at my last startup – I’m super proud that we were able to get to that stage. Personally, my proudest moment was holding my newborn daughter in the hospital for the first time!

The post Leadership Voices: Q&A with Artera Health Senior Vice President of Engineering Ashu Agte appeared first on Artera.