Editor’s note: This article was updated on May 6, 2026, with the latest information and resources.
One of the challenges of the AI revolution is simply keeping up. Technology evolves quickly: Interfaces get updated, models change in terms of performance, precision, and sometimes even tone and personality. Completely new functionality is being added to agents at a breakneck speed. For Salesforce Admins, keeping up with new concepts and terminology can definitely be a challenge, especially when new ideas are defined with acronyms or by unfamiliar technological terms.
A great example is Model Context Protocol, or MCP, a new standard designed to let agents connect with tools, services, and external applications to access data, actions and prompts. Let’s break down what that term means, how the technology works, and what it will mean for admins and their Agentforce implementations.
MCP is a protocol drafted by Anthropic and has emerged as the de facto standard for describing how an agent should access tools, data sources and systems. For Salesforce, this will allow Agentforce to easily access services like databases and enterprise tools. Currently this requires custom application development, but in the future it should surface in custom and standard Salesforce functionality.
Ever since computing adopted the client-server model with two very different things trying to talk to each other securely and consistently, the problem of how to make that connection work has existed. How do clients authenticate themselves? How do servers deliver information to the right location? How does the client know what kind of data to expect and respond to it correctly? Now take those questions and realize if someone creates a different kind of server or client, you have to ask them all over again and design an integration that handles different answers.
The Internet Age is full of novel ideas and protocols that solve these kinds of problems. Many application programming interfaces (APIs) include some kind of means of asking for answers to these questions directly, and even import them into client applications.
MCP provides a singular, agreed-upon way for an agent to ask a server about its functionality. With MCP, Agentforce has a universal connector to external data sources and tools.
Sound familiar? It should if you’ve been working with any kind of AI. Artificial intelligence will always, always, always be bad at its job if it lacks context. My classic example is the phrase “I need a ticket.” On its own, it lacks the detail needed to complete a task or generate a meaningful response, especially compared to something like “I need a plane ticket from Chicago to San Francisco for Dreamforce 2025.”
For an agent to work with an external tool, it needs to understand the context of the functionality in a way that fits into its system of topics, prompts and instructions. MCP provides a universal standard for a client to engage with an external server to receive the context needed to deliver accurate, effective results.
The working parts of MCP include:
A common way to think of MCP working with clients is adding new skills to the client. So when Agentforce Vibes needs to work against the Salesforce Platform, it takes your prompt, determines what actions are required to make that happen, contacts the MCP server (in this case hosted by Salesforce) and receives a response in the form of predictable structured data and resources.
MCP is the power behind the AgentExchange, which allows you to browse and try new skills, agents and solutions for Slack and Salesforce. These offerings extend Slack and Salesforce functionality across the enterprise ecosystem by allowing access to skills and functionality from a wide variety of partners.
For a more visual overview, check out this video:
We’re standing at the edge of the biggest shift our industry has ever seen. The Agentic Enterprise is transforming how businesses operate and how we work. Salesforce Admins aren’t observing this shift from the sidelines. You’re building it, piece by piece, every day. This is the natural evolution of a community that spans 160+ user […]
TDX 2026 returns to San Francisco and Salesforce+ on April 15–16. This year we’re introducing brand-new experiences designed to help you go deeper on the Agentforce 360 Platform and connect directly with the experts building it. TDX is where admins, developers, and architects come together to sharpen technical skills and have real conversations about what’s […]
Salesforce has launched the new Agentforce Builder, a brand-new experience for building agents powered by an enhanced version of the Atlas Reasoning Engine. For admins, this new builder represents a meaningful shift in how much control, clarity, and confidence you have when designing agent behavior. Previously, Atlas had a focus on retrieving and interpreting prompts. […]
