Salesforce has today expanded Headless 360 with an MCP-based architecture that lets AI agents discover and act on existing capabilities across enterprise workflows.
The move takes headless CRM beyond making Salesforce functionality available outside its interface, giving agents access to customer data, business logic, and governed actions at runtime.
CX leaders must now consider whether their customer data and governance frameworks can support reliable agent-led execution.
“Salesforce was built on the idea that customers should be able to extend the platform far beyond the interface we provide,” noted a Salesforce executive.
“Headless 360 carries that idea into the agentic era. Instead of rebuilding data, logic, and governance for every new agent, customers can activate what they have already built on Salesforce wherever work happens.”
The Limits of a Connected CRM
The original Headless proposition was built around separating CRM capabilities from the Salesforce interface, allowing data and functionality to be accessed across different environments.
Today, it has expanded to address one of the pressing limitations that becomes more evident as AI agents take on more customer-facing work.
For example, an agent may have access to Salesforce but still reaches the boundary of what has been explicitly connected or configured for it, causing it to stall and hand the task back to an employee.
Furthermore, accessing CRM capabilities is only useful if agents can work with the customer context required to make appropriate decisions and actions.
With data work often involving sourcing fields, mapping schemas, building segments, and activating information across tools and teams, processes that can take create severe delays.
For customers, these unnecessary gaps in Headless 360 can result in slower resolutions, inconsistent experiences, and interactions that lack the context needed to feel relevant or trustworthy.
Inside Salesforce’s Agent-Ready Headless Architecture
Most notably, Salesforce’s Headless 360 MCP Server is now available in open beta, improving on the earlier model by allowing agents to discover the Salesforce capability they need at runtime.
Rather than requiring developers to predefine every API or feature, agents can now discover, understand, and invoke Salesforce capabilities dynamically.
As a metadata-aware server, the MCP enables agents to inherit existing object relationships, validation rules, and automations alongside the user’s Salesforce own permissions and policies, allowing them to work within already established business logics.
Secondly, Salesforce is extending the architecture across its wider CX portfolio, giving agents access to capabilities spanning customer engagement, sales and data integration.
In service, Headless capabilities can bring dispatching, Field Service scheduling, and support workflows into external applications and other customer touchpoints.
For marketing, the Marketing Engagement MCP allows marketers to manage automation, customer journeys, and data extensions through natural language inside Slack.
Data 360’s new MCP Server also exposes roughly 200 APIs, enabling authorised agents to analyse, structure, and activate customer data without teams manually completing each step across separate tools.
As a result, this extends Data 360 into a platform where agents can also build and activate customer data.
Furthermore, Prebuilt Data 360 Skills are designed to support common workflows with general availability targeted for August 2026.
Finally, the expansion adds a broader conversational and development layer, with Slackbot’s MCP Client now connected to Slackbot with more than 20 partner applications, including Docusign, Notion, and Zoom.
From here, users can ask Slackbot to perform actions across applications while retaining existing permissions and data boundaries, enabling Agent Skills and Plugins to then package reusable rules and resources into governed, agent-readable instructions.
As of right now, more than 100 prebuilt Skills are available, giving organizations the ability to reuse verified capabilities across different workflows instead of relying on individual prompts.
Are Businesses Ready for Agents to Act?
For CX teams, the expansion enables agents to execute capabilities wherever customer and employee work takes place.
For example, a service agent can now take action across cases, scheduling, customer data, and other workflows, while external agents can access governed Salesforce capabilities without requiring separate integrations.
In fact, early customers are reportedly seeing measurable gains, with Engine cutting its time to production by 90%, while VentureCrowd reduced its development cycles by 90%.
For CX, this could reduce handoffs and screen switching across customer-facing operations, giving customer data a more active role in the experience.
Data 360 now provides the context agents need to make decisions and execute actions based on relevant customer information rather than retrieving records.
CX leaders must now assess whether their organizations are ready for agents to execute work rather than assist employees, agent handling will become critical as they become more capable.
Salesforce’s approach makes those controls part of the architecture, enabling agents to inherit the existing rules and capabilities within the organization.
In a previous conversation, Simon Harrison, Founder of Actionary, told CX Today that this shift is changing how people will interact with enterprise software.
“This is the future of applications,” he said.
“It is hands down the only way we will decide to use applications in the future.
