Table of Content
Subscribe to our Newsletter
Get the latest from our team delivered to your inbox
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Ready to get started?
Try It FreeTable of Content
- An updated Salesforce integration parses SOQL and extracts Salesforce data relationships, field-level lineage, and business logic into the Foundational Data Graph, connecting CRM context to the rest of the enterprise.
- A new MCP integration gives Agentforce agents direct access to Foundational lineage, provenance, ownership, usage, sensitivity, code context, and governance guardrails at the point of work.
- A Slackbot integration is coming soon, extending the same governed enterprise context into Slack.
SAN FRANCISCO, September 16, 2026. Foundational, the data and AI governance company, today announced at Dreamforce 2026 a new set of integrations for Salesforce and Agentforce. The integrations give enterprise agents deeper, verified context about the data they use and the systems they act on.
Salesforce holds some of the most important business data in the enterprise. The meaning and history behind that data rarely starts or ends inside the CRM. Customer, product, finance, risk, and operational fields are created in application databases, moved through pipelines and warehouses, enriched by custom code, then synchronized into Salesforce. The same data continues downstream into analytics, reporting, and other operational systems. Even in the CRM itself, dependencies, hidden logic, custom code and jobs, are all often very much hidden.
Foundational connects all of those pieces into a single data knowledge graph. The updated Salesforce integration reads Salesforce code, metadata, and report logic, parses any custom Salesforce Object Query Language (SOQL), and extracts the relationships and query logic that are otherwise difficult to discover through the Salesforce interface. Foundational maps that Salesforce context into the Foundational Data Graph, where it resolves against upstream and downstream systems across the enterprise.
With the new Agentforce MCP integration, that graph becomes available to Agentforce agents at runtime. An agent can establish where a field came from, how it was transformed, and what code defines it. It can check where else the field is used, whether it holds sensitive data, and what breaks if it changes, before an agent or human takes action.
From Salesforce Data to Enterprise Context
The combined integration creates a two-way context path between Salesforce and the broader enterprise. Foundational first discovers the data structures and logic inside Salesforce, including SOQL, objects, fields, and reports. It then resolves those assets against the same data as it appears in databases, warehouses, pipelines, BI tools, application code, and legacy systems. Through MCP, Agentforce calls back into that connected graph when it needs context for a question, decision, or action.
This matters for enterprise Agentforce deployments where a CRM field alone is insufficient. A renewal-risk value, account segment, eligibility flag, or customer metric is often calculated outside Salesforce and loaded into the platform later. Foundational gives an agent the ability to trace that value to its origin and understand the dependencies around it.
Foundational's code analysis engine covers Java, Python, PySpark, C#, C++, COBOL, ETL tools such as Informatica, SQL dialects, and many more systems and languages. It also finds any SOQL embedded in the enterprise applications that read and write Salesforce from outside the org, including integration services, batch jobs, and internal tools. A CRM field can be traced back to the mainframe record, billing system, or warehouse table that determines its value, and forward to every dashboard, model, and agent that consumes it.
The analysis requires no access to the underlying data. Foundational reads source code and system metadata only, and customer records stay inside the customer's own perimeter. Full coverage is documented in Supported languages and platforms.
What Agentforce Can Use Through Foundational MCP
Salesforce supports third-party Model Context Protocol (MCP) servers in Agentforce. Foundational uses that interface to expose enterprise data context and governance capabilities as tools Agentforce calls inside its workflows.
An Agentforce agent calls Foundational to:
- Trace the source of a Salesforce field before relying on it.
- Identify the systems and reports that depend on a proposed change.
- Locate the code that defines a metric.
- Understand how sensitive data has propagated.
- Retrieve ownership and usage context before routing work to the right team.
The same interface supplies policy and lineage context when an agent prepares an answer or takes an action that crosses systems.
Because Foundational builds lineage from source code and system metadata, the context reflects the organization's actual implementation instead of a manually maintained description of how data is supposed to move. Agentforce becomes more useful for complex enterprise workflows, and teams avoid recreating cross-system context for every agent.
The context also produces an audit trail. When a compliance team asks what data an agent used, where it originated, and under what authority it acted, the answer derives from code.
Setup instructions are available at Connect Foundational MCP to Agentforce.
"Agentforce becomes most useful when it understands where a field came from, what code created it, what depends on it, and what rules apply before an agent acts," said Alon Nafta, CEO of Foundational. "Salesforce sits at the center of how companies run sales, service, and customer operations. The data behind those workflows spans many systems. We make that entire chain available to Agentforce as verified context, without asking teams to rebuild it manually."
Coming Soon: Foundational Context in Slackbot
Foundational is developing a Slackbot integration that brings the same enterprise data graph and governance context into Slack. Employees will ask questions about data, lineage, ownership, impact, and governance from the place where teams already collaborate, using the same Foundational context available to Agentforce.
Together, the Salesforce connector, the Agentforce MCP integration, and the upcoming Slackbot integration make enterprise data context available where work happens: inside Salesforce, inside agents, and inside team conversations.
Resources and Links
- Salesforce Agentforce
- Connect Foundational MCP to Agentforce
- How to set up the Salesforce connector
- Use Foundational MCP with your AI tools
- Supported languages and platforms
- Foundational Help Center
About Foundational
Foundational is a next-generation data and AI governance platform that analyzes source code and metadata to map how data is created, transformed, and used across the enterprise. Foundational builds complete source-to-target, cross-platform lineage across application code, databases, data platforms, transformation pipelines, BI tools, legacy systems, and AI workloads. The platform helps organizations automate governance and compliance, track sensitive data, understand change impact before deployment, support migrations and modernization, and give enterprise agents verified context through the Foundational Data Graph. Foundational works with some of the world's biggest enterprises and F500 companies. Learn more at foundational.io.
Media Contact
code snippet <goes here>
<style>.horizontal-trigger {height: calc(100% - 100vh);}</style>
<script src="https://cdnjs.cloudflare.com/ajax/libs/gsap/3.8.0/gsap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/gsap/3.8.0/ScrollTrigger.min.js"></script>
<script>
// © Code by T.RICKS, https://www.timothyricks.com/
// Copyright 2021, T.RICKS, All rights reserved.
// You have the license to use this code in your projects but not to redistribute it to others
gsap.registerPlugin(ScrollTrigger);
let horizontalItem = $(".horizontal-item");
let horizontalSection = $(".horizontal-section");
let moveDistance;
function calculateScroll() {
// Desktop
let itemsInView = 3;
let scrollSpeed = 1.2; if (window.matchMedia("(max-width: 479px)").matches) {
// Mobile Portrait
itemsInView = 1;
scrollSpeed = 1.2;
} else if (window.matchMedia("(max-width: 767px)").matches) {
// Mobile Landscape
itemsInView = 1;
scrollSpeed = 1.2;
} else if (window.matchMedia("(max-width: 991px)").matches) {
// Tablet
itemsInView = 2;
scrollSpeed = 1.2;
}
let moveAmount = horizontalItem.length - itemsInView;
let minHeight =
scrollSpeed * horizontalItem.outerWidth() * horizontalItem.length;
if (moveAmount <= 0) {
moveAmount = 0;
minHeight = 0;
// horizontalSection.css('height', '100vh');
} else {
horizontalSection.css("height", "200vh");
}
moveDistance = horizontalItem.outerWidth() * moveAmount;
horizontalSection.css("min-height", minHeight + "px");
}
calculateScroll();
window.onresize = function () {
calculateScroll();
};let tl = gsap.timeline({
scrollTrigger: {
trigger: ".horizontal-trigger",
// trigger element - viewport
start: "top top",
end: "bottom top",
invalidateOnRefresh: true,
scrub: 1
}
});
tl.to(".horizontal-section .list", {
x: () => -moveDistance,
duration: 1
});
</script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/gsap/3.8.0/gsap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/gsap/3.8.0/ScrollTrigger.min.js"></script>
<script>
// © Code by T.RICKS, https://www.timothyricks.com/
// Copyright 2021, T.RICKS, All rights reserved.
// You have the license to use this code in your projects but not to redistribute it to others
gsap.registerPlugin(ScrollTrigger);
let horizontalItem = $(".horizontal-item");
let horizontalSection = $(".horizontal-section");
let moveDistance;
function calculateScroll() {
// Desktop
let itemsInView = 3;
let scrollSpeed = 1.2; if (window.matchMedia("(max-width: 479px)").matches) {
// Mobile Portrait
itemsInView = 1;
scrollSpeed = 1.2;
} else if (window.matchMedia("(max-width: 767px)").matches) {
// Mobile Landscape
itemsInView = 1;
scrollSpeed = 1.2;
} else if (window.matchMedia("(max-width: 991px)").matches) {
// Tablet
itemsInView = 2;
scrollSpeed = 1.2;
}
let moveAmount = horizontalItem.length - itemsInView;
let minHeight =
scrollSpeed * horizontalItem.outerWidth() * horizontalItem.length;
if (moveAmount <= 0) {
moveAmount = 0;
minHeight = 0;
// horizontalSection.css('height', '100vh');
} else {
horizontalSection.css("height", "200vh");
}
moveDistance = horizontalItem.outerWidth() * moveAmount;
horizontalSection.css("min-height", minHeight + "px");
}
calculateScroll();
window.onresize = function () {
calculateScroll();
};let tl = gsap.timeline({
scrollTrigger: {
trigger: ".horizontal-trigger",
// trigger element - viewport
start: "top top",
end: "bottom top",
invalidateOnRefresh: true,
scrub: 1
}
});
tl.to(".horizontal-section .list", {
x: () => -moveDistance,
duration: 1
});
</script>
See Foundational in action
Book a demo to see how Foundational grounds enterprise agents in verified data lineage.
See Foundational in action
Book a demo to see how Foundational grounds enterprise agents in verified data lineage.
See Foundational in action
Book a demo to see how Foundational grounds enterprise agents in verified data lineage.
Ready to get started?
Try It Free
