Salesforce has launched Headless Data 360 for Model Context Protocol, allowing AI agents to access more than 200 Salesforce APIs directly and handle data transformation, querying, and activation tasks that previously took days or weeks.
The service works with any AI agent—Claude, Cursor, ChatGPT, or Salesforce's Agentforce—and understands natural-language requests, automatically discovering the necessary data fields and executing the work in hours or minutes rather than months.
What happened
Salesforce announced Headless Data 360 for Model Context Protocol (MCP), exposing more than 200 APIs as programmable endpoints that AI agents can access directly. The service allows teams to query, build, transform, map, segment and activate data fields without leaving existing tools, and will include prepackaged Skills for common tasks starting in August.
Why it matters
Historically, accessing and preparing data required workers to move between tools and teams over days or weeks. Data 360 lets agents handle this work in hours or minutes by understanding natural-language requests (such as "lifetime value of all customers for electronics purchases, excluding software") and automatically discovering the necessary fields, transforms and formulas without human specification of exact field names or function calls.
What to watch
Prepackaged Skills for modeling, mapping, transforms and activation will be available later in August; custom Skills can also encapsulate common workflows. Dr. Paramjit Chopra, founder and CEO of Midwest Institute for Minimally Invasive Therapies P.C., highlighted that physician-curated ontology ensures AI responses remain trustworthy by being structured and monitored by human experts.
Ask the AI about this article →
Salesforce's expansion of Headless Data 360 builds on its April release of Headless 360, which connected any system on Salesforce APIs via MCP. The new Data 360 service goes deeper, moving beyond simple querying to enable agents to handle the full lifecycle of data work—transformation, mapping, segmentation and activation—all programmatically. The key shift is that agents no longer need humans to specify exact field names, schema details, or function calls; instead, they can understand conceptual requests in natural language and automatically discover and invoke the relevant APIs and transformations.
This addresses a historical pain point: data workers have traditionally spent days or weeks moving between tools, consulting documentation, and coordinating across teams to pull and prepare data. By exposing more than 200 APIs as direct endpoints and allowing agents to navigate them without a graphical interface, Salesforce aims to compress work that took months into hours or minutes. The addition of prepackaged Skills (launching in August) and support for custom Skills further reduces friction by eliminating the need for users to rebuild common workflows and prompts from scratch.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
As AI technology matures, the bottleneck in the industry is moving beyond semiconductor constraints like GPUs…
OpenAI has launched an Apple Messages plug-in for ChatGPT that lets users connect their Messages inbox to the…
Amazon Bedrock now supports OpenAI GPT-5.6 models (Sol, Terra, and Luna variants) across more than 25 AWS Regi…
Slack introduced Slack Code, a new feature that lets teams collaborate with AI coding agents (Claude, Devin, G…
Cisco is transforming its digital customer experience (DCX) strategy by embedding AI throughout customer journ…
Mastercard CEO Michael Miebach introduced "Agent Pay" last April, a payment framework that allows AI agents to…
