The Salesforce MCP server lets Claude, Cursor, ChatGPT, and AI agents read and act inside Salesforce. Here's the official setup, the real security risks, and how to deploy it with DLP-grade redaction at the MCP layer.
The Salesforce MCP server is a Model Context Protocol implementation that exposes Salesforce's API as a standardized set of tools to AI agents. Once connected, an agent like Claude can perform record query, record get, SOQL run, object list, Apex action invoke on the authenticated user's behalf — turning Salesforce's API surface into AI-actionable capabilities.
Refer to the official Salesforce MCP server documentation for the current tool list, OAuth scopes, and rate-limit behavior. The setup pattern is consistent with other MCP integrations: an OAuth client ID/secret, a custom connector in Claude (or another MCP-aware AI client), and the server starts serving tool calls.
From the user's perspective, the AI agent suddenly knows their Salesforce. From the security perspective, the AI agent now has read access — and often write access — to every record the user can touch in Salesforce.
That's the value. It's also where security teams need a control layer.
The risks fall into four categories that every healthcare, fintech, and enterprise security team should price into the deployment.
1. Every record is regulated data. Salesforce is a CRM — Accounts, Contacts, and Cases are PII by definition, and Opportunities and custom objects routinely hold financial data, SSNs, and card numbers. query_records and run_soql return all of it to the agent.
2. SOQL gives the agent database-level reach. A single run_soql call can return thousands of records across objects. There is no WHERE not_regulated = true clause — the agent gets the raw rows.
3. Custom objects hide sensitive data in plain sight. Most orgs store their most sensitive data in custom objects and custom fields. Standard Salesforce Shield rules often miss them; an MCP tool call returns them by default.
4. Attachments and Files are unfiltered. Contracts, IDs, signed forms, and exported reports stored as Salesforce Files flow to the agent as raw content — including text inside scanned images.
The traditional DLP a company already runs — at the network edge, on the file share, inside the SaaS-native rule engine — does not sit in the MCP path. The tool response goes straight from Salesforce into the AI agent's context window. That gap is where Strac Salesforce MCP DLP lives.
Strac's Salesforce MCP DLP sits between AI agents and the Salesforce MCP server. Every tool call passes through Strac's MCP-layer inspection before content reaches the AI agent's context window. Sensitive content is redacted, tokenized, or vaulted depending on policy. Non-sensitive content flows through untouched.
What this looks like in practice:
The same Strac MCP DLP layer covers Claude Cowork, Slack MCP, and other surfaces — one control plane across every place AI agents touch your regulated data.
MCP DLP protects the AI-agent surface. Strac's native Salesforce DLP protects the direct-user surface — the same Salesforce workspace, but inspected at the point where humans share, upload, send, and grant access. Most enterprises run both: native DLP for the user-driven actions, MCP DLP for the agent-driven actions. Together they cover every path regulated data can take in and out of Salesforce.
What Strac's native Salesforce DLP includes:
Deep dives and integration pages:
For the broader integration catalog — every SaaS, cloud, browser, and endpoint surface Strac covers — see strac.io/integrations.
The screenshot below shows Strac's MCP DLP redacting sensitive data from a real Claude session — patient identifiers, customer emails, and credit card numbers tokenized inline before the model received the prompt. The same inspection pattern runs on every Salesforce MCP tool call routed through Strac.
Setup is agentless and takes under 10 minutes.
.webp)
json
"mcpServers": {
"salesforce": {
"url": "https://mcp.strac.io/salesforce",
"auth": { "type": "bearer", "token": "<your-strac-token>" }
}
}
For Cursor, OpenAI Agents, custom agents — same endpoint, same auth.The same Strac Salesforce MCP DLP control produces evidence mapped to every major compliance framework.
For the broader AI-data-governance program this sits inside, see the AI Data Governance framework.
The Salesforce MCP server is a Model Context Protocol implementation that lets AI agents (Claude, Cursor, ChatGPT, Perplexity, custom agents) read and act inside Salesforce via standardized tool calls. It's how an AI assistant gets contextual access to every Account, Contact, Opportunity, Case, custom object, and attachment the authorizing user can read.
By itself, no — not without an additional DLP layer. The Salesforce MCP server honors the authorizing user's permissions but returns whatever that user can see, including PII, PHI, credentials, source code, and other regulated content. For enterprise use with regulated data, you need an MCP-layer DLP control like Strac Salesforce MCP DLP that inspects and redacts every tool response before content reaches the AI model.
Salesforce's built-in protections operate at the storage and policy layer — sensitivity labels, retention policies, native DLP rules at posting/sharing time. None of those sit in the MCP tool-call path by default. Strac is purpose-built for the MCP layer: it inspects every tool response before content reaches the AI agent's context window, with detection breadth (PII / PHI / PCI / secrets / source code / OCR-in-images) that goes well beyond most native rule engines.
Yes. Strac exposes a standard MCP endpoint, so any MCP-aware AI client routes tool calls through it with one configuration change. No SDK changes, no application code changes.
PII (SSN, driver's license, passport, address, phone, email), PHI (clinical notes, MRN co-occurrence, ICD-10 codes adjacent to identifiers, lab values), PCI (full and partial card numbers via Luhn check), credentials (API keys, AWS / GCP / Azure access keys, OAuth tokens, JWTs, SSH keys, private keys — 48+ patterns), proprietary content (M&A keywords, source code fingerprints), and custom detectors trained on your internal data classifications. Detection runs across text, files, images (OCR), and structured fields.
Under 10 minutes for the first workspace. OAuth Strac into Salesforce, paste the Strac MCP endpoint into your AI client's config, pick a policy template, done. No agents to install, no Salesforce re-permissioning, no application code changes.
Redacted content is replaced inline in the tool response. Optionally, sensitive content can be vaulted — replaced with a short-lived retrieval link that only authorized users can resolve, so the original data is retrievable for legitimate use without ever entering the AI context. Vaulted data is stored encrypted at rest in your Strac tenant; you control retention.
Yes. Strac produces a per-call audit log: timestamp, AI client identity, user, tool invoked, resource accessed, data classes detected, redactions applied, vault references, disposition. The log is queryable in the Strac console and exportable to your SIEM. This is the evidence trail SOC 2, HIPAA, PCI, and GDPR auditors will ask about for AI-agent activity in Salesforce.
The Salesforce MCP server is rapidly becoming the way AI agents read into Salesforce. That surface contains every category of regulated and proprietary data your organization has. Running Salesforce MCP in 2026 without an MCP-layer DLP control is not a question of if the first incident reaches your security team; it's when.
Strac Salesforce MCP DLP gives you the protection layer, the audit evidence, and the framework-agnostic compliance coverage so you can let your team use Salesforce with Claude, Cursor, Cowork, ChatGPT, and any future AI client without making each one a separate security exception.
If you are running — or about to run — Salesforce MCP in production, book a 30-minute demo. We'll walk through the architecture, the policy templates, and a deployment plan for your specific Salesforce workspace and AI clients.
For the broader MCP DLP control plane across every SaaS surface, see the MCP DLP pillar. For more SaaS-specific deep dives: Slack MCP, Google Workspace MCP, Gmail MCP, Google Drive MCP, Microsoft 365 MCP, Notion MCP, Jira MCP.
.avif){kind=icon}
.gif)
