How is this different from connecting Salesforce MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Salesforce MCP API changes?

We track the Salesforce MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Salesforce tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Salesforce?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Salesforce MCP server myself?

No. TrustGate connects to the Salesforce MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Salesforce directly.

Connect Salesforce MCP to your AI agents, securely.

Q: Is Salesforce MCP secure?

The server itself exposes 11 tools, and some of them can write to your Salesforce account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Salesforce.

One secured endpoint for every Salesforce call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Salesforce MCP now

What your agents can ask once Salesforce MCP is connected.

“Show me all open opportunities over 500K grouped by owner”
“Find every contact associated with Acme Corp”
“Which fields are required to create a Case?”

“Update the stage on this opportunity to Closed Won”
“What were the cases opened in the last 7 days?”
“Show the opportunities I was looking at recently”

Select the tools your AI agents can call

11 tools from the Salesforce MCP schema.

Showing 11 tools

getObjectSchemareadReturns Salesforce schema information: a compact index of all queryable objects, or full field detail for one object.
soqlQueryreadExecutes a SOQL query to retrieve Salesforce records, with relationship traversal and subqueries.
findreadExecutes a text search across multiple Salesforce objects simultaneously.
getUserInforeadReturns the authenticated user's identity and context: ID, name, email, role, profile, manager, and timezone.
listRecentSobjectRecordsreadReturns records of a specific type that the user recently viewed or modified.
getRelatedRecordsreadRetrieves child records related to a parent record by traversing relationships.
createSobjectRecordwriteCreates a new Salesforce record.
updateSobjectRecordwriteUpdates an existing record by ID. Only the fields supplied are changed.
updateRelatedRecordwriteUpdates a parent record by traversing a child-to-parent relationship from a child record.
deleteSobjectRecordhigh riskPermanently deletes a record by ID. Deleted records go to the Recycle Bin for up to 15 days.
deleteRelatedRecordhigh riskDeletes a parent record by traversing a child-to-parent relationship. Deleting a master record also deletes its detail records.

What Salesforce MCP exposes

Salesforce MCP groups its 11 tools into 3 categories, each with a suggested starting policy.

Category	Covers	Access	Suggested policy
Schema	Object index and field-level schema with admin guidance	Read	Allow schema discovery
Records	SOQL queries, text search, related records, create, update and delete	Read / Write	Require approval for deletes; rely on field-level security
Users	Authenticated user identity, role, profile and timezone	Read	Limit to the connected user