What the connector covers
We expose accounts, contacts, leads, opportunities, cases, tasks and custom objects (the __c ones). You choose exactly which ones, and for each tool whether it can only read or can also write.
Authentication
We connect using a connected app with OAuth, so every call respects the user's profile, permission sets and sharing rules. Credentials stay on the server and never reach the AI model.
What we handle that generic servers often miss
- Free-form SOQL from a model is a risk; we ship approved, parameterized queries instead.
- Field-level security must be respected per user, which is why we prefer OAuth over a single integration user.
- Large orgs have hundreds of fields per object; we curate what the model sees so answers stay accurate.
Works with your AI clients
The same server works in Claude, ChatGPT, Cursor, VS Code and agent frameworks that support MCP. Run it locally for a pilot or as a remote server for the whole team.
Questions about Salesforce and MCP
Is there an official Salesforce MCP server?
Some vendors publish their own MCP servers and they change quickly. When you send a brief we check what exists for Salesforce today and tell you honestly whether it covers your needs.
How long does a Salesforce MCP connector take?
A focused connector with up to 10 tools usually ships in 7 to 10 business days after you approve the tool list.
How much does a Salesforce MCP server cost?
A single-system connector starts at $1,900, fixed after a free written scoping. Multi-system production setups start at $5,900.
Can the AI change data in Salesforce?
Only through write tools you approve, and risky ones wait for a person to confirm. Everything is logged.