AI employees you can reach over MCP
With Switch MCP, ChatGPT, Claude, Copilot or your own software can hand work to your Switch AI employees, and your AI employees can use other tools' MCP servers. Every result is still approved by a person.
Why MCP matters for AI employees
Most companies now use more than one AI tool. Someone lives in ChatGPT, someone in Claude, IT has rolled out Copilot, and the CRM has its own assistant. Without a shared way to connect them, each one is an island and people copy answers between them by hand.
MCP is that shared way. With Switch MCP, any MCP-ready agent or app can hand a job to one of your Switch AI employees, and your AI employees can use other tools' MCP servers. The work still lands in Teams or Slack, with the same named owner and approval step.
What to connect first
Start where people already ask for things: the assistant your team uses most. Connecting it to one Switch AI employee, say the one that prepares finance reports, is usually enough to show the value. On Managed, the Switch team sets up the first connections with you.
From MCP (any agent or app) to a first result
Connecting MCP (any agent or app) is part of setup, not a separate project. We look at how your team uses MCP (any agent or app) today and pick the job that costs the most time. A typical first candidate is "let Claude or ChatGPT ask your finance AI employee for overdue invoices" in MCP + Xero: the AI employee prepares invoice list in Teams, and the controller approves it.
The point isn't to add another AI tool; it's to move a number your business cares about. That's why Switch is custom: we set a goal, build to it and measure it with you. Start with a free test, then choose Platform or Managed.
Example jobs
Job
Works in
Produces
Approved by
Let Claude or ChatGPT ask your finance AI employee for overdue invoices
MCP + Xero
Invoice list in Teams
Controller
Trigger onboarding when a deal is won
MCP + CRM
Welcome pack draft
Account manager
Pull numbers from another tool's MCP server
MCP
Weekly report
Report owner
See what an AI employee would do for your team.
30 minutes with Switch. We map your first agents with you.
How it works with Switch
Step 1
Agree the plan
Agree the steps, owners and dates together.
Step 2
Map your needs
Understand your workflow, pain points and goals.
Step 3
See it on your work
See a working agent on your own workflow.
Step 4
Business case
Connect the value to cost, revenue and margin.
Step 5
Price and terms
Agree scope and price for one first agent.
Step 6
References
Hear from customers who have done it.
Step 7
Procurement
Clear legal, security and vendor onboarding.
Step 8
Sign and start
Sign the shared scope and book the kick-off.
Related integrations
By company size
More ai employees by tool
Questions
Which plans include Switch MCP?
Platform, Managed and Enterprise. On the free test it is available on request.
Does a person still approve the work?
Yes. Every AI employee hands its result to a named person in Teams or Slack, who approves, edits or rejects it before anything is sent or changed.
Will AI employees replace people on the team?
No. They take repeatable work off the team's plate so people spend their time on judgement, customers and decisions.
How do we get started?
Start with a free test together with a Switch team member, then choose Platform to build your own AI employees or Managed to have Switch find, build and roll them out for you.