Choose the tools
Select the capabilities a client needs and describe how to use them.
Give AI clients access to selected business tools.
MCP Servers. Build and test a Model Context Protocol (MCP) server draft in Pascal. Choose its tools and resources, then discuss the configuration needed for external client access.
Product walkthrough. Press Space or Enter to pause or play.
MCP Servers. Tools your client can request.
Test a draft
Try the saved draft and inspect tool inputs and results before publication.
Plan external access
Confirm the hosting, authentication, and tool permissions required by your client with the Pascal team.
From business context to a useful capability.
Follow a customer-success server through the native builder. Select an account lookup, define who can use it, and test the saved draft with a specific customer name.
The Customer success server includes Find customer accounts, a customer playbook, and an account-brief prompt. The selected lookup retains its read permission; adding it to a server does not widen access.
Review workspace sign-in and limit the server to the Customer success team. The server’s audience and the permissions of each capability both apply when a request arrives.
Test Find customer accounts with Northstar as the input. The saved draft returns the illustrative account and an access decision. A successful draft test does not establish a hosted client connection.
In practice
A customer-success manager is preparing for a Northstar renewal. The team’s MCP server brings together an account lookup, the customer playbook, and a reusable briefing prompt. A compatible AI client can use those selected capabilities to prepare the conversation. Any later action still needs its own permissions and approvals.
Explore the solutionDiscuss an MCP connection.
Tell us which AI client and business tools you want to connect. We’ll discuss draft testing and the setup required for external access.