Skip to main content
MCP gives agents hands on your Karzoun data. These patterns help you get reliable results without repeating yourself in every chat.
Coming soon: screenshot of an agent listing customers and applying tags via Karzoun MCP tools.
For hosted connections (Claude.ai, Manus, remote Cursor), see AI app connectors — same tools, different client config.

Ground the agent first

Add a short system or project instruction so the model knows Karzoun tools exist:
Point the agent at this docs site for operation names: tool catalog.

Pattern: Lookup before action

Example prompt: “Find customer with email alice@example.com, show their tags, then add tag VIP if missing.”

Pattern: Safe exploration

Start read-only with a tool prefix:
Or instruct: “Only use query tools for the next five messages.” Use currentUser to verify the token works and see which workspace identity the app runs as.

Pattern: Paginated lists

Agents often fetch unbounded lists and hit the 512 KB response cap. Good prompt: “List the first 5 customers created this month using page 1 and perPage 5.” Tool args example:
See pagination for pagination.totalCount and hasNextPage.

Pattern: CRM hygiene

Pattern: Webhook inspection

For integration debugging (not provider webhooks):
  1. webhooks — list subscriptions
  2. webhookDetail — inspect config
  3. webhookDeliveryLogs — see failures and HTTP status codes
Pair with the webhooks guide for tenant outbound events.

Pattern: Hosted backend agent

For server-side workers calling /mcp:
  1. Store KARZOUN_APP_TOKEN in secrets manager
  2. initialize → capture mcp-session-id
  3. tools/call in a loop with explicit tool names
  4. Log GraphQL errors from tool responses
Do not expose the session or token to end users. Details: Hosted MCP.

Anti-patterns

Custom rules in Cursor

Optional .cursor/rules/karzoun-mcp.mdc:
Last modified on August 8, 2026