Connectors and agents

Connect outside apps with the Model Context Protocol, control what they may do, and run agents that work under spend caps and approvals.

Connected apps (MCP) overviewConnect remote Model Context Protocol servers so Keplar and its agents can use outside tools, with per-tool permissions, approvals and plan limits.
Add a connectionConnect an MCP server step by step, test it with a handshake, enable only the tools you want, and the address and credential rules that apply.
Connect with OAuth (Beta)How OAuth sign-in for remote MCP servers works in Keplar, what it stores, what it refuses, and why it is labeled Beta.
Tool permissions and approvalsRead versus write tools, grants, auto-run rules, approval cards, schema-change locks and how scheduled runs always ask first.
Agents overviewWhat a Keplar agent is, which plans include agents, the built-in agents, how to run, pause and stop them, and what they cost.
Agent guardrailsSpend caps, approval gates, auto-send rules, kill switches and the audit log: how Keplar limits what an agent can do and spend.
Agent schedulesHow agents run on a schedule, which triggers exist, the time zone to use when reading cron times, and why scheduled runs always wait for approval.
Business tools: forms, CRM, inbox and dashboardHow a contact form on a Create site becomes a lead, a deal and a drafted reply, and what the dashboard, CRM, inbox, orders and audit log show.