Kin

Connects an agent to a unified integration layer so it can call tools across apps like Gmail, Google Drive, Slack, and GitHub using scoped, server-resolved credentials the agent never sees. Per-integration permission modes and approval gates intercept reads, writes, and destructive actions, letting users review or block sensitive operations before they execute.

Connects a user's existing LinkedIn, WhatsApp, Instagram, Telegram, email and calendar accounts to any MCP-compatible agent so it can search, read and act on them without browser automation, including outreach, messaging, inbox triage and event management. It provides 170+ intent-named tools with OAuth 2.1 authentication, per-provider pacing, and approval prompts before sends, posts or deletions.

Enables MCP clients to connect once to self-hosted, user-owned upstream accounts and then discover and invoke granted tools through a single authenticated endpoint. Each client receives its own key with deny-by-default tool grants, while sensitive calls require durable human approval and credentials stay encrypted and never forwarded upstream.

Enables AI agents to act on live business objects under enforceable per-call identity, per-tool grants, and mandatory human approval for irreversible actions, with connectors isolated from core logic.