KortixDocs
Concepts

Connections

Let the agent call your external tools, brokered server-side per project.

A connection (connector) lets a project's agent call an external tool or service — Slack, Gmail, a database, any HTTP/GraphQL API. Connections are per-project, and the agent can only use what you connect.

  • Declared as [[connectors]] in kortix.toml — provider is one of Pipedream, MCP, OpenAPI, GraphQL, or HTTP. The definition lives in git; the credentials live in the platform, never in the repo.
  • Credentials are shared or per-user. A connection can use one shared credential, or each member connects their own account.
  • Per-call policies — each tool can be set to run, require approval, or be blocked.
  • Set up in the dashboard — the project's Connectors page offers Pipedream one-click connect plus a custom path for OpenAPI/GraphQL/MCP/HTTP. See Connecting your tools.

Under the hood

Every session gets a kortix-executor MCP server and a scoped Executor token. The agent discovers tools through it (connectorsdiscoverdescribecall); each call is brokered by the Kortix API, which resolves the credential server-side, enforces sharing and policies, runs it, and audits it. The agent never holds third-party credentials. Pipedream's one-click connect requires Pipedream API keys to be configured on the platform.

Connections | Kortix Docs | Kortix