Exposing AgentKit via MCP

Scalekit lets you configure MCP endpoints that manage authentication, create personalized access URLs for users, and define which AgentKit tools are accessible. You can also bundle several toolkits (e.g., Gmail + Google Calendar) within a single endpoint.

Model Context Protocol (MCP) is an open-source standard that enables AI systems to interface with external tools and data sources. Where the integrating-agentkit skill uses the SDK directly, this workflow configures AgentKit to expose tools over the MCP protocol so any compliant client — LangChain, Claude Desktop, MCP Inspector — can consume them.

Note: AgentKit MCP servers only support Streamable HTTP transport.

Guardrails

• MUST use Streamable HTTP transport — stdio and SSE are not supported by AgentKit MCP servers.
• MUST use the dashboard Connection Name verbatim as the connection_name in code — they must match exactly.
• MUST NOT expose connector tools without per-user authenticated MCP URLs; each user authorizes their own connected account.

What you'll build

1. A Scalekit MCP server that fetches the user's latest email and creates a reminder calendar event
2. A LangGraph agent that connects to this server via langchain-mcp-adapters and invokes the tools