Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Examples

Full working examples showing how to integrate AgentKit with popular AI frameworks and agent platforms.

Each example builds a working agent that reads a user’s Gmail inbox using Scalekit-authenticated tools.

These platforms manage the agent harness for you. Pass a Scalekit MCP URL, describe the task, and the platform handles tool discovery, execution, and session state.

These integrations give you full control. Fetch Scalekit tool schemas, wire them into your framework, and run the tool-use loop yourself.

FrameworkLanguageIntegrationNotes
LangChainPythonSDK, native adapterScalekit returns native LangChain tool objects. No schema reshaping needed.
Google ADKPythonSDK, native adapterScalekit returns native ADK tool objects. No schema reshaping needed.
AnthropicPython, Node.jsSDK, directTool schemas use input_schema, which matches Anthropic’s format exactly.
OpenAIPython, Node.jsSDK, directRename input_schema to parameters to match OpenAI’s function format.
Vercel AI SDKNode.jsSDK, tool() helperWrap tools with tool() and jsonSchema(). No manual schema conversion needed.
MastraNode.jsMCPNative MCP support via @mastra/mcp. Tool discovery is automatic.