Skip to main content
Hone offers the same surface in Python and TypeScript, so the concepts you learn in one transfer directly to the other. Each SDK gives you two ways in:
  • Conversations — instrument agent turns from your application code.
  • MCP — wrap an MCP server so every call it handles is captured for you.
You can use both in the same organization. They write to the same ingestion pipeline and show up together in the dashboard.

Which one do I use

Conversations SDK

Reach for this when your agent is application code that produces a reply per turn. You control when a turn begins and ends, and you attach the user, the input, and the output.

MCP wrapper

Reach for this when your agent is an MCP server. A single wrapper call records every tool, resource, and prompt invocation without touching each handler.
Rules of thumb:
  • If you already talk to the model directly and shape the conversation, use Conversations.
  • If the model reaches your capabilities through MCP, use the MCP wrapper and get full tool-level coverage for one line.
  • If both are true (an app-level agent that also exposes MCP tools), use both. Turns and tool calls link together into one event tree.

Install

The shared shape

Both SDKs expose the same core calls. The naming follows each language’s conventions (snake_case in Python, camelCase in TypeScript), but the behavior is identical.
CallWhat it does
initConfigures the SDK with your API key and optional endpoint.
begin / endOpens an interaction for a turn and closes it with the output and success flag.
trackRecords a completed turn in one fire-and-forget call.
identifyAttaches traits to a user id.
set_property / set_propertiesAdds custom properties to the current interaction (for example model, tokens, cost).
MCP wrapperAuto-captures every tool, resource, and prompt call on an MCP server.

Full references

Python SDK

Every call with runnable examples.

TypeScript SDK

Every call with runnable examples.

MCP

Wrapping an MCP server in Python and TypeScript.