💬Execution logs

Execution logs give you a way to inspect any MCP servers called by the LLM, including with their arguments and return values.

Execution logs are useful to understand the calls being made by your agents, as well as the type of arguments. Each execution is timestamped so you can understand execution time and optimize latency accordingly.

Execution logs work out-of-the-box across any agent, so you won't have to add specific instrumentation to your code.

Using Execution logs

Head over to Execution logs in your Toolhouse. In the left hand side column, you will see your past executions, tagged by their own call ID as generated by the agent. Click on one execution to see its details on the right hand side of the page.

What data is available for each execution

For each MCP server call, you'll see these details:

Data	Description
Call ID	The ID of the call, as passed by the LLM. This is useful to tell apart two different calls of the same server by the same agent.
Execution timestamp	The date and time of when the server was called. This is computed by Toolhouse.
Duration	The duration of the exeuction. This is determined by measuring the delta between the time Toolhouse invokes the server and the time it returns its output to Toolhouse.
Input	Input arguments as generated by the LLM.
Output	The complete return value of the call.