MCPHub Docs

Log Schema

Fields captured for every tool call in the audit log.

Log Schema

Every tool call record in the tool_calls table has these fields:

Fields

FieldTypeDescription
idUUIDUnique identifier for this tool call
workspace_idUUIDWorkspace this call belongs to
server_idUUIDThe MCP server that handled the call
tool_namestringName of the tool invoked (e.g. read_file)
caller_agentstringIdentifier of the calling agent/script. Set to "mcphub-playground" for playground invocations
statusstring"success" or "error"
error_messagestring | nullError detail if status is "error"
duration_msint | nullWall-clock duration of the tool call in milliseconds
input_tokensint | nullInput token count (if provided by caller)
output_tokensint | nullOutput token count (if provided by caller)
output_size_bytesint | nullResponse payload size in bytes
created_attimestampWhen the tool call was recorded (UTC)

Token fields

input_tokens and output_tokens are optional — they're only populated when:

  • The calling agent provides them in a direct ingestion request
  • The proxy can extract them from the MCP response metadata

These fields power the cost estimator in Analytics.

caller_agent values

Common values you'll see:

ValueSource
"mcphub-playground"Tool Playground invocations
"claude-desktop"Claude Desktop via proxy
"ci-pipeline"Your CI scripts (set this yourself in direct ingestion)
nullNot provided

Set caller_agent in direct ingestion requests to make the audit log more useful for attribution.

On this page