Use the Speak AI MCP server tool get_webhook_attempts to get the delivery log for
an inbound webhook: each received request with its HTTP acknowledgement status (200
= sample captured, 202 = accepted and run started, 401/403 = rejected) and the
automation run it started.
What does it do?
Get the delivery log for an inbound webhook: each received request with its HTTP
acknowledgement status (200 = sample captured, 202 = accepted and run started,
401/403 = rejected) and the automation run it started. Use get_automation_runs for
the run outcomes themselves.
Parameters
get_webhook_attempts takes 3 parameters, 1 of them required.
| Name | Type | Required | Description |
|---|---|---|---|
webhookId |
string | Yes | Unique identifier of the inbound webhook |
page |
number | No | 0-based page index |
pageSize |
number | No | Results per page |
Behaviour
The Speak AI MCP server publishes these behaviour hints for get_webhook_attempts.
- Only reads data. Does not modify your workspace.
- Does not delete or overwrite existing data.
- Repeating an identical call is safe.
- Stays inside Speak AI. Does not reach other systems.
Related
- Webhooks lists the rest of the Webhooks category.
- Tool reference lists every Speak AI MCP server tool.
- MCP server covers setup, supported clients, and what agents can do once connected.