Every call, logged and explained

Each search, read and run your agents make: which operation, how long it took, which account it used, and in the API’s own words why it failed.

Start for free
MCPAPI’s Logs page, with example data.
Logspaid|4,812 credits

Logs

What agents did through MCPAPI. Only argument names are kept: values and responses are never stored.

WhenToolCallStatusTime
execute_toolstripe.PostRefundsas live, approved in the chat(charge, reason)completed200412 ms
get_tool_detailsstripe.PostRefundscompleted38 ms
search_tools“refund a payment”completed521 ms
execute_toolstripe.GetChargesas live(customer, limit)completed200288 ms
search_tools“list a customer’s charges”completed498 ms
execute_toolasana.createTaskas default(name, assignee, due_on, projects)completed201655 ms
execute_toolpolar.checkouts:create(products)
This key is read-only, and polar.checkouts:create is a write.
denied12 ms
execute_toollinear.create_issue(title, teamId)completed731 ms
execute_toolstripe.PostCustomersCustomeras sandbox(customer, email)
Stripe: Invalid email address: ana@acme
error400301 ms
Approvals on record
A write that asked first shows that it was approved, and where.
The whole trail
Searches with their query, details, runs with their arguments’ names; never their values or your keys.
Why it failed
Refusals give the rule that stopped them; API errors quote the API.

Try it on your own APIs

Free with 100 credits a month. No card needed.