Agent Trail
Find who did what and when, with every tool call, model call, agent session, and setting change in one record
When an agent does something unexpected, a call is blocked, or someone asks who changed a rule, you need the record behind it. Agent Trail records every tool call, model call, and agent session that passes through Agent Authority, and every change to its settings. Each entry names who acted, what they acted on, and when.

What's recorded
Each row lists events by the name the Action filter shows.
| Group | Action | What it records |
|---|---|---|
| Tool calls | Tool Executed | A call that passed the rules and ran: the tool and the MCP server |
| Tool calls | Tool Failed | A call that was blocked or failed, and why: blocked by a rule, refused by a usage limit, or an error |
| Tool calls | Tools Searched | Each tool search and the tools it returned, but not the query |
| Tool calls | Approval Requested, Approval Granted, Approval Declined, Approval Expired | A call that needed approval, and what became of it |
| Model calls | Model Call | Each model call through the gateway, including calls a rule denied |
| Agents | Agent Connected | Each MCP session an agent opens, with the servers it could reach, was blocked from, or couldn't reach |
| Agents | Agent Created, Agent Updated, Agent Revoked, Agent Deleted | An agent added, changed, revoked, or removed |
| Agents | Agent Tagged | A tag assigned to an agent |
| MCP servers and tools | MCP Created, MCP Updated, MCP Deleted | A server added, changed, or removed |
| MCP servers and tools | Tools Synced | Each time the gateway finds new or changed tools on a server, and the first time it reads a server's tools |
| MCP servers and tools | Tools Approved | New or changed tools that were held back, approved by an administrator |
| MCP servers and tools | MCP Tagged, Tool Tagged | A tag assigned to a server or a tool |
| Sign-ins and access | Connection Created, Connection Removed, Connection Revoked, Connection Expired | A person's sign-in to a server that acts on their behalf |
| Sign-ins and access | MCP Request Created, MCP Request Withdrawn, MCP Request Dismissed | A person's request for access to a server |
| Rules | Policy Set, Policy Updated, Policy Removed | An access rule added, changed, moved, or removed |
| Rules | DLP Rule Created, DLP Rule Updated, DLP Rule Deleted | A response filter added, changed, or removed |
| Rules | Rate Limit Created, Rate Limit Updated, Rate Limit Deleted | A usage limit rule added, changed, or removed |
| Rules | Tag Created, Tag Updated, Tag Deleted | A tag added, changed, or removed |
| Rules | Audit Policy Created, Audit Policy Updated, Audit Policy Deleted | An audit policy added, changed, or removed |
| Administration | API Key Created, API Key Rotated, API Key Revoked | An API key added, rotated, or revoked |
| Administration | Role Created, Role Updated, Role Deleted, User Roles Changed | A role added, changed, or removed, or a person's roles changed |
| Administration | User Deleted, Group Deleted | A person or a group removed |
| Administration | Gateway Settings Updated | A change to the gateway's settings |
| Administration | Webhook Created, Webhook Updated, Webhook Deleted, Webhook Disabled | An event forwarding webhook added, changed, removed, or turned off |
| Administration | Ingest Key Created, Ingest Key Revoked | A telemetry ingest key added or revoked |
| Findings | Anomaly Detected, Anomaly Escalated, Anomaly Resolved, Anomaly Status Changed | An anomaly found, escalated, resolved, or triaged |
| Findings | Finding Status Changed | A status change on a non-human identity finding |
| Costs | Seat Price Set, Seat Price Ended, Seat Price Deleted | A seat price set, ended, or removed; a new rate names the rate it replaced |
| Costs | Seat Assigned, Seat Assignment Ended, Seat Assignment Removed | A plan assigned to a person, ended, or removed |
Approvals, access requests, held-back tools, model calls, audit policies, and non-human identity findings appear only when SecureAuth has turned those features on for your organization.
What each entry shows
- Timestamp – when the event happened
- Actor – the person or agent that acted
- Action – the event, by the name the Action filter shows
- Resource – the MCP server, agent, rule, or other item involved
- Details – what the action did, such as the tool name, the error, or the fields that changed
When the event records them, an entry also shows the IP address and the client it came from.
Entries with more to show have a chevron: agent connections, tool calls, tool searches that returned tools, model calls with a redaction or a recorded prompt, Tools Synced entries with more tools than fit on the row, and changes that list fields before and after. Select it to expand the entry. Anomaly entries link to the anomaly instead.
See which rule decided a call
Expand a Tool Executed or Tool Failed entry to see the tool, the MCP server, the agent, and the decision.
- Allowed – the call ran, and the entry names the rule that allowed it.
- Blocked – the entry names the rule that blocked the call, and the reason. A call that matched no rule is blocked by default, so its entry names no rule.
- Refused by a usage limit – the entry names the limit. A limit set to log only lets the call run and still names the limit on the entry.

Expand an Agent Connected entry to see what the agent could use when it opened the session. Each server it could reach shows how many of its tools were allowed, conditional, or denied. A conditional tool runs only when an argument-level condition passes on that call, or only after someone approves it. Expand a server to see its tools grouped under the rule that decided them. Tools that matched no rule appear under No matching rule · default deny. A blocked server names the rule that blocked it, or says no rule grants access. A server the agent couldn't reach shows the reason. Each rule name links to the rule in Agent Access.

See what was redacted
A tool call whose response was redacted carries a Redacted ×N badge, where N is the total number of spans replaced. Hover over the badge or move focus to it to see how many spans each response filter replaced. Expand the entry to see the same counts, with each filter name linked to it in Data Protection. Agent Trail stores the filter names and counts, never the redacted text.
Model calls carry the same badge when a Data Protection rule redacted the prompt or the response.
A filter in log-only mode adds a Would redact ×N badge instead, and its counts appear under DLP log-only matches when you expand the entry. The agent gets the content unchanged. End users never see log-only matches.
What end users see
End users see a narrower version of this feed. Their Activity page shows only their own events, and only these: their tool calls, model calls, tool searches, approvals, access requests, agent events, and sign-ins to servers. Detail payloads are stripped, so they see which tools an agent could use but never which rule decided it. On an agent connection event, blocked servers, denied tools, and why a server couldn't be reached appear only in Agent Trail. Tool rows stay single-line, and the redaction badge reads a generic Content redacted without naming the rules or counts. Administrative changes, and anyone else's activity, are visible only in Agent Trail.
How long Agent Trail keeps events
Agent Trail keeps three months of history, then deletes it. To keep events longer, or to investigate them in your SIEM, forward them as they happen with Event forwarding.
Filtering
Use the filter dropdowns at the top of Agent Trail to narrow the feed:
- Action – filter by event, using the names in What's recorded
- Agent instance – see activity for a specific connected client
- Agent – roll up across every instance of one agent (for example, all Claude Code clients)
- User – events attributed to a specific gateway user
- Group – events from the current members of a user group
- MCP – see events related to a specific MCP server
- Agent tag – events from any agent carrying a tag (for example, all
prodagents) - Resource tag – events on any MCP server or tool carrying a tag
- Autonomous – choose Only for events by autonomous agent instances, or Exclude for events by user-bound ones
Agent Trail lists the newest events first. Scroll down and click Load more to see older ones.
Excluding values
The Action, Agent instance, Agent, User, Group, and MCP filters can also hide events. Click a value to include it. Click again to exclude it, and once more to clear it. The include and exclude buttons on each row set a value directly.
An exclusion keeps events that have no value for that field. Excluding an agent still shows events that name no agent, such as policy changes. Excluding a group hides events from its current members. The Agent tag and Resource tag filters only include.
The Autonomous filter works differently. Both Only and Exclude keep just the events an agent performed, so policy changes and other events with no agent drop out. Events recorded before SecureAuth tracked this flag match neither choice.
Find what you need
| To answer | Filter by |
|---|---|
| Why a call was blocked | Action set to Tool Failed, with Agent or User, then expand the entry |
| Which tools an agent got when it connected | Action set to Agent Connected, with Agent; the oldest entry is its first session |
| Who changed an access rule | Action set to Policy Set, Policy Updated, or Policy Removed |
| Whether a response filter is working | Action set to Tool Executed, then look for the Redacted ×N badge |
| Every tool call to one MCP server | MCP |
| Only setting changes, without the tool calls | Action, with Tool Executed excluded |
Moving a rule records Policy Updated with its new position, whether you drag it or set Place at when you edit it.
Why an agent can't reach an MCP server
An Agent Connected entry lists each server the agent couldn't reach, with the reason. The MCP filter doesn't find these entries, so filter by Action and User instead.
| The entry says | What it means |
|---|---|
| its server could not be reached | The gateway couldn't connect to the MCP server |
| the user's sign-in could not be refreshed | The person's own sign-in to the server couldn't be renewed |
| it needs a user, and this agent belongs to the organization | The server acts for a person, and an organization-owned agent has none |
| enterprise-managed authorization failed | Enterprise-managed authorization failed; the entry names where it failed and the error code |
A server that kept its last known tools is listed once, as allowed, with the reason under it. A server made of several services lists each service that failed with its own reason, even when the rest connected. To see which servers are failing and for whom, see MCP server health.
Next steps
You can now find who did what in Agent Trail, see which rule decided a call, and trace why an agent couldn't reach a server. Next, forward events to your SIEM so you keep them past three months.
- Event forwarding – send events to your SIEM as they happen
- MCP access audit – the MCP entries, with filters for MCP servers and tools
- MCP usage analytics – trends instead of a raw event feed
- Policies – the rules behind every allow and deny you see here


