> ## Documentation Index
> Fetch the complete documentation index at: https://docs.guardway.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Logs

> Inspect every request, MCP tool call, guardrail trigger, and trace through the gateway.

## What this is for

The **Logs** page is the operational view of traffic flowing through your gateway. It captures four complementary perspectives, organized as tabs:

* **Requests** — flat, filterable table of every HTTP request the gateway served.
* **MCP** — every tool call made through an MCP server attached to the gateway.
* **Guardrails** — every guardrail rule trigger (input or output, blocked or logged).
* **Traces** — OpenTelemetry timelines showing how each request flowed through guardrails, auth, routing, cache, and the upstream provider.

<Warning>
  Request, MCP, guardrail, and trace logs are recorded **on the gateway**. Viewing them requires the dashboard to be connected to that gateway — see [Activation](/guardway-gateway/activate). Administrative audit logs live on the platform — see [Audit Log](/platform/settings/audit-log).
</Warning>

## Requests

The default tab. A flat table of every HTTP request, sortable on any column.

### Columns

Timestamp, method, path, status, duration, provider, model, API key name, tokens (prompt + completion), cost, client IP, and trace ID.

### Filters

| Filter     | Notes                                            |
| ---------- | ------------------------------------------------ |
| Time range | Presets (1h, 24h, 7d, 30d) or a custom calendar. |
| Gateway    | Multi-select. Leave empty for all gateways.      |
| Provider   | Multi-select.                                    |
| API Key    | Multi-select.                                    |
| Search     | Matches request path, model, or API key name.    |

<Frame caption="Logs → Requests">
  <img src="https://mintcdn.com/fcguardwayai/rJTQ_bXDRs9Cgazf/images/screenshots/platform/logs/logs-table.png?fit=max&auto=format&n=rJTQ_bXDRs9Cgazf&q=85&s=10b45cfbc13bacb547431dab223b1fa8" alt="Requests log table" width="2382" height="1754" data-path="images/screenshots/platform/logs/logs-table.png" />
</Frame>

<Tip>
  Click a row's **trace ID** to jump straight to the matching trace.
</Tip>

## MCP

Every call to a tool exposed by an MCP server registered with the gateway is logged here.

| Column             | Notes                                                         |
| ------------------ | ------------------------------------------------------------- |
| Timestamp          | When the call was made.                                       |
| MCP server         | The server that handled the call.                             |
| Tool               | The tool name.                                                |
| Caller             | The API key or session that invoked the tool.                 |
| Status             | `ok`, `error`, or `denied` (blocked by MCP scope on the key). |
| Duration           | Round-trip time.                                              |
| Request / Response | JSON payload, viewable inline.                                |

Filters mirror Requests: time range, gateway, and a free-text search that matches tool name, MCP server, or API key name.

<Frame caption="Logs → MCP">
  <img src="https://mintcdn.com/fcguardwayai/rJTQ_bXDRs9Cgazf/images/screenshots/platform/logs/mcp-logs-table.png?fit=max&auto=format&n=rJTQ_bXDRs9Cgazf&q=85&s=f1d420cfc08d974fadf8d8f31149665a" alt="MCP logs" width="2846" height="1276" data-path="images/screenshots/platform/logs/mcp-logs-table.png" />
</Frame>

<Tip>
  If a call shows **denied**, check the API key's MCP scope on [API Keys](/platform/configuration/api-keys) — the key's allow-list is the usual cause.
</Tip>

## Guardrails

Every guardrail rule trigger — both rule-based ([Guardrails](/platform/configuration/security#guardrails)) and SLM-based ([SLM Guardrails](/platform/configuration/security#slm-guardrails)) — is recorded here. Each row shows the rule name, category, action taken (`block`, `warn`, `redact`, `log`), the matched content (or its hash for redacted entries), and a link back to the originating request.

Use this tab to audit policy hits, tune thresholds before promoting an SLM model to a blocking action, and confirm a rule is matching what you expect.

<Frame caption="Logs → Guardrails">
  <img src="https://mintcdn.com/fcguardwayai/rJTQ_bXDRs9Cgazf/images/screenshots/platform/logs/guardrails-logs.png?fit=max&auto=format&n=rJTQ_bXDRs9Cgazf&q=85&s=bc555852f4dd463215c1ab2a940e069e" alt="Guardrails logs" width="3036" height="1768" data-path="images/screenshots/platform/logs/guardrails-logs.png" />
</Frame>

## Traces

A trace is a timeline of the steps a request went through inside the gateway. Each step has an icon:

| Icon   | Step                                                                    |
| ------ | ----------------------------------------------------------------------- |
| Shield | Guardrail evaluation (PII, hate speech, prompt injection, keyword, IP). |
| Key    | Authentication and quota check.                                         |
| Router | Routing rule match + provider selection.                                |
| Cloud  | Upstream model call.                                                    |
| Cache  | Cache hit or miss.                                                      |

Click a step to see its latency, tokens consumed, cost contribution, and any error. The entire trace is time-aligned, so a slow guardrail or a stuck provider call stands out immediately.

<Frame caption="Logs → Traces">
  <img src="https://mintcdn.com/fcguardwayai/rJTQ_bXDRs9Cgazf/images/screenshots/platform/logs/traces-detail.png?fit=max&auto=format&n=rJTQ_bXDRs9Cgazf&q=85&s=ff69a64e4db1f2f19c934b3d3c34d72b" alt="Trace detail" width="3456" height="1924" data-path="images/screenshots/platform/logs/traces-detail.png" />
</Frame>

## How to configure

There is no configuration on this page itself — Logs is read-only. To change what gets captured:

<Steps>
  <Step title="Add or rotate API keys">
    [Configuration → API Keys](/platform/configuration/api-keys) determines which key labels show up in the **API Key** filter.
  </Step>

  <Step title="Tune guardrails">
    [Configuration → Security](/platform/configuration/security) controls what shows up in the **Guardrails** tab.
  </Step>

  <Step title="Adjust retention">
    Log retention is set per gateway in the gateway environment. See [Environment](/guardway-gateway/environment).
  </Step>
</Steps>

## Exports

From any tab, click **Export** to download the current filter as CSV or JSON. Exports are assembled locally on the gateway; the dashboard only forwards the query.

## Related

* [Audit log](/platform/settings/audit-log) — administrative actions, recorded centrally on the platform.
* [Configuration → Security](/platform/configuration/security) — rules whose triggers show up in the Guardrails tab.
* [Notifications](/platform/settings/notifications) — push these events to webhooks.