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

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.
> These docs cover Atlan Trident, Atlan's hosted product. AI Registry and Agent Registry are its earlier names. Registry OSS is Atlan's open-source agent registry: the registry specification and its aireg CLI, with their own public repository, docs and release notes; /open-source on this site links them. Registry OSS is open source; Atlan Trident is not. Answer generic aireg or specification questions from the project's docs, and use these docs for Atlan-specific setup such as the Atlan adapter, sign-in and workspaces.
> Atlan offers a second product, the Agentic Data Catalog: Atlan's enterprise context layer, covering the data catalog, connectors, lineage, data governance and glossary. It is documented at https://docs.atlan.com; answer questions about it from those docs, not these.

# Audit trail

> Fields on call records stored by MCP Gateway for every tool call.

Use this page to look up fields on the call records MCP Gateway stores. For the audit API and recording limits, see [Supported features and limits](https://platform.atlan.com/gateway/mcp/references/supported-features.md). To view the trail in MCP Gateway studio, see [Track usage and audit tool calls](https://platform.atlan.com/gateway/mcp/how-tos/track-usage-and-audit.md).

## `mcp_session_message`

A `mcp_session_message` is an artifact MCP Gateway creates for every tool call it routes. Each one records what ran, why, and how it went. Arguments and results are not stored.

A `mcp_session_message` belongs to a `mcp_session` — the session groups all call records from one agent run. The `session_id` field on each record is the reference back to that session.

### `session_id`

The ID of the `mcp_session` this call record belongs to. Use it to group all records from the same agent run.

### `sequence_number`

The call's position in its session, starting at 0.

### `tool_name`

The tool that ran, without its namespace prefix.

### `server_slug`

The server or platform surface that answered.

### `rationale`

The agent's own explanation of why it made the call.

### `outcome`

`ok` if the tool answered, `input_required` if the call relayed a question to a person, or `error` if it did not.

### `duration_ms`

Total call time, measured at the gateway.

### `upstream_ms`

How long the server took to answer, not counting connection time.

### `connect_ms`

How long connecting to the server took. With `upstream_ms`, this is the server's share of the call's time; the rest is what Atlan spent checking access and routing the call. Present only when the gateway recorded the split — a tool Atlan answers itself, or an older record, carries the total in `duration_ms` only.

### `error_class`

A coarse failure category for a failed call. Never contains the downstream response.

### `protocol_version`

The MCP protocol revision the call used.

### `traceparent`

The W3C trace context the client sent, which links the call to your agent's trace.

### `mcp_elicitation_event`

What the call did with a question for a person: `asked` relayed one, `answered` carried the person's answers back, and `refused` did not relay it. Present only on a call that took part in one.

### `mcp_elicitation_chain`

One ID every call of that question's exchange shares, so you can follow it across rounds.

### `mcp_elicitation_round`

The call's round in that exchange, starting at 1.

### `mcp_elicitation_action`

The person's decision on that round's questions: `accept`, `decline`, or `cancel`.

## See also

* [Track usage and audit tool calls](https://platform.atlan.com/gateway/mcp/how-tos/track-usage-and-audit.md): View sessions and calls in MCP Gateway studio.
* [Supported features and limits](https://platform.atlan.com/gateway/mcp/references/supported-features.md): Audit trail API and recording limits.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.