Skip to main content
Glama

Read audit log

audit_list
Read-only

The organization's audit log, the newest event first: every change to its people and roles, invitations and requests to join, teams and their members, which wikis exist and who holds them (grants, visibility, renames, deletions), what is shared with other organizations, its sites, domains and settings. Each event says what was done (action, the method that did it: wiki.grant), when (at), who did it and through what (actor: id, client web, cli, mcp, assistant or app, and the agent when one acted for them), what it was done to (target: kind, id, name as it was then), the person it was done to (person) and the rest (detail). Read by the organization's owners only. Narrow with action, actor, person, kind or target; continue with before, the next of the page before.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "org": "<org>"
    },
    "name": "audit_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgYesslug of the organization whose people, teams and access to use. Required on every call, even when only one organization is listed; a path never names it.
kindNoOnly changes to this kind of thing.
actorNoOnly changes this person made, by user id.
limitNoEvents per page; 50 when left out.
actionNoOnly one kind of change: a method (wiki.grant, team.addMember, members.remove) or a whole family (wiki, team, members, share, site, domains, org).
beforeNoThe next of the page before, to continue past it.
personNoOnly changes made to this person or by them, by user id.
targetNoOnly changes to this one thing, by its id or its name then: a wiki's name, a team's id or slug, a site's id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond them: newest-first ordering, the owner-only access requirement, and — since there is no output schema — the full shape of an event (action, at, actor including client channel, target, person, detail). It does not discuss page-size defaults or total counts, but the behavioral picture is strong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core fact (audit log, newest first) is front-loaded and the filtering/pagination instructions close it out. The first sentence is a long enumerated run-on, and the event-field breakdown partly overlaps the parameter list, but almost every clause carries scope information that helps an agent decide if this tool has the events it needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter read tool with no output schema, the description covers everything an agent needs: what is logged, ordering, access prerequisite, how to filter, how to paginate, and the structure of returned events. Nothing material is left to guesswork.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter is already documented in structured form, which sets the baseline at 3. The description does add a conceptual mapping — action as the method that did it (wiki.grant), actor as who did it, person as the one acted upon, target as the thing in its then-current name — but it largely restates the schema descriptions rather than extending them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and scope: 'The organization's audit log, the newest event first', then enumerates exactly what is captured (people, roles, invitations, teams, wikis, shares, sites, domains, settings). This is clearly a change-history reader, distinct from the sibling list/read tools such as members_list or site_list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives operational guidance on narrowing ('Narrow with action, actor, person, kind or target') and continuing ('continue with before'), plus a permission gate ('Read by the organization's owners only'). However, it never says when to prefer this over alternatives — an agent must infer that this is for history rather than current state, and that members_list/site_list exist for snapshots.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources