mcp-github-enterprise

Get audit log

get_audit_log

Read-onlyIdempotent

Fetch recent audit-log events for an organization or enterprise, optionally filtered by action or actor, to review security-relevant activity.

Instructions

Fetch recent audit-log events for the organization (or the enterprise, when GHE_ENTERPRISE is set), optionally filtered by a search phrase like 'action:repo.destroy' or 'actor:octocat'.

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": "get_audit_log"
  }
}

Input Schema

Name	Required	Description
`org`	Yes	Organization login (must be within GHE_ORG_ALLOWLIST when that is set)
`scope`	No	Default org. 'enterprise' requires GHE_ENTERPRISE.
`phrase`	No	Audit-log search phrase, e.g. action:org.update_member
`perPage`	No	Events to return (1–100, default 50)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent and non-destructive semantics, so the description's added value is environment gating: enterprise scope only works when GHE_ENTERPRISE is set, and results are 'recent' events. It does not explain ordering, whether more than one page is retrievable, or any rate-limit behavior, which keeps it short of a 5.

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

Conciseness5/5

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

A single front-loaded sentence carrying the resource, the scope, the optional filter, and the syntax example, with no redundant or filler wording.

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

Completeness4/5

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

With four fully documented parameters, no output schema and annotations covering the safety profile, the description carries enough for correct invocation. The undefined 'recent' window and the lack of any statement about pagination or result limits are the only remaining gaps.

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 description coverage is 100%, so the schema already documents org, scope, phrase and perPage. The description only restates the org/enterprise scope choice and supplies a second example phrase form ('actor:octocat'), which adds marginal meaning beyond the structured fields.

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

Purpose4/5

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

The description gives a specific verb+resource ('Fetch recent audit-log events') and scopes it correctly to the organization or the enterprise. No sibling tool covers audit logs, so there is no ambiguity to resolve, but it also never explicitly contrasts itself with the many list_* siblings.

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 implies when the tool applies (need audit-log events, optionally narrowed by a search phrase) and states the environment condition for enterprise scope. It gives no when-not guidance and names no alternative for related needs such as posture assessment or security alerts.

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