Skip to main content
Glama
shigechika

gwsadm-mcp

by shigechika

ip_activity

Identifies every account a source IP address acted on across applications and domains, and shows posture flags and login failures to determine whether an attacker's address reached other accounts.

Instructions

Every account ONE source address acted as, across applications and domains.

The follow-through after user_activity names an attacker's address: did the same source get into other accounts? The Reports API filters on actorIpAddress server-side, so this is one probe per (domain × application) over the matching events only, not a scan of the whole tenant's log — and every domain's probes run in one pool, so a slow domain does not delay another's answer. Per domain it returns the acting accounts (count, first/last seen, which applications) ordered by most recent, the posture flags the address triggered (same definition as user_activity; Google's own verdicts are included here when they carry the address, since userKey=all sees them), and per-application accounting. Failed logins from the address appear under applications.login.events as login_failure — a spray from this address shows there before it ever succeeds.

Coverage reads as in user_activity: window.start, per-application capped / error (and the union capped, a failed application included), and a per-domain error when that domain's credential is rejected (the other domains still answer). A quiet answer for a current-day window can be data lag rather than absence.

Read-only (Reports API activities().list only, the admin.reports.audit.readonly DWD scope).

Args: ip: The source address, IPv4 or IPv6 literal (no zone id). Validated before use. hours: Window length ending now. applications: Comma-separated application names; default as in user_activity. max_pages: Page budget per (domain × application). top: Accounts returned per domain, most recently seen first; accounts_total says how many there were. domain: Restrict to one configured [domain.*] section. Default: every configured domain, since an address is not tied to one.

Input Schema

NameRequiredDescriptionDefault
ipYes
topNo
hoursNo
domainNo
max_pagesNo
applicationsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.22.1

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so: it declares read-only behavior, names the Reports API method and DWD scope, explains per-domain concurrency, reports partial failures/capping, and warns that quiet current-day results may reflect data lag.

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 description is front-loaded with the purpose and organized into usage, return, coverage, safety, and args sections. It is dense and longer than typical, but nearly every sentence carries operational meaning for a complex multi-domain audit query.

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?

There is no output schema, but the description explains the returned accounts, flags, per-application accounting, login failure visibility, coverage indicators, and per-domain error behavior. An agent has enough context to invoke and interpret this tool correctly.

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

Parameters5/5

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

Schema description coverage is 0%, but the Args section documents all six parameters meaningfully: `ip` validation and IPv4/IPv6 literal requirement, `hours` window semantics, `applications` comma-separated/default behavior, `max_pages` as a per-domain/application budget, `top` ordering and `accounts_total`, and `domain` restriction/default.

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 first sentence states a specific resource and scope: accounts that one source IP acted as, across applications and domains. The description also distinguishes this from `user_activity` by framing it as the follow-through after an attacker address is named.

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

Usage Guidelines5/5

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

It explicitly says when to use this tool: after `user_activity` names an attacker's source address, to see whether that address reached other accounts. It also explains the default domain behavior and why an address is not tied to one domain.

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