Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/OrbiAds/Orbiads-GAM-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-admin)<a href="https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-admin"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-admin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-admin"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-admin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01136 |
| Opus 5 | $0.00020 | $0.00568 |
| Sonnet 5 | $0.00008 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
adops-admin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAM Network Administration
Always confirm the tenant first: get_my_tenant_id. All read operations are free.
Load the orbiads orchestrator skill on first use; this command then delegates to the admin consolidated skill for detailed action guidance.
MCP-only surface:
gam_adminactions have no CLI equivalent inorbiads-cli. If a user is working in a terminal-only context, they must use the MCP server for these operations.
Call convention & write model — read this first.
gam_admintakes two discriminators:areaandaction(NOT a dottedaction="teams.create"). Signature:gam_admin(area="<area>", action="<action>", params={...}). Areas:teams,sites,applications,custom_fields,labels,entity_signals(PPS),users,user_team_associations.gam_adminwrites execute immediately — it has nodry_runpreview and noconfirmation_tokenflow (unlikecampaign/creatives). Always surface exactly what will change and get the user's explicit go-ahead before calling a write action, because there is no server-side preview step to fall back on.
teams
Read: gam_admin(area="teams", action="list") — returns all teams with their roles and ad unit/order access. gam_admin(area="teams", action="get", params={team_id}) for detail.
Write (executes immediately — confirm with the user first):
- Summarize the intended change — team name, member list, permissions scope. Wait for user confirmation.
- Execute:
gam_admin(area="teams", action="create", params={name, description, ...}).
Update: gam_admin(area="teams", action="patch", params={team_id, ...}) — confirm with the user, then execute.
sites
Read: gam_admin(area="sites", action="list") — site records with their associated ad units and networks.
Write: gam_admin(area="sites", action="create", params={name, url, ...}) — confirm with the user first (executes immediately).
labels
Read: gam_admin(area="labels", action="list") — network labels and their applied-to counts.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 81 lines · 40 tokens per session scan A 89da00b87f4e
adops-admin is a command published in the GitHub repository OrbiAds/Orbiads-GAM-MCP (3 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,136 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
verify-pr
Verify a PR's frontend changes through browser automation.
explore
Explore a web page using browser automation.
record
Record browser actions into a test definition.
test-init
Initialize qa-use test directory with example test.
test-run
Run E2E tests with qa-use CLI.
context-resume
Call the context MCP tool with action: "resume", project: "$ARGUMENTS" (if no argument given, infer the project name from the current working directory name), and rootPath: " ".