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/amekala/ads-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/amekala/ads-mcp/setup)<a href="https://agentmods.dev/commands/amekala/ads-mcp/setup"><img src="https://agentmods.dev/badge/commands/amekala/ads-mcp/setup/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/amekala/ads-mcp/setup"><img src="https://agentmods.dev/badge/commands/amekala/ads-mcp/setup.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 | $0.00015 | $0.00670 |
| Opus 5.5 | $0.00006 | $0.00268 |
| Sonnet 5.5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
setup 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 1mo 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.
What it actually says
IMPORTANT: You may execute this workflow directly or delegate parts to the single performance-marketing-agent subagent. Keep responsibility for final output in this command and ensure all required checks are completed.
Run the full brand workspace setup. Follow these steps in order:
-
Connect to Adspirer — Call
get_connections_status.- If it works: continue to step 2.
- If the MCP server is not found: tell the user "Run
/mcpand find the adspirer server (listed under the plugin, e.g. plugin:adspirer-advertising-agent:adspirer) — click to authenticate. If you don't see it, run/plugin marketplace add amekala/ads-mcpthen/plugin install adspirer-advertising-agent. After authenticating, run/adspirer:setupagain." - As a fallback: run
claude mcp add --transport http adspirer https://mcp.adspirer.com/mcpvia Bash, then tell the user to restart Claude Code, run/mcpto authenticate, then run/adspirer:setupagain. - If the MCP server is registered but not authenticated: tell the user "Run
/mcp, find the Adspirer server, and authenticate it. Then run/adspirer:setupagain."
-
Scan local folder for brand docs — use Glob to find files:
**/*.md,**/*.txt,**/*.csv,**/*.yaml,**/*.json,**/*.pdf. Read any files found. -
Pull live campaign data from the platforms that came back connected. Follow
adspirer-mcpfor the call contract.Direct calls:
get_connections_status— run this first; skip any platform it reports as not connectedget_campaign_performance(lookback_days: 30)get_meta_campaign_performance(lookback_days: 30)
Through a router, with
{"action": "execute", "tool_name": "...", "arguments": {...}}:google_ads→list_campaigns,get_business_profile,get_benchmark_contextlinkedin_ads→list_linkedin_campaigns,get_linkedin_campaign_performance(lookback_days: 30)
-
Create CLAUDE.md at the project root with: brand context from scanned docs, connected platforms and account info, performance snapshot with key metrics, KPI targets. Existing-file guard: if a CLAUDE.md already exists and is not an Adspirer brand workspace (e.g. it's a software project's instructions), never overwrite or restructure it — ask the user whether to append a clearly-marked
## Adspirer Brand Contextsection instead, and don't touch the file until they answer. If it's already a brand workspace, update it in place preserving user edits. -
Present a summary of everything found — accounts connected, campaigns discovered, key metrics, and what you can help with
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.
- 1mo ago First seen · 26 lines · 15 tokens per session scan A 28eac62424b7
setup is a command published in the GitHub repository amekala/ads-mcp (103 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 670 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
create-campaign
Create a new ad campaign with AI-generated strategy.
optimize
Get optimization recommendations for your campaigns.
performance
Get a performance report for your campaigns.
research
Research a competitor's advertising strategy.
status
Check the status of your connected ad platforms and active campaigns.
audit
Run a comprehensive 7-dimension account audit.