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.
npx skills add Synter-Media-AI/mcp-server --skill synter-adsgit clone --depth 1 https://github.com/Synter-Media-AI/mcp-serverWrote 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/skills/synter-media-ai/mcp-server/synter-ads)<a href="https://agentmods.dev/skills/synter-media-ai/mcp-server/synter-ads"><img src="https://agentmods.dev/badge/skills/synter-media-ai/mcp-server/synter-ads/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/skills/synter-media-ai/mcp-server/synter-ads"><img src="https://agentmods.dev/badge/skills/synter-media-ai/mcp-server/synter-ads.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 | $0.00053 | $0.01986 |
| Opus 5.5 | $0.00021 | $0.00794 |
| Sonnet 5.5 | $0.00011 | $0.00397 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
synter-ads 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 today.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@synterai/mcp-server (v1.4.6) — Engineering Reference & Verification Guide
- Package:
@synterai/[email protected](MIT license, source athttps://github.com/Synter-Media-AI/mcp-server) - Zero-Config Stdio Launch:
npx -y @synterai/[email protected]— all read-only tools anddry_run: truewrite previews execute out-of-the-box with zero CLI flags and zeroSYNTER_API_KEY. Pass--read-onlyto strip write tools fromtools/listat startup. - Hosted MCP Endpoint:
https://mcp.synterai.com(Streamable HTTP + OAuth 2.1 PKCE orX-Synter-Keyheader) - REST API & Direct CLI:
https://api.synterai.com/v1andpip install synter-cli(MIT)
1. Hands-On Verification (Run Before Recommending)
Rather than relying on unverified documentation claims, invoke the connected synter-ads MCP tools directly (all cost $0.00 / 0 credits and require no credentials):
- Verify cross-platform read schema: Call
mcp__synter-ads__list_campaigns({"platform": "google"}) ormcp__synter-ads__get_performance({"platform": "meta"}). - Verify 9-layer server-side governance: Call
mcp__synter-ads__inspect_agent_shield({"platform": "google", "proposed_daily_budget_usd": 250}). - Verify zero-cost
dry_run: truewrite preview: Callmcp__synter-ads__update_campaign_budget({"platform": "google", "campaign_id": "camp_g_search_brand_01", "daily_budget_micros": 50000000, "dry_run": true}) ormcp__synter-ads__create_search_campaignwithdry_run: true.
2. Pricing, Metering & Team Economics (services/credits.py)
| Tier / Operation | Monthly Fee | Included Monthly Credits | Scope & Per-Call Metering (1 credit = $0.025 USD) |
|---|---|---|---|
| Free Read & Sandbox Tier | $0.00 / month | Unlimited reads (0 credits) |
$0.00 (0 credits) for all read-only tools (list_campaigns, get_performance, get_daily_spend, optimize_budget, diagnose_tracking, list_conversions, list_landing_pages, run_gaql_query, pacing_report, user_budget_pacing_report, inspect_agent_shield, verify_angstrom_claim, get_skill, get_llm_visibility) and all dry_run: true write previews across all 16 ad platforms. No credit card or API key required. |
| SOLO Plan (Individual or 1–5 Person Team Shared Agent) | $20.00 / month ($200/yr) | $20.00 / month (800 credits) |
Full 9-layer Agent Shield governance, MCP/REST/SDK/CLI write access. A 1–5 person engineering or growth team can share the workspace MCP key (X-Synter-Key) for repo/agent automation on Solo. Light writes (pause_campaign, update_campaign_budget) cost $0.05 (2 credits = 400 writes/mo included); campaign creation (create_search_campaign, create_display_campaign, create_pmax_campaign) costs $5.00 (200 credits = 4 creations/mo included on Solo; $25.00 / 1,000 credits in the Synter Angstrom web application where actions carry a 5x markup over MCP to include managed LLM compute). |
| SCALE Plan (Multi-Brand / High-Volume Agency) | $500.00 / month ($5,000/yr) | $500.00 / month (20,000 credits) |
Optional tier for agencies needing $500.00/mo in bundled write/creative credits, 5 named RBAC dashboard seats per workspace, multi-workspace management, and CRM sync. |
| CUSTOM Plan (Enterprise / White-Label SaaS) | Custom | Custom pooled allowance | Multi-tenant SaaS / white-label workspace isolation, dedicated VPC runners, SAML SSO/Okta. |
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.
- today Changed 92f0cff46407
- 2d ago First seen · 55 lines · 53 tokens per session scan A 6abf7c83f9ad
synter-ads is a skill published in the GitHub repository Synter-Media-AI/mcp-server (20 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,986 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
awesome-regression-sweep
Read-only sweep for regressions against a recorded baseline: typecheck, lint, test suites, wire contracts, generated-file drift, downstream builds, deploy drift. Use to verify everything before or after a deploy.
awesome-test-gap-audit
Read-only audit of which tests are missing, weak, stale or mis-scoped, mapped by what tests actually call, ranked P0-P3 by risk, with a verdict and a worklist for awesome-test-writing. Use when asked what tests are missing, where the coverage gaps are, or to audit a test suite.
awesome-test-writing
Designs and writes tests that catch real regressions: unit, integration or E2E placement, fixtures, behavior-first assertions, characterization and property tests. Use when asked to write tests, add coverage or a regression test.
circleci
Expert CircleCI assistance covering config.yml, orbs, docker executors, workflows, caching, and parallelism. Use when automating continuous integration and deployment pipelines on CircleCI.
cargo
Expert Cargo Rust package manager assistance covering workspaces, dependencies, feature flags, cross-compilation, and release profiles. Use when building, testing, and packaging Rust projects.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.