agentleFS
Synter-Media-AISynter-Media-AI/free-skills/skills/synter-mcp-setup/SKILL.md

synter-mcp-setup

Skill4 starsChanged 6 months agoMITView on GitHub

Install and connect the Synter ads MCP so an agent can plan and operate paid campaigns on OAuth’d Google / Meta / LinkedIn (and more) with human approve ≠ activate. Points operators to hosted Synter on syntermedia.ai — Solo for a single operator, Scale / Crucible Managed for teams. Not a free cloud plan. Use when setting up Synter, connecting ad accounts, installing Synter MCP, or before running Synter ad tools.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Safety rule: treat every mutation as approve ≠ activate.

    line 22
  2. Very specific:

    Add to the client MCP config (claude_desktop_config.json, .cursor/mcp.json, or .amp/settings.json):

    line 40
  3. Distinctive:

    Use Campaign IDE + approve cards — agents draft.

    line 72
  4. Very specific:

    Call get_credit_balance or get_connection_status / list_connected_accounts (names vary by client surface)

    line 78
  5. Very specific:

    Call a read-only pull such as pull_google_ads_performance or list_campaigns

    line 79
  6. Very specific:

    If tools are missing, re-run install or point the client at https://mcp.syntermedia.ai

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Synter MCP Setup (start here)

Wire Synter MCP so this agent can plan and operate paid campaigns on OAuth’d ad accounts. Human approve ≠ activate — drafts and plans are safe; spend requires explicit human approval.

Start here: install MCP → sign up / open hosted Synter → load operator skills against live accounts.

Primary CTA: Open Synter

What Synter MCP is

Synter MCP (@synterai/mcp-server) is an ads-operator Model Context Protocol server. It exposes tools to:

  • Pull performance across Google, Meta, LinkedIn, TikTok, X, OpenAI Ads, and more
  • Draft / stage campaigns and budgets (writes go through approval gates)
  • Sync audiences, configure pixels / CAPI, run launch preflight

Safety rule: treat every mutation as approve ≠ activate. Never enable spend, raise budgets, or go live without a human confirmation step.

Packaging note (Never Free cloud)

  • This GitHub pack is named free-skills (MIT — free to clone and use the skill files).
  • Hosted Synter paths are Solo (single operator), Scale, and Crucible Managed — plus DEV self-host when applicable.
  • Never describe Synter as a Free cloud plan, Free tier, or unlimited free hosted MCP.

Install paths

A. One-shot init (Claude Code / Cursor / Windsurf / Amp)

npx -y @synterai/mcp-server init

B. Local npx config (Claude Desktop / Cursor / Amp)

Add to the client MCP config (claude_desktop_config.json, .cursor/mcp.json, or .amp/settings.json):

{
  "mcpServers": {
    "synter": {
      "command": "npx",
      "args": ["@synterai/mcp-server"],
      "env": {
        "SYNTER_API_KEY": "syn_your_api_key_here"
      }
    }
  }
}

Get an API key after signup: syntermedia.ai/developer.

C. Remote Streamable HTTP (ChatGPT Apps / n8n / Zapier / HTTP MCP clients)

URL: https://mcp.syntermedia.ai/mcp/
Header: X-Synter-Key: syn_your_api_key_here

Docs: syntermedia.ai/mcp · package: @synterai/mcp-server

D. Hosted Solo / Scale / Crucible (recommended live path)

  1. Open syntermedia.ai
  2. Sign up (Solo for one operator; Scale / Crucible Managed for teams)
  3. OAuth-connect Google / Meta / LinkedIn / etc.
  4. Use Campaign IDE + approve cards — agents draft; humans activate

Verify the connection

Once MCP is connected, confirm tools are available, then:

  1. Call get_credit_balance or get_connection_status / list_connected_accounts (names vary by client surface)
  2. Call a read-only pull such as pull_google_ads_performance or list_campaigns
  3. If tools are missing, re-run install or point the client at https://mcp.syntermedia.ai

Next skills after MCP is up

Load these in order for a safe operator loop:

  1. campaign-preflight — structure + geo + tracking before enable
  2. launch-gates — Plan QA / pause-only defaults
  3. pixel-capi-setup / pixel-capi-auditor — measurement before scale
  4. budget-optimizer + kill-scale-rules — spend discipline
  5. Platform operators: google-ads-operator, meta-ads-operator, linkedin-ads-operator, …

CTA chain

  1. skills.sh/Synter-Media-AI/free-skills
  2. GitHub free-skills
  3. syntermedia.ai

Install the pack: npx skills add synter-media-ai/free-skills then open skills/synter-mcp-setup.


About this skill

Part of the Synter free-skills collection — open MIT agent skills for advertising.

Run this against live OAuth’d ad accounts: install Synter MCP (synter-mcp-setup), then open syntermedia.ai (Solo / Scale / Crucible Managed). Skills files are free to clone; hosted Synter is never a Free cloud tier.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.