Give your AI a pre-publish compliance check.
Four MCP tools for your agent: checkcontent against 8 platforms' policies before it ships, track policy changes, see how much each platform is actually enforcing (EU DSA), and follow the fines and lawsuits regulators are bringing. No API key, no config file — add the connector, sign in, and approve.
Pick your client to connect ↓
- 1
Open Settings → Connectors → Add custom connector.
Claude asks for a paid plan at this step — theirs, not ours.
- 2
Paste this link.
https://www.auditsocials.com/api/v1/mcp - 3
Sign in and approve. That's it — nothing to paste back.
AuditSocials
wants to connect to your assistant
Check content before you post
Runs a pre-publish policy pass on the draft you send
Read recent policy changes
The latest platform moves AuditSocials detected
Spend credits from your plan
The same pool as your API key — 500/mo free
We never see what you ask your assistant — only the content it sends here to check.
Tip:connect once and the tools live in your account. Like any AI connector, enable AuditSocials for a conversation if it doesn't show up, and pick “Always allow” so it stays on across chats.
AlternativePrefer an API key? Config-file setup for older / headless clients
Older clients or headless setups (CI, servers) can use a key in mcp.json instead of signing in. Grab a free key here, then use the hosted URL or run it locally with npx — same tools, same account.
{
"mcpServers": {
"auditsocials-compliance": {
"url": "https://www.auditsocials.com/api/v1/mcp",
"headers": { "Authorization": "Bearer as_live_..." }
}
}
}{
"mcpServers": {
"auditsocials-compliance": {
"command": "npx",
"args": ["-y", "auditsocials-compliance-mcp"],
"env": { "AUDITSOCIALS_API_KEY": "as_live_..." }
}
}
}Four tools, plain language.
No prompt engineering — your agent reads the tools and picks the right one. Check content, track policy changes, measure enforcement, and follow regulator moves. Here's what each does, with a real exchange.
Catch the risk before you post.
Send any draft — caption, ad, post or video script — and your agent gets back the exact risky phrases, why each is a problem, and a compliant rewrite, across all 8 platforms. Hard bans and the quiet stuff (reduced distribution, demonetization).
Try the live checker{
"content": "BUY NOW — 90% off, guaranteed results",
"platforms": ["meta", "tiktok"]
}{
"verdict": "needs_changes",
"findings": [{
"severity": "critical",
"matchedText": "guaranteed results",
"suggestion": "Drop the outcome guarantee"
}]
}Just ask — in plain language
No prompt engineering. Your agent picks the tool automatically. A few ways it comes up:
Check this caption against TikTok and Meta before I post it: “…”
Did TikTok change its advertising policy this week?
Is this ad copy safe to run on Meta? Rewrite anything risky.
What healthcare policy changes happened across platforms this year?
Not just hard bans — the quiet risks too.
Most checks only tell you what's outright prohibited. Platforms rarely ban outright — they quietly reduce distribution, demonetize, or shadow-limit. Every finding carries a confidence label so your agent can act proportionately:
A specific, well-established policy term matched. High confidence — fix before publishing.
A borderline or semantic signal — reduced-distribution territory. Flagged, not overstated.
Findings are grounded in the same live policy engine behind the AuditSocials Policy Tracker and enforcement layer — never fabricated, and hedged when uncertain.
Credits scale with depth: policy read 1 · enforcement 5 · AI check 5 · regulator signals 10. No credit card.
Meta, TikTok, LinkedIn, Google Ads, YouTube, X, Snapchat, Pinterest + DSA signals.
Higher volume when you outgrow the free tier — usage-based.
Give your AI a pre-publish compliance pass
One connector, 30-second setup — sign in and approve, no key or config file. Your agent discovers all four tools automatically: check any draft against all 8 platforms, track policy changes, measure enforcement volume, and follow regulator moves — on demand.
Connector URL
https://www.auditsocials.com/api/v1/mcpPaste into your client's “Add custom connector” → sign in → approve. No key needed.