一个模型上下文协议 (MCP) 服务器，可在 AI 生成的社交媒体和广告内容发布前，对照 8 个平台（Meta（Facebook/Instagram）、TikTok、LinkedIn、Google Ads、YouTube、X（Twitter）、Snapchat 和 Pinterest）的当前广告和社区政策进行检查。 它会返回确切的风险短语、风险原因以及合规的改写建议，从而避免帖子、广告账户和营销活动被标记、降权、限制曝光或封禁。
为您的 AI 写作助手或代理提供一个发布前合规护栏：一个自描述的工具，可对任何草稿进行调用——无需提示工程，无需 SDK。
🛡️ 8 个平台，当前政策 — Meta、TikTok、LinkedIn、Google Ads、YouTube、X、Snapchat、Pinterest 的广告 + 社区指南。
🎯 可操作的结果 — 确切的风险短语、严重程度、置信度标签、违反政策的原因，以及合规的改写建议。
🤖 为代理而生 — 单个 MCP 工具，带有丰富的描述；您的代理会自动发现并调用它。
⚡ 30 秒设置 — npx，放入免费密钥，完成。适用于 Claude、Cursor、VS Code、Windsurf、Cline 以及任何 MCP 客户端。
🆓 免费套餐 — 每月 50 次检查，无需信用卡。
Related MCP server: banproof-mcp
AI 内容与广告文案工具：生成社交帖子、标题、推文、视频脚本或广告创意，需要在发布前进行审核/品牌安全检查。
代理工作流与自动运行系统（Claude、Cursor、自定义代理）：起草和安排内容，且不能导致账户受限。
营销与增长团队及代理机构：在多个平台投放付费广告，希望在广告被拒或账户被标记之前发现政策风险。
开发者：构建社交调度器、DTC 营销 SaaS、影响者工具或合规功能，希望通过 API/MCP 调用进行政策检查，而无需自行维护 8 个平台的规则手册。
该护栏结合了确定性模式规则与基于实时平台政策的 AI 推理。它会在以下类别中揭示风险：
健康、保健与补充剂 — 不切实际的减肥声明、“奇迹”/“治愈”用语、无法验证的“临床证明”背书。
金融与加密货币 — “保证回报”、“无风险”、“快速致富”、“零风险”、未经证实的回报数字。
误导性与未经证实的声明 — 最高级用语、虚假紧迫感、无法证实的隐含结果。
禁止与限制内容 — 平台不允许或需要限制的类别（受管制商品、敏感属性等）。
平台特定广告规则 — 那些会悄悄导致广告被拒或分发减少，而非直接禁止的规则。
每条发现都带有置信度标签（firm 与 possibly_risky），以便您的代理采取相应措施——修复确定的，审查边缘的。这些发现基于 AuditSocials 政策追踪器背后的实时政策引擎；它们绝非捏造，并在不确定时会加以说明。
获取免费 API 密钥 → https://www.auditsocials.com/compliance-api（每月 50 次检查，无需信用卡）。
将服务器添加到您的 MCP 客户端（配置如下），并将您的密钥设置为 AUDITSOCIALS_API_KEY。
询问您的代理：“在我发布之前检查一下：…”
{
"mcpServers": {
"auditsocials-compliance": {
"command": "npx",
"args": ["-y", "auditsocials-compliance-mcp"],
"env": { "AUDITSOCIALS_API_KEY": "as_live_..." }
}
}
}该服务器通过 stdio 使用 MCP 协议，因此可与任何兼容 MCP 的客户端配合使用。将配置粘贴到您的客户端中，并放入您的密钥。
Claude Desktop — claude_desktop_config.json → mcpServers（上述配置）。
Claude Code — claude mcp add 或您的 .mcp.json → mcpServers。
Cursor — 设置 → MCP → 添加服务器（相同的 mcpServers 结构）。
VS Code（GitHub Copilot / MCP） — 使用上述 command/args/env 添加到您的 MCP 配置。
Windsurf、Cline、Continue、Zed 及其他 MCP 客户端 — 将它们指向 npx -y auditsocials-compliance-mcp 命令，并在环境中设置 AUDITSOCIALS_API_KEY。
添加服务器后重启客户端，以便它发现该工具。
无需提示工程。您的代理会自动选择该工具。示例：
“在我发布之前，对照 TikTok 和 Meta 检查这段标题：'…'”
“为我的补充剂品牌写 3 条 Instagram 标题——每条先进行合规检查。”
“这段广告文案在 Meta 和 Google Ads 上安全吗？重写任何有风险的部分。”
“检查我的发布推文，对照所有 8 个平台，标记政策风险。”
check_social_content_compliance检查一段社交/广告内容是否符合 8 个平台的当前政策，并返回总体结论及具体发现。
参数 | 类型 | 说明 |
|
| 要检查的帖子/标题/推文/视频脚本/广告文案。最多 10,000 个字符。 |
|
| 可以是 |
|
| 有助于应用正确的规则集。 |
返回： 总体 verdict（例如 ok / needs_changes）、简短 summary 以及 findings 列表——每条包含 severity、confidence、匹配的短语、风险原因以及建议的合规改写。每次响应还会报告您剩余的月度额度。
输入——广告草稿：“快速致富！保证 500% 加密货币回报，零风险，立即投资。”
Verdict: NEEDS_CHANGES
4 potential issue(s) (2 firm) for LinkedIn. Review and apply the suggested fixes before publishing.
• [critical/firm] Guaranteed returns language (Finance & Crypto)
risky text: "Guaranteed"
why: Any language suggesting guaranteed investment outcomes ("guaranteed", "risk-free", "100% returns", …).
fix: Remove any guarantee of financial outcome; state that returns vary and capital is at risk.
• [high/firm] High-risk claim language (Finance & Crypto)
risky text: "Get rich quick"
fix: Rephrase to a hedged, substantiable statement and add any required disclaimer.
… + 2 more
— 49 of 50 credits left this month (free).一个额度 = 一次完整质量检查（确定性 + AI，全部 8 个平台）。按量收费，而非深度——每个套餐都返回完整结果。
套餐 | 每月检查次数 | 价格 |
免费 | 50 | $0 — 无需信用卡 |
入门 | 5,000 | $99 / 月 |
成长 | 25,000 | $299 / 月 |
规模 | 自定义 / OEM |
随时在 https://www.auditsocials.com/compliance-api/usage 或通过 GET /api/v1/credits 查看您的余额。
此包是一个轻量级开源客户端（约 160 行）。所有政策数据、AI 推理、配额和计量都位于服务端的托管 AuditSocials Compliance API 中——该包不包含任何密钥、规则、政策数据，仅通过 HTTPS 将您的内容与 API 密钥一起转发。这意味着随着平台政策变化，护栏能保持最新，而您无需发布更新。
your agent ──(MCP/stdio)──▶ auditsocials-compliance-mcp ──(HTTPS + your key)──▶ AuditSocials Compliance API ──▶ live 8‑platform policy engine什么是 AuditSocials Compliance MCP？ 一个 MCP 服务器，为 AI 助手提供一个单一工具，用于在发布前检查社交媒体/广告内容是否符合 8 个主要平台的当前政策，并返回具体风险和合规改写建议。
涵盖哪些平台？ Meta（Facebook 和 Instagram）、TikTok、LinkedIn、Google Ads、YouTube、X（Twitter）、Snapchat 和 Pinterest——广告和社区政策。
它能保证我的内容会被批准吗？ 不能。它是一个风险标记层，而非保证。平台审核不透明且不断变化；该工具会揭示已知的政策风险，并引用每条标记背后的规则，以便您自行决定。它明确不声称能预测或保证批准。
我需要 API 密钥吗？
是的——在 https://www.auditsocials.com/compliance-api 获取免费密钥（每月 50 次检查，无需信用卡）。将其设置为 AUDITSOCIALS_API_KEY。
哪些 MCP 客户端可用？ 任何支持 stdio 服务器的 MCP 客户端——Claude Desktop、Claude Code、Cursor、VS Code、Windsurf、Cline、Continue、Zed 等。
我的内容或密钥会被存储吗？ 该包通过 HTTPS 将您的内容和密钥发送到 API 以执行检查。它本身不存储任何密钥。请参阅隐私政策。
这与通用审核 API 有何不同？ 通用审核标记毒性/安全性。而此工具检查平台广告与社区政策——那些会导致广告被拒、账户受限或内容降权的规则——涵盖 8 个平台，并提供确切的政策原因和改写建议。
🔑 获取免费 API 密钥： https://www.auditsocials.com/compliance-api
📖 API + MCP 文档： https://www.auditsocials.com/compliance-api/mcp
📡 政策追踪器（背后的实时引擎）： https://www.auditsocials.com/policy-tracker
📦 npm： https://www.npmjs.com/package/auditsocials-compliance-mcp
关键词： MCP 服务器、模型上下文协议、AI 内容合规、社交媒体政策检查器、广告政策合规 API、发布前审核、品牌安全、Meta 广告政策、TikTok 社区指南、Google Ads 政策、LinkedIn 广告政策、YouTube 广告友好指南、X 广告政策、Snapchat 广告、Pinterest 广告、AI 代理合规护栏。
MIT · © AuditSocials
Check a piece of social media content (post, caption, tweet, video script, or ad copy) against the CURRENT advertising and community policies of 8 platforms — Meta, TikTok, LinkedIn, Google Ads, YouTube, X, Snapchat, Pinterest — BEFORE it is published. Call this whenever you draft or edit social/ad content so the post, account or ad is not flagged, demonetized, or banned. Returns specific policy risks (with the exact risky phrase, why it's risky, and a compliant rewrite) plus an overall verdict. Use it as a final compliance pass on anything you write for social media.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | The social content to check (post/caption/tweet/video script/ad copy). | |
| platforms | No | Target platforms. Omit to check against all 8. | |
| contentType | No | Type of content (helps apply the right rule set). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full responsibility. It describes output structure in detail (specific policy risks, phrase, reason, rewrite, verdict). However, it does not explicitly state the tool is read-only (no modifications), which is implied but could be clearer. Still, it offers strong behavioral insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the purpose, scope, and usage guidance. Every sentence adds value with no redundancy. Well-structured for agent consumption.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 simple parameters with full schema coverage and no output schema, the description fully covers what the tool does, when to use it, what input is expected, and what output to expect. It leaves no significant gaps for a pre-publication compliance check tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description text does not add new semantic value beyond what the schema already provides (e.g., platform list, content type, content). It restates but does not extend.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies a clear verb ('Check'), resource ('social media content'), scope (8 platforms, multiple content types), and purpose (pre-policy compliance). It distinguishes the tool as a final compliance pass, which is unambiguous even without sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'BEFORE it is published', 'whenever you draft or edit', 'as a final compliance pass'. Provides clear context and no ambiguity, even in the absence of sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1check_social_content_complianceScored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool's purpose is clearly defined.
There is only one tool, so no inconsistency exists. The name 'check_social_content_compliance' follows a clear verb_noun pattern and is descriptive.
A single tool for checking social content compliance is reasonable, as the tool is comprehensive in its description. While a few additional tools (e.g., batch checking) might be expected, the count is not inappropriate for a focused utility.
The tool covers the core task of checking text-based content against multiple platforms' policies, including risk identification and compliant rewrites. It lacks support for image/video compliance checks, but for a text-focused checker, it is largely complete.
Your AI drafts social posts for Instagram, TikTok, LinkedIn and 6 more. Yaybird checks every draft against your brand rules, and nothing goes live until a person approves it, in the chat or on a phone.
Schedule posts to 10 social platforms and check drafts against hook rules learned from your audience
Generate platform-native social posts that are humanized, AI-detection scored and illustrated.
Draft posts in your own voice from saved business context and check every draft before you post.
