AuditSocials Glossary MCP
OfficialAuditSocials Glossary MCP — 212 терминов рекламы и политик платформ для ИИ
Сервер Model Context Protocol (MCP), предоставляющий AI-ассистентам авторитетный глоссарий терминов рекламы в социальных сетях и политик платформ с открытой лицензией — 212 терминов (CC BY 4.0), охватывающих политику платформ, правовые и нормативные рамки (DSA, GDPR, FTC), метрики рекламных технологий, стандарты контента и креативов, конфиденциальность и данные, отраслевые правила, а также правоприменение и риски.
Позвольте AI-ассистентам точно определять и искать термины соблюдения рекламных норм с указанием источника и постоянным URI в каждом ответе — вместо выдумывания определений для регуляторного и платформенного жаргона.
📚 212 тщательно отобранных терминов по 8 категориям — политика платформ, правовые/регуляторные, рекламные технологии, стандарты контента, конфиденциальность, отраслевые правила, правоприменение и риски.
🔗 Цитируемые и постоянные — каждое определение содержит URL источника и стабильный URI
w3id.org; набор данных имеет DOI Zenodo.🆓 Без API-ключа, без настройки — глоссарий встроен и доступен только для чтения; просто
npx.🤖 Основа для RAG и агентов — уменьшение галлюцинаций по терминологии DSA/GDPR/FTC и политик платформ.
Область применения: только глоссарий. Трекер политик AuditSocials, аналитика правоприменения и сканер не предоставляются через этот сервер. Для оперативных проверок политик перед публикацией см. сопутствующий AuditSocials Compliance MCP.
Инструменты
Инструмент | Описание |
| Определяет термин по имени или slug. Возвращает полное определение, категорию, применимые платформы, связанные термины и постоянный URI. |
| Поиск по ключевому слову и/или категории. Возвращает соответствующие термины с краткими определениями. |
| Список категорий глоссария с количеством терминов. |
Related MCP server: ProductBrain
Быстрый старт
npx -y auditsocials-mcpНе требуется ни API-ключ, ни настройка — глоссарий из 212 терминов встроен.
Настройка клиента
Общается по MCP через stdio, поэтому работает с любым MCP-совместимым клиентом.
Claude Desktop / Claude Code — добавьте в mcpServers:
{
"mcpServers": {
"auditsocials-glossary": {
"command": "npx",
"args": ["-y", "auditsocials-mcp"]
}
}
}Cursor, VS Code, Windsurf, Cline, Continue, Zed и другие MCP-клиенты — укажите им команду npx -y auditsocials-mcp (переменные окружения не нужны).
Использование — просто спросите своего ассистента
"Определите блокировку аккаунта, используя глоссарий AuditSocials."
"Найдите в глоссарии AuditSocials термины DSA."
"Какие категории есть в глоссарии соблюдения рекламных норм AuditSocials?"
"Определите теневой бан и перечислите связанные термины."
Каждый ответ включает определение, категорию, применимые платформы, связанные термины, URL источника и постоянный URI — чтобы ваш ассистент цитировал, а не угадывал.
Что внутри
212 терминов, охватывающих:
Политика платформ — концепции рекламы и правил сообщества на Meta, TikTok, LinkedIn, Google Ads, YouTube, X, Snapchat, Pinterest.
Правовые и регуляторные — DSA, GDPR, FTC, COPPA и связанные рамки.
Рекламные технологии и метрики — терминология доставки, атрибуции и измерения.
Стандарты контента и креативов, конфиденциальность и данные, отраслевые правила и правоприменение и риски (блокировки, апелляции, демонетизация, теневое ограничение).
Данные, происхождение и лицензия
Архивированный набор данных (DOI): https://doi.org/10.5281/zenodo.20458599
Постоянные URI:
https://w3id.org/auditsocials/glossary/{term}Лицензия: CC BY 4.0 — бесплатно для использования с указанием авторства.
Курируется AuditSocials — сервисом аналитики политик платформ, который отслеживает изменения политик, действия регуляторов и решения о правоприменении на восьми социальных платформах.
Часто задаваемые вопросы
Что такое AuditSocials Glossary MCP? Сервер MCP, позволяющий AI-ассистентам определять и искать 212 терминов рекламы в социальных сетях и политик платформ с открытой лицензией, с указанием источника в каждом ответе.
Нужен ли мне API-ключ?
Нет. Глоссарий встроен и доступен только для чтения — просто запустите npx -y auditsocials-mcp.
Зачем использовать его вместо прямого запроса к модели? Регуляторная терминология и терминология политик платформ (DSA, GDPR, FTC, демонетизация, теневые баны) легко может быть неверно истолкована. Это решение обосновывает ответы на курируемом, цитируемом наборе данных с постоянными URI — идеально для RAG и агентов.
Могу ли я использовать определения в своем продукте? Да, по лицензии CC BY 4.0 с указанием авторства AuditSocials (ссылка на URL источника или DOI).
Какие MCP-клиенты работают? Любой stdio MCP-клиент — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Cline, Continue, Zed и другие.
Ссылки
📖 Глоссарий (веб): https://www.auditsocials.com/knowledge/glossary
🧭 DOI набора данных (Zenodo): https://doi.org/10.5281/zenodo.20458599
🛡️ Сопутствующий — оперативная проверка политик перед публикацией: https://www.npmjs.com/package/auditsocials-compliance-mcp
Разработка
npm install
npm run export-glossary # regenerate the bundled snapshot from source data
npm run build # compile to dist/Keywords: MCP server, Model Context Protocol, advertising compliance glossary, platform policy terminology, DSA glossary, GDPR terms, FTC advertising, social media policy definitions, content moderation glossary, regtech, ad‑tech glossary, CC BY 4.0 dataset, RAG grounding, AI definitions.
Лицензия
Содержимое: CC BY 4.0 · © AuditSocials
Available Tools
3 toolsglossary_defineA
Define a social media advertising / platform-policy compliance term from the AuditSocials Compliance Glossary. Accepts a term name or slug (e.g. 'account suspension' or 'account-suspension'). Returns the full definition, category, applicable platforms, and related terms.
| Name | Required | Description | Default |
|---|---|---|---|
| term | Yes | The term name or slug to define |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It clearly implies a read-only lookup (returns a definition) with no side effects. The description does not mention errors, auth, or rate limits, but for a simple glossary lookup, the behavioral traits are sufficiently transparent.
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?
The description is two sentences long, front-loaded with the core purpose, and contains no extraneous information. Every sentence adds value, making it highly efficient.
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 the tool's simplicity (single parameter, no output schema, no annotations), the description fully covers the necessary context: what it does, what input it expects with examples, and what the output contains. No important aspect is missing for a glossary lookup 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?
The schema already describes the parameter ('The term name or slug to define') with 100% coverage. The description adds concrete examples ('account suspension' or 'account-suspension'), which aids the agent in formatting input correctly. This improves upon the baseline of 3.
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 clearly states the tool's action ('Define a term'), specifies the domain ('AuditSocials Compliance Glossary'), and provides examples of input format. It is distinct from sibling tools glossary_search (which likely searches) and glossary_list_categories (which lists categories), making the purpose unambiguous.
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?
The description explains what the tool returns (definition, category, platforms, related terms), which helps an agent decide when to use it. However, it does not explicitly contrast with sibling tools or provide when-not-to-use guidance, leaving the decision partially implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glossary_list_categoriesA
List the AuditSocials Compliance Glossary categories with the number of terms in each. Useful to understand the scope of the vocabulary.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It correctly indicates a read-only operation (listing with counts) and adds context about grouping by category. The behavior is transparent and appropriate, though no details on potential pagination or output format are given.
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?
The description is two sentences with no wasted words. It front-loads the core action and then explains utility, perfect for quick agent parsing.
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 no parameters, no output schema, and simple sibling context, the description is sufficiently complete. It explains the output (categories with counts) and its usefulness. Minor gap: no mention of sorting or hierarchical structure if applicable.
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?
The tool has zero parameters, so the description need not add parameter details. It compensates by explaining what information is returned (categories with term counts), adding meaning beyond the empty schema.
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 clearly states the tool lists glossary categories with term counts, using specific verbs ('list') and resources ('categories'). It distinguishes itself from siblings like glossary_define and glossary_search by highlighting the purpose of understanding vocabulary scope.
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?
The description implies usage by noting it's useful for understanding vocabulary scope, but provides no explicit guidance on when to use this versus siblings. It lacks exclusions or context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glossary_searchA
Search the AuditSocials Compliance Glossary by keyword and/or category. Returns matching terms with their short definitions. Use this to discover terms before calling glossary_define.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 10) | |
| query | Yes | Keyword to match against term names and definitions | |
| category | No | Optional category filter: Platform Policy, Legal & Regulatory, Ad Tech & Metrics, Content & Creative, Privacy & Data, Industry-Specific, Enforcement & Risk |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosure. It states that the tool returns 'matching terms with their short definitions,' indicating a read-only search. It does not mention potential errors, pagination, or authentication needs, but for a simple search tool this is adequate.
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?
The description is extremely concise with two sentences: the first clearly states the action and result, the second provides usage guidance. Every word adds value with no redundancy or filler.
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?
For a search tool with 3 well-documented parameters and an implied list return, the description adequately covers the basics. It explains the output and provides workflow context. It could briefly mention that results are a list of terms, but given the schema covers parameters, this is not a significant gap.
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 coverage is 100% with all parameters already described in the schema. The description mentions 'keyword and/or category' but adds no new semantic details beyond what the schema provides, so a baseline score of 3 is appropriate.
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 clearly states the tool's function: searching the glossary by keyword and/or category and returning matching terms with definitions. It distinguishes itself from the sibling 'glossary_define' by noting this tool is for discovery before calling the define tool.
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?
The description explicitly tells when to use this tool: 'Use this to discover terms before calling glossary_define.' This provides clear guidance on the workflow, though it does not discuss when not to use it or mention the other sibling 'glossary_list_categories'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
v0.1.0- First observed
glossary_define - First observed
glossary_list_categories - First observed
glossary_search
TDQS
Scored across 3 tools
Each tool has a clearly distinct and non-overlapping purpose: define a specific term, search by keyword, and list categories. There is no ambiguity about which tool to use for a given task.
All tools follow the consistent pattern 'glossary_<verb>_<noun>' (glossary_define, glossary_search, glossary_list_categories). The naming is predictable and clearly conveys the action and resource.
Three tools is a reasonable number for a focused glossary server. It covers the core operations without being too sparse, though a few more tools (e.g., list all terms) could be added without causing bloat.
The tool surface covers the essential workflows: discovering terms (search and categories) and retrieving detailed definitions. A minor gap is the lack of a tool to list all terms directly, but the search and category tools adequately enable discovery.
Maintenance
Related MCP Connectors
GrowthVector's free marketing knowledge base for AI assistants: search SEO, GEO (AI search), paid ads, email, and affiliate marketing guides, read full pages, look up glossary terms, and get ready-made prompts. GrowthVector (growthvector.io) is a free library of practical marketing guides and tools for small businesses.
Real-time Meta, Google, LinkedIn and TikTok ad library access for AI assistants. No API keys.
AI laws from 110+ countries, enforcement actions and a 3,900-term glossary. Free, no API key.
60+ Meta Ads tools for AI agents: audits, campaign management, audiences and CAPI tracking.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI-powered access to authoritative design systems knowledge, including W3C standards, WCAG guidelines, and best practices from 188+ curated entries via semantic vector search.7 npm219MIT
- FlicenseNot gradedqualityDmaintenanceConnects AI assistants to a team's product knowledge base, enabling search, capture, and navigation of glossary terms, business rules, decisions, and relations via MCP.40,277 npm-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to browse and query Facebook Ads data including ad accounts, campaigns, ad sets, and performance insights via natural language.10 npmMIT
- FlicenseNot gradedqualityBmaintenanceProvides a curated technical glossary with search, lookup, and category listing tools, enabling AI assistants to answer tech concept questions via MCP.-