AuditSocials Glossary

io.github.eminegurcuPublished by GitHub account eminegurcuv0.1.1Updated Oct 24, 2026

Define & search 212 advertising & platform-policy terms (DSA, GDPR, FTC). CC BY 4.0.

The publisher's own server: Socials Homes

VerifiedSTDIODesktop onlyKnowledge & MemoryBusiness & Commerce

Overview

AI-generated overview

A local stdio MCP server that lets an assistant define and search a bundled 212-term glossary of social media advertising and platform-policy terminology.

What you can do
  • Look up a term by name or slug and get its full definition, category, applicable platforms, related terms and persistent URI
  • Search the glossary by keyword and/or category and get matching terms with short definitions
  • List glossary categories with term counts
  • Ground answers on DSA, GDPR, FTC, ad-tech metrics, content standards, privacy and enforcement terminology with source attribution
When to use it
Useful when an assistant needs accurate, citable definitions of advertising-compliance and platform-policy jargon (DSA, GDPR, FTC, shadow bans, demonetization) instead of guessing. It is a read-only reference, not a live policy checker.
Requirements
Runs as a local process over stdio, started with npx, so Node.js and network access for the first package download are needed. No API key, environment variables or configuration required; the glossary is bundled.
Before you install
Read-only glossary with no credentials or write actions. Scope is limited to definitions: the vendor's policy tracker, enforcement intelligence and scanner are not exposed. Reusing definitions in your own product requires attribution under CC BY 4.0.

Installation

In SourceWeft

  1. Open AuditSocials Glossary in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AuditSocials Glossary MCP — 212 Advertising & Platform‑Policy Terms for AI

[npm version] [npm downloads] [license: CC BY 4.0] [DOI] [MCP]

A Model Context Protocol (MCP) server that gives AI assistants an authoritative, openly‑licensed glossary of social media advertising & platform‑policy terminology — 212 terms (CC BY 4.0) covering platform policy, legal & regulatory frameworks (DSA, GDPR, FTC), ad‑tech metrics, content & creative standards, privacy & data, industry‑specific rules, and enforcement & risk.

Let AI assistants define and search advertising‑compliance terms accurately, with source attribution and a persistent URI on every response — instead of hallucinating definitions for regulatory and platform‑policy jargon.

  • 📚 212 curated terms across 8 categories — platform policy, legal/regulatory, ad‑tech, content standards, privacy, industry rules, enforcement & risk.
  • 🔗 Cited & persistent — every definition carries a source URL and a stable w3id.org URI; the dataset has a Zenodo DOI.
  • 🆓 No API key, no config — the glossary is bundled and read‑only; just npx.
  • 🤖 Grounding for RAG & agents — reduce hallucination on DSA/GDPR/FTC and platform‑policy terminology.

Scope: glossary only. The AuditSocials policy tracker, enforcement intelligence and scanner are not exposed through this server. For live pre‑publish policy checks, see the companion AuditSocials Compliance MCP.


Tools

ToolDescription
glossary_defineDefine a term by name or slug. Returns the full definition, category, applicable platforms, related terms and persistent URI.
glossary_searchSearch by keyword and/or category. Returns matching terms with short definitions.
glossary_list_categoriesList glossary categories with term counts.

Quickstart

bash
npx -y auditsocials-mcp

No API key and no configuration required — the 212‑term glossary is bundled.

Client setup

Speaks MCP over stdio, so it works with any MCP‑compatible client.

Claude Desktop / Claude Code — add to mcpServers:

json
{  "mcpServers": {    "auditsocials-glossary": {      "command": "npx",      "args": ["-y", "auditsocials-mcp"]    }  }}

Cursor, VS Code, Windsurf, Cline, Continue, Zed and other MCP clients — point them at the npx -y auditsocials-mcp command (no env needed).

Usage — just ask your assistant

  • "Define account suspension using the AuditSocials glossary."
  • "Search the AuditSocials glossary for DSA terms."
  • "What categories are in the AuditSocials advertising‑compliance glossary?"
  • "Define shadow ban and list related terms."

Each answer includes the definition, category, applicable platforms, related terms, a source URL and a persistent URI — so your assistant cites rather than guesses.

What's inside

212 terms spanning:

  • Platform policy — advertising & community‑guideline concepts across Meta, TikTok, LinkedIn, Google Ads, YouTube, X, Snapchat, Pinterest.
  • Legal & regulatory — DSA, GDPR, FTC, COPPA, and related frameworks.
  • Ad‑tech & metrics — delivery, attribution, and measurement terminology.
  • Content & creative standards, privacy & data, industry‑specific rules, and enforcement & risk (bans, appeals, demonetization, shadow‑limiting).

Data, provenance & license

Curated by AuditSocials, a platform policy intelligence service that monitors policy changes, regulator actions and enforcement decisions across eight social platforms.

FAQ

What is the AuditSocials Glossary MCP? An MCP server that lets AI assistants define and search 212 openly‑licensed social‑media advertising and platform‑policy terms, with source attribution on every response.

Do I need an API key? No. The glossary is bundled and read‑only — just run npx -y auditsocials-mcp.

Why use it instead of asking the model directly? Regulatory and platform‑policy terminology (DSA, GDPR, FTC, demonetization, shadow bans) is easy to get subtly wrong. This grounds answers in a curated, cited dataset with persistent URIs — ideal for RAG and agents.

Can I use the definitions in my own product? Yes, under CC BY 4.0 with attribution to AuditSocials (link the source URL or DOI).

Which MCP clients work? Any stdio MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Cline, Continue, Zed and others.

Links

Development

bash
npm installnpm run export-glossary   # regenerate the bundled snapshot from source datanpm 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.

License

Content: CC BY 4.0 · © AuditSocials

Source: README.md at commit 6cc31af

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Socials integrations