MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Content moderation with prompt injection detection, toxicity scoring, and PII redaction
npm MIT -
@vettly/mcpgithub.com/nextauralabs/vettly-docsupdated this year
MCP server for content moderation with Claude and Cursor. Content moderation policy testing.
npm MIT -
@sfwapi/mcpactive
MCP server for the SFW API: nudity detection and image moderation tools (analyze_url, analyze_file) for Claude, Cursor, VS Code and other MCP clients
npm MIT -
MCP server that lets Claude help blast.hk moderators review the approval queue
MIT -
Discord server management MCP for AI agents: chat, moderation, admin, and full server building. Formerly Omnicord.
npm Apache-2.0 -
MCP server exposing the full Discord API to LLM agents — rich messages, interactions, threads, moderation, AutoMod and server config on discord.js.
npm MIT -
MCP server that lets AI agents run a Discord bot: messages, DMs, channels, threads, roles, members, moderation, live events and bulk operations.
npm MIT -
Uncensored Seedance 2 API wrapper (Python): relaxed-moderation ByteDance video generator via MuAPI. Text-to-Video, Image-to-Video, Omni Reference.
MIT ★ 2 -
Uncensored Wan 3.0 API wrapper (Python): relaxed-moderation Alibaba video generator via MuAPI with synchronized audio and high motion.
MIT ★ 4 -
mcpgithub.com/Tuteliq/mcpactive
MCP server with 41 AI-powered tools for child safety, fraud detection, and content moderation. Detects bullying, grooming, sextortion, romance scams, social engineering, and more. For Claude, Cursor, and MCP-compatible AI assistants.
npm MIT ★ 3 -
Run a Discord server from an AI assistant — 30+ actions across messages, channels, roles, members, moderation, threads, webhooks, invites and the audit log, behind one hierarchical MCP tool with tiered discovery.
MIT ★ 1 -
MCP server for Tuteliq — 87 tools for child safety, fraud detection, synthetic content forensics, identity verification, grooming, bullying, sextortion, document analysis, and content moderation. Interactive UI widgets for Claude, Cursor, and MCP-compatib
npm MIT -
Trust and safety MCP server for AI agents. Detect grooming, bullying, self-harm, CSAM, fraud and deepfakes across text, voice, image and video, then triage a moderation queue and produce KOSA, DSA and GDPR evidence. Around 80 tools plus workflow skills for Claude Code and Cowork. OAuth sign-in, no API key to configure.
MIT -
A MCP for querying MyAnonamouse.net . This code is moderately complete, future versions will likely only refine.
MIT ★ 3 -
MCP server that gives Claude, Cursor and other MCP clients access to OpenAI text, image, speech, transcription, embeddings and moderation
npm MIT -
Frank AI Researcher: a remote MCP server for AI-moderated customer interviews, studies, and transcripts.
MIT -
Discord bot bridge via FastMCP — guilds, messages, moderation, RAG search, agentic workflow. Local web dashboard. For Cursor / Claude Desktop.
MIT ★ 2 -
facebook-mcp-servergithub.com/NachaFromMars/facebook-mcp-serverupdated this year
Facebook Page management MCP server via Graph API. Tools: create posts, moderate comments, fetch insights, filter negative feedback. Requires Graph API token with Page permissions.
MIT ★ 1 -
Public message board for AI agents. One GET publishes. Humans read, agents write; the code, the moderation log and the dataset are all open.
Apache-2.0 ★ 2 -
Omnicord: a Discord server management MCP for AI agents. Chat, moderate, administrate, and build out entire servers from one brief, through any MCP client.
npm Elastic-2.0 -
MCP server that gives Claude, Cursor and other MCP clients access to OpenAI text, image, speech, transcription, embeddings and moderation
npm MIT -
MCP server that lets AI agents run a Discord bot: messages, DMs, channels, threads, roles, members, moderation, live events and bulk operations.
npm MIT ★ 4 -
Discord server management MCP for AI agents: chat, moderation, admin, and full server building. 160+ tools, confirmations the model cannot answer, undo. Formerly Omnicord.
npm Apache-2.0 ★ 12 -
MCP server for Blogger: draft, edit, publish and schedule posts, manage pages and moderate comments from Claude or any MCP client. Includes an Agent Skill.
MIT -
Facebook MCP server for Claude Code and AI agents. Posting, scheduling, drafts, Page and post insights, and comment moderation through Meta's official Graph API.
MIT ★ 3 -
Facebook MCP server for Claude Code and AI agents. Post to your Pages, schedule and draft, read insights, and moderate comments through Meta's official Graph API.
npm MIT -
x402-tools-mcpgithub.com/mizukaizen/x402-tools-mcpupdated this year
22 x402 pay-per-call utility tools for AI agents — scrape, validate, embed, store, moderate, notify, convert, prevent loops. No accounts, no API keys. USDC on Base via the x402 protocol.
npm ★ 1 -
Uncensored Seedance 2.5 API wrapper (Python): relaxed-moderation ByteDance video generator via MuAPI. Native 4K, 30s clips, Omni Reference, Video Edit/Extend, Motion Control.
MIT ★ 6 -
Discord MCP server for Claude, Cursor and VS Code: read and send messages, moderate members, manage roles, channels, forums, webhooks and events. Toolset profiles, guild allow-list, dry-run for mass actions.
npm MIT -
Discord MCP server for Claude, Codex, Cursor, VS Code and other MCP clients: read and send messages, moderate members, manage roles, channels, forums, webhooks and events. Toolset profiles, guild allow-list, dry-run for mass actions.
npm MIT ★ 34 -
@melis-ai/x402-tools-mcpgithub.com/mizukaizen/x402-tools-mcpupdated this year
22 x402 pay-per-call utility tools for AI agents — scrape, validate, embed, store, moderate, notify, convert, prevent loops. No accounts, no API keys. USDC on Base via the x402 protocol.
npm MIT -
mcp-telegramgithub.com/beautyfree/mcp-telegramupdated this year
Telegram MCP server (MTProto). Connect Claude, Codex, Cursor, Claude Code, VS Code, Cline, Windsurf, and other MCP clients to a real Telegram user account: read dialogs, search messages globally, send/edit/forward, react/poll, moderate channels, tag Saved
npm MIT -
Shared workspace where humans and AI agents across harnesses (Codex, Claude, Gemini, Pi, and more) hold live conversations - every delivery visible, fence-gated, and human-moderated, with a durable audit of what ran. One Rust binary: hub + node, mTLS everywhere.
Apache-2.0 ★ 1 -
Self-hosted MCP server on Cloudflare Workers that lets an AI assistant read and post on Discord as your own bot: forum posts with tags and images, messages, replies and edits. No delete or moderation tools, no pings, optional server/channel allow-list.
MIT -
mcp-telegramgithub.com/beautyfree/mcp-telegramupdated this year
Telegram MCP server (MTProto). Connect Claude, Cursor, Claude Code, VS Code, Codex, Cline, Windsurf to a real Telegram account — read/search/send messages, moderate channels, manage stories/contacts/folders, transcribe voice, and call any raw MTProto method. Browser-based sign-in. 100+ tools.
npm MIT ★ 34 -
Telegram AI CLI MCPgithub.com/stufently/telegram-ai-cli-mcpno update data
A CLI and MCP server, built from one Python codebase, for a personal Telegram account over MTProto (not the Bot API). Before the first start, sign in from a terminal with tg-ai account login; the server has no login flow of its own and will not work until that is done. Read tools cover chats, inbox, message search, who a username belongs to, group members, folders, drafts, scheduled messages, mentions, sessions and a waiting watch; an optional local archive answers searches offline. Anything that changes Telegram (sending, replying, joining, deleting, moderation) is a typed plan tool, available only under the plan profile: it records the intention, and a person applies it with tg-ai plan apply. No tool applies a plan, and reading never marks a chat read. Direct messages stay closed until allowlisted. Telegram may limit accounts it judges to be running abusive automation; use on your own account is at your own risk.
smithery -
Official Python, TypeScript, and MCP-server clients for the SentiSift API.
MIT ★ 1 -
Least-privilege Discord MCP for privacy-safe reads, audits, and reviewed administration
npm AGPL-3.0-only -
内容合规审核 MCP Server:零依赖本地违禁词检测,8平台独立词库(小红书/抖音/视频号/快手/B站/公众号/闲鱼/通用),P0/P1 分级 + 修改建议,无网络请求无 API Key
-
MCP server for Sparkient decision intelligence — 15 tools for creating, training, running, and inspecting task-specific decision models
MIT -
中文敏感词/违禁词检测 MCP Server | 支持小红书/抖音/快手/B站 | 风险分级+安全替换建议 | 微信: chenganp | 邮箱: [email protected]
npm MIT ★ 105 -
Search and administer Discord through MCP, with explicit access scopes and reviewed changes.
npm AGPL-3.0 ★ 1 -
English profanity filter API + MCP server: find and censor swear words, including obfuscated spellings. Word list, not AI.
MIT -
originality-mcpgithub.com/Eyalm321/originality-mcpupdated this year
MCP server for Originality.ai — AI detection, plagiarism, fact checking, readability, grammar, and SEO optimization
npm ★ 2 -
MCP Server for Chinese sensitive/prohibited word detection. Supports Xiaohongshu, Douyin, Kuaishou, Bilibili. 中文敏感词违禁词检测 MCP 服务,支持小红书、抖音、快手、B站。
npm MIT -
MCP server that gives AI agents typed decisions instead of prose: classify, route, score, and flag with calibrated probabilities. npx -y openjev-mcp
npm MIT ★ 1 -
Human review for AI output: reviewers check model output against policy, with decisions on a hash chain. HTTP, MCP and webhooks. Apache 2.0, free to self-host.
Apache-2.0 ★ 6 -
HeartFlow (心虫) — AGI Layer 1: the Discriminator. Rule-based engine that checks what AI says before it reaches humans. 46 discrimination dimensions, 9-layer pipeline, 137 modules (logic/decision/cognition/emotion/memory/ethics/collaboration), 179 MCP tools
npm MIT