MCP servers and skills: search, filter by where they run, and compare.
MCP Server for send text/markdown message via dingding (aka dingtalk) group custom robot
Node.jsMIT★ 12No key
MCPLink onlyFew stars
A job search where every document line cites a fact you can check; nothing is sent for you.
Hosted by authorNo licenseFew starsNo key
Shared room so a human's AI agents meet over MCP: rooms, lounge, files, knowledge.
Hosted by authorNo licenseFew starsNo key
Official BotSpot hosted MCP connector: LumiBot strategy files, historical backtests, results and bot monitoring. OAuth sign-in; paid BotSpot plan required.
MCPLink onlyFew stars
Use this skill when a user needs a screenshot, website thumbnail, full-page capture, or PDF of a public HTTP(S) webpage saved as a local artifact through Latchshot, including report, QA, archive, and
in the skill textpages, raw HTML, scraping or extraction, arbitrary browser actions, CAPTCHA or anti-bot bypass, or local-file capture. # Latchshot page capture Use the bundled dependency-free
OfficialSkillMIT★ 40k in collectionNo key
面向 AI agent 的通用学术论文阅读 Skill，适配实验、理论、方法、综述及观点文章。采用四问题框架与三种阅读深度，支持段落、公式和图表精读，交付可下载 Markdown 笔记并在对话中完整展示正文，兼容 Obsidian。
SkillMIT★ 29No key
If the user's intent is not already clear, ask the questions one at a time, use the coding harness's prompt tools when available, and do not guess.
in the skill textwith `eve add channel/slack`. Credentials run through **Vercel Connect**, which provisions the bot token and verifies inbound webhooks, so there is no `SLACK_BOT_TOKEN
OfficialCommandApache-2.0★ 5.6k in collectionNo key
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and people every session. 45 commands: hybrid sem
in the skill textYour vault is the memory. Claude, Grok Bot, Codex - same brain. Your vault outlives whichever CLI you switch to. obsidian-second-brain: AI second brain for
SkillMIT★ 4.8kNo key
Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.
PythonApache-2.0★ 122No key
Markdown-Native Multi-Agent Task Coordination
in the skill textHistory is built in. ## ✨ Features - 🤖 **AI-Native**: MCP server for seamless bot integration - 📝 **Human-Readable**: Plain Markdown with YAML frontmatter - 🔄 **Git-Backed**: Full version control and
SkillMIT★ 32No key
Talk, and a team of bots does the work in a real browser, a shell and your files while she keeps talking. Open source, runs on your machine, on your ChatGPT plan or an OpenAI key. npx thursday-agent
in the readmedead call. So anything slower than a few seconds goes to a bot, and she keeps talking — interrupt her, change the subject, or ask how the
Node.jsMIT★ 49No key
Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat articles, web pages, YouTube, PDF, Markdown, search queries → Podcast/PPT/MindMap/Quiz etc.
in the readme绕过策略（6 层级联） ``` Level 1: 代理服务（r.jina.ai / defuddle.md） ↓ 失败 Level 2: 站点专属 Bot UA（Googlebot ~50站 / Bingbot ~4站） ↓ 失败 Level 3: 通用绕过（UA伪装 + X-Forwarded-For
SkillMIT★ 6.2kNo key
AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.
in the readmereplies** — tables, checklists, collapsible blocks and formulas render natively in Telegram via Bot API 10.1 rich messages; plain formatting keeps its proven path, with a graceful
Node.jsMIT★ 237No key
Web fetch, search, and crawl for AI agents. Built from scratch in Rust. No keys, no accounts. AGPL v3.
in the readmerevalidation (304), persistent cookies, connection pooling, TCP Fast Open. The loudest remaining bot tell, and nobody else fakes it. | | 👻 **Solve-and-bounce** | The browser solves the
SkillAGPL-3.0★ 818No key
Drop-in replacement for the official fetch MCP: clean, LLM-ready Markdown from any URL. JS rendering, anti-bot, honest errors, SSRF-safe. Zero-config, $0.
Node.jsMITFew starsNo key
A local emulator for enterprise SaaS APIs — Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and more — with the real response shapes, pagination, auth and per-document ACLs, over a corpus you sup
in the readmethe real Slack API: create a workspace, register an app, add a bot user, pick OAuth scopes, register a redirect URL, install to the workspace — then
PythonMIT★ 290No key
AI-native web scraper. Single binary with a bundled Claude Code skill. MIT-licensed alternative to Firecrawl.
in the readmearticles"*) to `webreaper` automatically. ## Table of contents - Why WebReaper - Quick start - Bot protection that just works - Power your agent - AI features - Use cases - Packages - Compared
SkillMIT★ 150No key
Record meetings and dictation on your Mac. Everything becomes plain Markdown files that Claude, Codex, or any AI can search. Free, open source, 100% local transcription.
in the readmeTranscripted Private meeting notes that never leave your Mac. No bot joins your call. Transcripted is a free, open-source Mac app for meeting notes and
SkillMIT★ 77No key
EMET is an MCP memory server built for ISO 9001 / ISO 13485 document control: persistent, shared memory for AI agents and bot teams. Nothing is deleted; records are superseded, retired and retained. C
Node.jsMIT★ 1Few starsNeeds a key
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Ma
PythonMIT★ 48No key
SoundCloud for AI agents — skill files for the first music and podcast platform built for autonomous bots
in the readmepoint your agent directly to the skill:** ``` ``` ## Quick Start **1. Register your bot** ```bash curl -X POST \ -H "Content-Type: application/json" \ -d '{"handle": "my_bot", "display
Hosted by authorMIT★ 3Few starsNo key
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth, passkeys, anti-bot reach, on-by-default prompt-injection defen
SkillMIT★ 16No key
Unified Python library for web scraping — single URL or whole-site → markdown, with stealth, JS rendering, and LLM-ready output
in the readmemarkdown. One async Python interface over 39 URL engines — with automatic anti-bot escalation and LLM-ready output. Search delegates to Enrichfold. 39 URL engines
PythonMIT★ 4Few starsNo key
Turn topics, links, and files into AI-generated research notebooks — summarize, explore, and ask anything.
in the readmecountless sources manually - **Geo-restrictions**: Unable to access content from different regions - **Bot Detection**: Getting blocked when trying to scrape valuable data - **Synthesis Challenges**: Difficulty connecting
SkillMIT★ 152No key
MCP server that fetches URLs through real Chromium and returns clean Markdown
in the readmeHTTP, which fails on JS-required pages and gets blocked by Cloudflare bot detection on many sites; or - use a real browser but return raw HTML
PythonMITFew starsNo key
MCP server for AI agents to read any web page in full — past the robots.txt and bot blocks that stop native fetch — as clean, ad-stripped Markdown. Plus web search.
Node.jsApache-2.0Few starsNo key
The focused-crawling MCP server for AI agents. Rank a whole site by your topic, read any page as clean Markdown, extract anything
in the readmeendpoint**: - **Agent skill**: - **Latest release**: **1.4.0** — clearer errors when a site's bot protection (Cloudflare, DataDome, …) blocks a fetch ( changelog ) ## Why focused crawling? Most crawlers visit
PythonMIT★ 12No key
Telegram channel scraper for public channels, no login: posts, views, reactions, Telegram media links, every album item, file names and sizes, links and inline buttons. Apify actor, $0.30 per 1,000 po
in the readmeUTC, views, the author signature, whether it was edited, and "via @bot" when a bot posted it. - **Media, as Telegram's own links.** Photos, videos, GIFs
Hosted by authorMIT★ 1Few starsNo key
Self-hosted AI execution agent for Discord: runs shell commands and edits files on your hosts, drives browsers, schedules jobs and delegates to sub-agents, within per-user host access, a command gover
in the readmeroutes, and tool loop | ## Odin Desktop Prefer an app to a Discord bot? ** Odin Desktop ** is Odin as a desktop app for Linux and Windows
PythonMIT★ 3Few starsNo key
Agent Skill — WeCom local-decrypt reading plus WecomTeam CLI/Bot operations for chat search, media/file discovery, todos, and online documents/sheets.
in the readmeand other supported online APIs | Partially available, permission-dependent | | Realtime interaction | WecomTeam Bot SDK WebSocket receive/reply path | Planned | The legacy self-built app HTTP API
SkillMIT★ 12No key
Fast, idiomatic Go MCP server for web search, image search, and page scraping to Markdown. Runs locally, no API keys, free.
in the readmereadability extractor before converting it to Markdown. To stay reliable against bot protection it impersonates real browsers at the TLS level and can rotate both browser
SkillMIT★ 15No key
Single-file, zero-dependency MCP server giving Claude, Cursor and any MCP client live web access.
in the readmesolved (`blockClass: "captcha"`). | | `seo_audit` | Fetch a URL as a no-JS bot **and** fully rendered, return both SEO views + the diff (JS-only content, changed
Node.jsMITFew starsNo key
Xiaohongshu (RedNote) & Douyin links to text for AI agents: image-note OCR, transcripts + on-screen text, viral breakdown with verbatim-checked quotes. Hosted MCP + API, Python SDK/CLI. | 给 AI Agent 用
in the readmeand a checked quote behind each key point. Works from Muse, Grok Bot, Manus Cue, Hermes, OpenClaw, Claude Code and Cursor: see linkdigest.dev/connect . No key
PythonMIT★ 2Few starsNo key
BGI tries to group code based on what the code actually does (its behavior), not just which file imports what.
in the readmeMCP server ](  server that lets AI agents
Node.jsMIT★ 5Needs a key
Tiny CLI and MCP server: fetch an URL -- return clean markdown. Built for AI agents.
in the readmethan you'd like. `markfetch` sends **a coherent Chrome header set** so bot-detection systems see a real browser, then runs the response through the **same
Node.jsMIT★ 3Few starsNo key
Remote MCP server (zero install, Streamable HTTP) for the Spazio Genesi digital-work attestation service - hash-based, no file ever transits
in the readmefor humans, the website (in-browser hashing, full privacy) or the Telegram bot @SGAttestBot. ## Status **In production.** Live at ` All 8 tools implemented, tested, and validated
Hosted by authorMITFew starsNo key
Yuanyi (元忆) — boundary-aware, file-based memory for AI agents, packaged as an Agent Plugin.
in the skill textPowers | | Hermes Agent | Portable Agent Plugins v1 packages | | OpenClaw | Plugin bundles | | Grok Bot | Skills, routines, and automations | | NanoClaw | Templates | Codex is verified by YottaMeta. Other clients
SkillMITFew starsNo key
Open-source packages that help AI agents read your website: gateway, agent detection, readability scoring, CLI and MCP server. Apache-2.0.
in the readmeagents, search crawlers and people apart from request headers, and verify Web Bot Auth signatures. No dependencies; runs at the edge. | npm | | `@rebilder/agent-readability` | Score how well
Node.jsApache-2.0Few starsNo key
MCP server for Synology Chat: read channels and posts, find users, send messages and files
in the readmesees exactly what that user sees in Chat (channels and DMs), no bot or webhook setup needed. ## Tools | Tool | What it does | |---|---| | `list_channels()` | Joined channels
DockerMITFew starsNeeds a key
Archive any URL to a shareable snapshot (rrweb/pdf/png) + agent-driven web QA — an MCP server for siteglass.io. No CAPTCHA, no signup.
in the readmepage **PNG**. No CAPTCHA, no signup, no ownership check, callable programmatically — a bot-friendly alternative to archive.today. (It renders JS-heavy pages; it does *not* produce
Node.jsMITFew starsNo key
MCP server for the useScraper API. This is a server that scrapes a URL to text or markdown
in the readmehtml, markdown). Default: markdown - `advanced_proxy` (optional): Use advanced proxy to circumvent bot detection. Default: false - `extract_object` (optional): Object specifying data to extract ## Installation ### Installing
SkillMIT★ 4Few starsNo key
Deterministic navigation maps over code AND markdown for AI agents — one MCP server, two lenses (tree-sitter TS/JS/Python + markdown). map the whole project, read one function or one doc-section, 99%
Node.jsAGPL-3.0★ 1Few starsNo key
Public listing files for the SecurePutCalls remote MCP server
MCPLink onlyFew stars
Checks for jobs continuously (24×7) on a schedule you control Parses job descriptions, extracts skills & keywords, and scores matches to your preferences Sends notifications (Email + Telegram bot supp
MCPLink only★ 4Few stars
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
in the readmeagents.yaml`, or make one from `/bots` in the UI. Anything a Bot does to a computer, a file, an MCP server or a component goes through
SkillMIT★ 6.5kNo key
Hylo: Personal knowledge agent compatible with Obsidian.
in the skill textare custom AI agents you define in **Settings → Agent Bots**. Each agent bot has a name, a system prompt, and a backing agent CLI (any agent
SkillApache-2.0★ 98No key
Who stands behind it
Who stands behind it
