emqx_mcp_gateway

Browser automation and web scraping

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

Poppify is an MCP server (and Claude Code plugin) for photo-led short-form vertical video. Upload 1–10 photos via the MCP, get a captioned 15/30/60s reel for Instagram, TikTok, YouTube Shorts, or Facebook — with motion, library-matched music, and optional voiceover. 27 MCP tools covering register/wallet, session creation, slide editing, audio matching, asset generation, and confirm/render. Recipe-driven composition (14 narrative frameworks). Library-first audio matching before any AI generation. $0.06 per render, 50 free seeds on signup, no subscription. Compatible with Claude Code, Claude.ai, ChatGPT, Cursor, Cline, and any MCP-compatible AI assistant. Built for SMBs and solo service providers who want consistent vertical reels without hiring a content creator. Not for: text-to-video generation (use Runway), avatar-based video (use HeyGen), 4K horizontal cinema, or sub-4s clips.

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

Official Model Context Protocol (MCP) server to search, filter, and retrieve live remote job listings from the Jobicy database in real-time. Works with Claude Code, Cursor, Cline, and custom AI agents.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Extract timestamped YouTube transcripts — plus video search, metadata, and related-video tools — for Claude, Cursor, Windsurf, and any MCP client.

MCP server to provide Figma layout information to AI coding agents like Cursor

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

tani (谷, "valley") is an agent-native hub. AI agents discover capabilities in a registry ranked by computed invocation trust — success rate, dependents and schema stability, earned by execution, never self-reported stars — exchange answers verified by execution, and find each other. tani-mcp puts the hub inside an agent's loop as 12 tools: resolve a capability by intent + constraints, describe a surface's schema/examples/failure-modes, discover and register agents, submit surfaces, and contribute verified answers. The same data is served as a human observatory (HTML) and as the tani/1.0 wire (application/tani+json, content-addressed, agent-signed). Live at https://tani.ai.

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

Retrieving and analyzing issues from Sentry.io

A Serper MCP Server

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

GitLab API, enabling project management

AI image generation using various models

A data firewall between AI and your calendar. Give Claude, ChatGPT, and other AI assistants controlled access to Google Calendar and Outlook to search your schedule, check availability, create, reschedule, and cancel events, and RSVP. The AI is held to the permissions you grant, every change is logged, and you can revoke access in one click.

A data firewall between AI and your inbox. Give Claude, ChatGPT, and other AI assistants controlled access to Gmail and Microsoft 365 to search, read, send, reply, forward, label, and delete email. Sensitive content is redacted before the AI sees it, the AI is held to the permissions you grant, every action is logged, and you can revoke access in one click.

Read and query the full Codex.io documentation, so your agent can write queries and subscriptions to the Codex GraphQL API for token and prediction market prices, charts, balances, and transactions.

Local MCP server for LiveJournal journals. It uses the legacy LiveJournal XML-RPC API to read entries, read comments, post to your own journal, and build a local SQLite cache for search.

Secure file operations with configurable access controls

SnapStack pipes browser screenshots into any MCP-capable LLM client, 100% locally. Click the extension to capture a tab — area or full page — and shots stack on a small always-on server bound to 127.0.0.1. Your AI reads them on demand over MCP: it gets a lightweight manifest (number, file path, dimensions, page metadata), never raw image bytes pushed to the model. No account, no telemetry — nothing ever leaves your machine.

让你的Agent来跟全世界对接需求，你的AI助理帮你把需求传达出去，又帮你接受别人给你的需求。 需求链平台是将整个人类联结在一起的一个工具，组成一个网络。 告诉你的AI助理，你的需求，Agent会在需求链平台上寻找到能解决你需求的人。 别人也会将他的需求传达给你，你接受你能处理的需求，你也可以将这个需求拆分，变成数个小的需求，继续放在需求链上传递下去。 比如说你想要一种技术的创新，一个人工智能的新算法，或者是需要一种新材料，想要一种新的解决方案，去解决工作生活中的真实痛点。 你或许有一个天才的想法，需要有人与你一起去验证是否可行。 或者你已经有一套成功的技术，需要让全世界都知道你的方案。 总之每个人都有各种需求需要解决，而需求链平台，就是帮你解决各种需求而存在的机制。 赶快打开你的Agent，告诉他，你的需求吧。 此需求链平台是地球人类共有的基础设施，永久开源，中立，免费。 Let your Agent connect with demands from across the globe. Your AI assistant will forward your requests and receive demands from others for you. The Demand Chain Platform is a tool that unites all humanity into a connected network. Simply tell your AI assistant what you need, and your Agent will find people on the platform who can address your requirements. Others will also send their demands to you. You may take on tasks you are capable of handling, or split a single demand into several smaller ones to keep them circulating on the Demand Chain. For instance, you may seek technological innovation, a new AI algorithm, advanced new materials, or practical solutions to real problems in work and daily life. You might have a brilliant idea and need partners to verify its feasibility. Or you possess proven technologies and wish to share your solutions with the whole world. Everyone has various needs to fulfill, and the Demand Chain Platform is built precisely for this purpose. Launch your Agent and submit your demands right away. As a shared infrastructure for all people on Earth, this Demand Chain Platform is permanently open-source, neutral and free of charge.

A Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

Playwright MCP server

AgentPing gives your AI agent a single focused tool — send_notification — so a long-running or autonomous agent can reach a human the moment it matters: a task finished, an approval is needed, a result is ready, or something broke. Notifications are delivered to whatever channels you configure: email, Slack, Discord, or a custom webhook. AgentPing is read-only by design — it can only send the notifications your agent triggers, with no access to your inbox, files, or accounts. Notifications are delivered to whatever channels you configure: email, Slack, Discord, or a custom webhook. AgentPing is read-only by design — it can only send the notifications your agent triggers, with no access to your inbox, files, or accounts. Hosted remote MCP server (Streamable HTTP) — nothing to run locally. Free tier: 100 notifications/month. Pro: $9/mo or $90/yr for 10,000/month.