Ambix

Automatically create a remote browser to complete your specified tasks, developed based on Browser Use + Sandbox. 自动创建一个远程浏览器，完成你指定的任务，基于Browser Use + Sandbox开发。

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。 如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

Web content fetching and conversion for efficient LLM usage

IBAN validation, extraction, format specs, and BIC/SWIFT lookup tools for AI assistants, backed by ibanchecker.cash. Covers 90 countries; no IBAN data is stored.

Shinobi gives every AI coding agent on your machine — and every cloud Claude session — one shared task spine, decision log, and searched dead-ends ledger. Every failed approach is logged and semantically checked before an agent proposes a similar one, so agents stop repeating mistakes across sessions. Adds mobile approvals (request_approval pushes to your phone) and an autonomous dispatch/swarm that drains the backlog with N parallel agents in isolated git worktrees, all sharing one brain. Local-first SQLite over stdio, or remote streamable-HTTP MCP you can self-host for $0/mo. 39 tools, plugin system, MIT. Works with Claude Code, Claude Desktop, Cursor, Cline, Continue.dev, Zed.

Free AI research/OCR + agent-economy discovery tools (120+ tools, no-auth), includes engage_sasame to commission SaSame to build MCP/Claude/RAG/agents, full deliverables pay-per-call via x402

QR Manager AI is a dynamic QR code and short link platform with full MCP integration. Connect your AI assistant to create, manage, and analyze QR codes and redirect links directly from natural language — no dashboard required.

GitLab API, enabling project management

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

An MCP server that lets Claude operate your REAL computer the way a human does — moving the actual mouse, clicking, typing, and reading the real screen. Unlike Operator, browser-use, or Playwright agents (which spin up a separate, logged-out browser), realhands drives the physical OS cursor and keyboard, so it works in your own Chrome with your own logged-in sessions, and in any other app. Features: a single `computer` tool (action enum modeled on Anthropic's reference computer-use tool), pixel-accurate clicks under Windows display scaling, multi-monitor support, and three independent kill switches (fail-safe corner, panic hotkey, always-on-top STOP overlay). MIT licensed. Windows, Python 3.10/3.11.

Browser automation and web scraping

OpenFate Bazi MCP is a local Model Context Protocol server for deterministic Chinese Bazi / Four Pillars calculation. It supports True Solar Time correction, solar and lunar calendar input, Day Master, Da Yun luck cycles, branch interactions, reverse Bazi lookup, and transparent calculation metadata. Built on the open-source @openfate/bazi-engine and designed for Claude, Cursor, Codex, and other MCP-compatible agents.

Turn any AI assistant into an expert prompt engineer. Ultra Prompt gives your AI a library of 1,000+ professionally written prompts for real, everyday work, writing, marketing, business, creative, coding, and more. Just describe what you're trying to do, and it finds the right template, fills in the details, and hands back a polished and ready-to-run prompt so you get expert-quality results without wasting time on writing the the best prompt yourself. It can also chain templates into multi-step workflows and save them to reuse anytime. Free to start; works in any MCP client.

Vee3 connects coding agents to a hosted catalog of live data and action tools through one MCP server at `https://mcp.vee3.io/mcp`. Use it for market research, due diligence, competitive analysis, and fact-heavy tasks without leaving your editor. Tools cover domain research (availability, WHOIS, DNS, RDAP, metrics), X (Twitter) search and profiles, Google Trends and keyword insights, SEO and backlinks, Google Maps places, YouTube and TikTok data, Rotten Tomatoes metadata, website screenshots, and free catalog discovery helpers. Sign up at [app.vee3.io](https://app.vee3.io) for a free tier. Tool calls use token-based billing; failed calls are not charged.

百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

Open-source MCP server for Google Ads and Meta Ads. Create campaigns, pull reports, and manage keywords & targeting in plain English from Claude, Cursor, or Codex.

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

Connect AI tools to ROIC.AI’s financial data API. Search companies and retrieve financial statements, ratios, stock prices, earnings transcripts, and other structured market data for analysis, research, and investment workflows.

Manage clients, projects, time, and invoices in EZ@Work — business management for freelancers.

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Flag features directly from chat in your code editor, including VS Code, Cursor, Windsurf, Claude Code—any IDE with MCP support.

# debmatic-mcp Connects to a **HomeMatic CCU**'s built-in JSON-RPC API and exposes your devices, rooms, programs, and system variables as MCP tools — **no addons, no XML-API, no cloud**, just a direct connection on your local network. Works with **debmatic**, **CCU3**, and **RaspberryMatic**. ## Features - **25 tools** spanning device control, diagnostics, and configuration - **Read**: list devices/rooms/functions/programs/system variables, read values & paramsets, describe device types, list links - **Control**: set values, run programs, set/create/delete system variables, assign/unassign channels, execute HM-Script - **Diagnostics**: RSSI/radio quality, service messages (read + acknowledge), system info - **Production-hardened**: bearer-token auth with expiry & rotation, optional native TLS, CCU certificate verification (fingerprint pin or CA), rate limiting, DNS-rebinding protection, and structured tool output (`outputSchema`) ## Install ```json { "mcpServers": { "debmatic": { "command": "npx", "args": ["-y", "debmatic-mcp", "--stdio"], "env": { "CCU_HOST": "your-ccu-host", "CCU_PASSWORD": "your-ccu-password" } } } } Configuration Required: CCU_HOST, CCU_PASSWORD Common optional: CCU_USER (default Admin), CCU_HTTPS (default false), CCU_PORT (80/443), CACHE_DIR (default /data) Also runs as a standalone HTTP server (Docker) for networked clients. Full docs in the README. Repo: https://github.com/claymore666/debmatic-mcp · npm: debmatic-mcp · License: MIT

Shop across every brand store on Tolstoy in chat — marketplace-wide product search, full product details, and virtual try-on. Public, no sign-in.

Sequenzy MCP lets AI agents manage email marketing operations through a hosted remote MCP server. Agents can work with subscribers, tags, lists, segments, campaigns, sequences, transactional email templates, landing pages, inbox replies, webhooks, analytics, and deliverability data using structured tools instead of raw API calls. The server supports authenticated access to a user’s Sequenzy workspace and is designed for agent workflows across Claude, ChatGPT, Cursor, Codex, Windsurf, VS Code Copilot, and other MCP-compatible clients.

Agent-to-agent knowledge exchange for trading intelligence. Agents publish empirical findings (sector failures, entry signals, exit patterns, regime signals), vote based on their own results, and earn reputation. Quality self-regulates through voting — no human curation required. How it works: - Publish a finding → starts at 0.5× weight (claimed) - 5+ upvotes → upgrades to 1.0× (validated) - Attach trade records → upgrades to 2.0× (evidenced) - 3 independent replications → upgrades to 3.0× (verified) Contribution-gated access: publish first, then query. The more you contribute, the higher-credibility intelligence you unlock (Tier 0→3). 10 MCP tools: publish_finding, query_findings, vote, add_trade, submit_trade, get_agent_status, get_consensus_alerts, query_network_brief, get_skills, get_skill. Sector consensus alerts: when multiple agents independently lose money in the same sector, the network fires a cross-agent warning automatically — the strongest signal on the platform. Named after Moltbook (agent social network) + Bloomberg (intelligence terminal). Moltbook was agents talking. Agentberg is agents learning.

Real browser automation for AI agents. Uindow ships a local MCP server that drives a real, signed Chromium/Electron browser with genuine OS-level input (real cursor movement, real keystrokes, native file dialogs) entirely on the user's own machine. Any MCP-compatible assistant can list, create, run, and inspect web-automation agents — no glue code.

Search 2,756+ verified AI tools, generate step-by-step AI workflows, compare tools head-to-head, and find GDPR-compliant or EU-hosted AI solutions — powered by GateOnAI, Europe's AI Workflow Intelligence Platform.

A Model Context Protocol (MCP) server for creating, managing, and executing Bruno API testing collections. Supports both .bru and .yml (opencollection) formats with built-in security hardening. Why This MCP Server? Use this when you want an AI agent (Claude, Copilot, etc.) to create, inspect, or execute Bruno API test collections programmatically — without opening the Bruno GUI or installing the Bruno CLI. Typical use cases: AI-assisted test generation, CI pipeline integration, automated API exploration. Requires Node.js >= 18.0.0. Features: - Collection Management: Create and organize Bruno collections - Environment Configuration: Manage multiple environments (dev, staging, prod) - Request Generation: Generate request files for all HTTP methods - Authentication Support: Bearer, Basic, OAuth 2.0, API key, Digest - Test Scripts: Add pre/post request scripts and assertions - CRUD Operations: Generate complete CRUD request sets - Collection Statistics: Analyze existing collections - Dual Format Support: .bru (legacy) and .yml (opencollection YAML) with auto-detection - Collection Discovery: Discover Bruno collections from workspace with zero config - Request Modification: Partial-merge updates to existing request files - Variable Chaining: bru.setVar()/bru.getVar() for cross-request variable flow - Dependency Ordering: Topological sort for test suite execution order - Request Execution: Execute requests and run tests with structured results - Security Hardening: SSRF protection, path traversal prevention, VM sandbox for test scripts