AnythingMCP

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.

Playwright MCP server

Repository management, file operations, and GitHub API integration

Read-only database access with schema inspection

Publish a static website to a live public URL — straight from chat. Hand Just Publish your HTML, CSS, JS, and images and get a shareable link in seconds. No build step, no dashboard, no deploy config.

Self-learning memory for AI tools. Remembers user preferences and context across Claude, Cursor, and Codex — with multi-parameter forgetting and cross-tool identity.

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。

Zaklad is a platform for building design systems. This MCP server lets you create, manage and view your own design system with AI: build and edit design tokens, themes, components, and icons. Zaklad turns them into a Figma library and production-ready code.

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

A self-service creative engine for app and consumer brands. Sense signals, express narratives, learn from results. Sold as Time-to-Winner, not video volume.

Schedule and publish social media posts to 11+ platforms (X, Instagram, Facebook, TikTok, LinkedIn, YouTube, Threads, Pinterest, Bluesky, Telegram, Google Business Profile) from Claude, ChatGPT, or Cursor. Connect via the hosted OAuth URL (no key, nothing to self-host) or run it locally with npx and your PostFast API key.

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。

Browser automation and web scraping

Command firewall for AI agents. Validates every shell command before execution — binary check locally, syntax and targets via API. Sub-100ms. $0.0068 AUD per check, 80 free on sign-up.

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

Public read-only MCP server backed by GetValetParking.com directory of 789 US valet parking operators across 31,186 cities. Discover valet operators by, filter by 9 service types, and fetch full operator profiles. No auth required.

NeuroRank exposes its esports cognitive-combine data over MCP. One free tool returns aggregate cohort stats with no key; two paid tools (get_player_report, get_team_report) return per-player and team scouting reports, gated by an x-api-key tied to a scout or team subscription. Streamable HTTP, stateless. Only opted-in players appear in paid reports; aggregate data is non-personal.

One shared, durable memory for all your AI coding agents — local-first, MCP, zero-dependency. Decisions, lessons, and project status persist across sessions, tools, and projects.

Sendmux is an email inbox API and email API for AI agents. Use this MCP server to let authorised agents work with Sendmux mailboxes, inbound email, clean JSON parsing, webhooks, outbound sending, provider routing, logs, billing, and team controls. Agents can read mailbox messages, send email, manage domains and mailboxes, inspect usage, and build multi-tenant email workflows without raw IMAP/SMTP plumbing. Learn more: https://sendmux.ai/product/inboxes MCP setup: https://sendmux.ai/docs/guides/mcp

Self-hosted, open-source MCP gateway: turn any API, database or MCP server into custom connectors for Claude, ChatGPT, Gemini, Copilot & Cursor — no code. Converts REST, SOAP, WSDL, GraphQL & SQL to MCP, with OAuth2, RBAC & audit log. 175+ pre-built adapters (Deutsche Bahn, weclapp, Etsy, DHL, Shopware).

GitLab API, enabling project management

Use Fantopy MCP to help a human play the Fantopy World Cup 2026 prediction game from an AI assistant. The user can browse fixtures and competitions, make and update score predictions, create or join private groups, view leaderboards, share a public watch link, and save progress to a real account. The AI is a companion for a human player, not a competitor. Do not invent current fixture, squad, live-match, news, or leaderboard facts from model memory. Use the Fantopy MCP tools.

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。

Aidress is the coordination layer for autonomous AI agents. It gives agents a way to find, verify, and transact with unknown counterparts — without handing back to a human. Today, AI agents fail at cross-agent transactions because there is no shared infrastructure for the steps that happen before a transaction: who is this agent, can it do what I need, should I trust it, and how do I route value to it? Aidress provides those five layers.

Run SSL/TLS scans, issue free Let's Encrypt certificates (private key stays local), and monitor certificate expiry from inside Claude Code or Cowork - through a single MCP server, no account needed for scans and issuance.