MCP Dock

# Install brew install --cask OldJii/tap/mcp-dock # Upgrade brew upgrade --cask mcp-dock

Note: The app is not signed. If you see "damaged" or "can't be opened" message, run:xattr -cr /Applications/MCP\ Dock.app

- Official- MCP Official Registry with verified servers
- Smithery- Smithery.ai community with community-contributed servers

We welcome community contributions! You can submit your own MCP Server or Skill configurations.
- Fork this repository
- Copy the template file:

- For MCP Servers:community-registry/servers/_template.json
- For Skills:community-registry/skills/_template.json

Your PR will be automatically validated against our JSON Schema. Once merged, your contribution will be included in the next data sync.

All configurations and data are stored locally:

- macOS:~/.mcp-dock/
- Windows:%USERPROFILE%\.mcp-dock\
- Linux:~/.mcp-dock/

Internet is required for loading the MCP list. Installed MCP configurations are stored locally and work offline.
- Delete the application
- Delete the config directory~/.mcp-dock/
- MCP configurations remain in each client's config file. Remove manually if needed.

This repository includes the full source code of MCP Dock (Community Edition). You can build, modify, and contribute to the project.

- Framework: Electron + React 18 + TypeScript
- Styling: Tailwind CSS
- State: Zustand
- Build: Vite + electron-builder
- Protocol: MCP JSON-RPC over stdio

# Install dependencies npm install # Start development mode npm run electron:dev # Build for production npm run package

src/ ├── renderer/ # Frontend (React + Vite + Tailwind) │ ├── src/ │ │ ├── components/ # UI components │ │ ├── pages/ # App pages (Store, Library, Inspector, etc.) │ │ ├── api/ # Registry API layer │ │ ├── store/ # Zustand state management │ │ ├── lib/ # Utilities and Electron bridge │ │ └── locales/ # i18n (English + Chinese) │ └── assets/ # Icons and static assets ├── main/ # Electron main process │ ├── config-manager # Multi-client config read/write (14 clients) │ ├── mcp-client # MCP JSON-RPC client for Inspector │ ├── skills-manager # Skills installation and management │ ├── history-manager # Config backup and rollback │ ├── env-manager # Runtime environment detection │ └── cache-manager # Local data caching ├── preload/ # Electron preload (secure IPC bridge) └── __tests__/ # Unit tests

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An MCP server for interactive user feedback and command execution in AI-assisted development, supporting both Web and Desktop interfaces.

200+ production tools for AI agents via Remote MCP. GitHub, Slack, Notion, Linear, Figma, Stripe, web search, OCR, document conversion, semantic memory/recall, Finviz, SEC filings, image generation, and more.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.

AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.