MCP MCP Server

This project takes a number of MCP servers from GitHub locations, packages them together with this repo's GHCR container, and launches them with

Local serverstdioPython

What is the MCP MCP server?

This project takes a number of MCP servers from GitHub locations, packages them together with this repo's GHCR container, and launches them with docker-compose to run as a stack for ML/AI resources. That is what the mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

Getting it running

Installation goes through your MCP client rather than a global install: point it at mcp-shield on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 5 tools. What each one is for:

  • Calculator — Slack
  • Everart — Google Maps
  • mcp — network
  • Flowise — The Flowise tool exposed by this server
  • Warnings — This is a first step to running these MCP services in a containerized and easier-to-deploy process. But you'll need to do some testing and validation

What it needs from you

  • Docker - Portainer (not necessary, but useful) - API Tokens/Keys for specific services (optional, depends on the server)

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP's toolset — Calculator, Everart, mcp and 2 more — is a fair guide to whether it matches your workflow. It is maintained by JoshuaRL; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
CalculatorSlack
EverartGoogle Maps
mcpnetwork
FlowiseThe Flowise tool exposed by this server.
WarningsThis is a first step to running these MCP services in a containerized and easier-to-deploy process. But you'll need to do some testing and validation for soem of the environment variables and connecting to other services

How to install the MCP MCP server

{
  "mcpServers": {
    "mealprep": {
      "command": "npx",
      "args": ["-y", "mcp-shield"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Docker - Portainer (not necessary, but useful) - API Tokens/Keys for specific services (optional, depends on the server)

Example prompts to try

  • Use MCP to Calculator.
  • Use MCP to Everart.
  • Use MCP to mcp.

Frequently asked questions

The stack includes servers for web search (SearXNG, Brave), GitHub, Slack, Google Maps, web crawl (Fetch, Puppeteer), sequential thinking, Postgres/vector retrieval (Supabase, Qwant, Pinecone, Memory), a calculator, Everart, and more. The list can be customized.