mcp s

MCP server from ag2ai/mcp-servers

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio ag2ai-mcp-servers docker run -i ag2ai/mcp-servers:latest \
  --env MCP_PORT="Port for the MCP server to listen on" \
  --env MCP_NETWORK="Name of the MCP network to join" \
  --env MCP_CONFIG_PATH="Path inside container to custom config (if applicable)"

How to use

This MCP server collection provides a set of Minecraft-compatible MCP (Model Context Protocol) servers that can run multiple MCP instances or services in parallel. Each server in the suite exposes a distinct API surface and tooling to interact with and manage your MCP workflows, experiments, or simulations. Use the docker command (shown in the mcp_config) to spin up a containerized environment that includes the MCP server(s) and their associated tooling. Once running, you can connect to the server endpoints, issue available commands, and observe logs to monitor behavior and results. The suite is designed to facilitate experimentation with different MCP configurations, enabling you to scale or swap components without rebuilding from scratch.

How to install

Prerequisites:

Docker installed and running on your system
Basic familiarity with running containerized services
git (optional, for cloning repositories)

Installation steps:

Pull and run the MCP server image: docker run -it --rm -p 8080:8080 ag2ai/mcp-servers:latest
If you prefer building from source (optional), clone the repository and run locally if a local start script is provided by the project: git clone https://github.com/ag2ai/mcp-servers.git cd mcp-servers

Follow any local setup instructions (e.g., npm install, pip install, or python -m setup) as documented in the repo
Configure network and environment variables as needed (see mcp_config env placeholders) and restart the server to apply changes.

Additional notes

Tips and notes:

Environment variables such as MCP_NETWORK, MCP_PORT, and MCP_CONFIG_PATH can be used to customize networking and configuration scopes for your MCP instances.
If you encounter port conflicts, adjust MCP_PORT or map container ports accordingly when using Docker.
Check container logs frequently during initial runs to verify successful startup and endpoint readiness.
If you are integrating with external orchestrators (e.g., Kubernetes), adapt the docker run pattern to your deployment spec (e.g., using a Deployment/Pod with proper volume mounts for config).
This readme uses a placeholder image tag; replace with a vetted or versioned image tag from your registry when deploying in production.
Ensure your MCP network requirements (latency, congestion, and concurrency) are aligned with the workload you plan to run.

Related MCP Servers

mcp-vegalite

MCP server from isaacwasserman/mcp-vegalite-server

github-chat

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

nautex

MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline

pagerduty

PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.

futu-stock

mcp server for futuniuniu stock

mcp -boilerplate

Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP