openconductor

The npm for AI agent tools — Install MCP servers without editing JSON. 220+ servers, one command.

Installation

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

Run in terminal:

Command

claude mcp add --transport stdio epicmotionsd-openconductor npx -y @openconductor/server-openconductor \
  --env OPENCONDUCTOR_TOKEN="REPLACE_WITH_TOKEN_IF_REQUIRED" \
  --env OPENCONDUCTOR_CONFIG_URL="optional-config-url"

How to use

OpenConductor provides a unified CLI to discover, install, and manage MCP servers. It acts as a centralized launcher for 180+ tools and capabilities, allowing you to quickly add functional agents and workflows to your AI setup without manually editing JSON configuration. With the CLI, you can search for available servers, install individual MCP servers, or install complete pre-configured stacks that bundle multiple servers along with a system prompt to tailor behavior for specific tasks. The included commands also let you list installed servers, remove or update them, initialize a configuration file, and view analytics or achievements as you build your deployment.

How to install

Prerequisites:

Node.js and npm installed on your system
Internet access to fetch packages

Installation steps:

Install the OpenConductor CLI globally

npm install -g @openconductor/cli

Install a single MCP server (example)

openconductor install github-mcp

Install a complete stack (example)

openconductor stack install coder

(Optional) Initialize or update your local MCP configuration

openconductor init
openconductor update

Notes:

You can adapt the example to install other servers by replacing github-mcp with the desired server identifier.
If you’re behind a proxy or need authentication tokens, export the required environment variables before running commands.

Additional notes

Tips and considerations:

The OpenConductor registry supports 180+ MCP servers; use openconductor discover to explore options.
Some servers may require API tokens or credentials; store tokens securely and reference them via env vars in your mcp_config.
Stacks bundle multiple servers with a system prompt; they’re ideal for getting a ready-to-use environment quickly.
Ensure your runtime environment has network access to fetch MCP server packages and dependencies.
If you encounter JSON editing issues, use the provided install commands to avoid manual config changes.
You can customize env vars per server in the mcp_config for secure and repeatable deployments.

Related MCP Servers

Pare

Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.

mcp-ssh-orchestrator

Secure SSH access for AI agents via MCP. Execute commands across your server fleet with policy enforcement, network controls, and comprehensive audit logging.

mcpx

Token-efficient MCP client: TypeScript schemas instead of JSON, LLM-friendly syntax, batch calls, TOON output. Built for Claude/GPT automations.

mcp-cron

MCP server for scheduling and running shell commands and AI prompts

mcp-jest

Automated testing for Model Context Protocol servers. Ship MCP Servers with confidence.

mcp-devtools

MCP DevTools: A suite of Model Context Protocol servers enabling AI assistants to interact with developer tools and services