MCPgee
MCPgee
MCPgeeMCPgee

Station

v1.0.0•Cloud Services•stable

Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

agentsaidevopsgogolang
Share:
422
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Station?

Station is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Station is our open-source runtime that lets teams deploy ag

Use Cases

Self-hosted agent runtime
Team agent deployment
Infrastructure control
cloudshipai

Maintainer

LicenseApache-2.0
Languagego
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx station

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Station

Station is an open-source, self-hosted AI agent orchestration platform written in Go that lets teams build, evaluate, and deploy multi-agent systems on their own infrastructure. It provides built-in LLM-as-judge evaluations, Git-backed agent versioning, full OpenTelemetry observability via Jaeger, and a single-command deploy workflow via the `stn` CLI. Station connects to multiple LLM providers (CloudShip AI, OpenAI, Google Gemini, Anthropic) and exposes an MCP stdio interface so any MCP-compatible client can run agents directly.

Prerequisites

  • Docker installed (required for Jaeger tracing backend)
  • An AI provider API key: STN_CLOUDSHIP_KEY, OPENAI_API_KEY, GEMINI_API_KEY, or ANTHROPIC_API_KEY
  • An MCP-compatible client such as Claude Code CLI or OpenCode
  • curl available to run the install script
1

Install the Station CLI

Run the official install script to download and install the stn binary for your platform.

curl -fsSL https://raw.githubusercontent.com/cloudshipai/station/main/install.sh | bash
2

Initialize Station with your AI provider

Set your provider API key as an environment variable, then run stn init to configure the provider and install the Ship CLI filesystem tools. Replace the export line with your chosen provider.

export OPENAI_API_KEY="sk-..."
stn init --provider openai --ship
3

Start the Jaeger tracing backend

Start Jaeger so you can view per-agent execution traces. The UI will be available at http://localhost:16686.

stn jaeger up
4

Add Station to Claude Code CLI

Register Station as an MCP server in Claude Code using the stdio transport. The OTEL environment variable enables trace export to Jaeger.

claude mcp add station -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 --scope user -- stn stdio
5

Verify the connection

Confirm Station is registered and discoverable by your MCP client.

claude mcp list
6

Deploy an agent to production

Once your agent definitions are ready and version-controlled, push them to the Station runtime.

stn deploy

Station Examples

Client configuration

OpenCode configuration file for connecting to Station via stdio with OTEL tracing enabled.

{
  "mcp": {
    "station": {
      "enabled": true,
      "type": "local",
      "command": ["stn", "stdio"],
      "env": {
        "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4318"
      }
    }
  }
}

Prompts to try

Example prompts for working with Station-managed multi-agent teams through an MCP client.

- "Create an SRE incident response agent team that monitors and triages alerts"
- "Deploy a research agent that searches the web and summarizes findings"
- "Show me the traces from the last agent execution"
- "Evaluate the last 10 agent runs and report quality scores"

Troubleshooting Station

stn command not found after install

The install script places the binary in ~/.local/bin or /usr/local/bin. Ensure that directory is in your PATH and restart your shell session.

Jaeger traces not appearing in the UI at http://localhost:16686

Verify `stn jaeger up` is still running (it starts a Docker container). Check that OTEL_EXPORTER_OTLP_ENDPOINT is set to http://localhost:4318 (gRPC port), not 16686 (the UI port).

Anthropic OAuth login fails with 'authentication unavailable'

Anthropic has restricted third-party OAuth. Use a direct API key instead: export ANTHROPIC_API_KEY="sk-ant-..." and run stn init --provider anthropic --ship.

Frequently Asked Questions about Station

What is Station?

Station is a Model Context Protocol (MCP) server that station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Station?

Follow the installation instructions on the Station GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Station?

Station works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Station free to use?

Yes, Station is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Station Alternatives — Similar Cloud Services Servers

Looking for alternatives to Station? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.

Open WebUI

★ 138.2k

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Anything LLM

★ 60.4k

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LocalAI

★ 46.4k

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Nacos

★ 33.0k

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

Xiaozhi ESP32

★ 26.7k

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Gateway

★ 11.8k

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Cloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "station": { "command": "npx", "args": ["-y", "station"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Station?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides