Octopus Deploy
Enables AI assistants to inspect, query, and diagnose problems within Octopus Deploy instances. Provides read-only access to deployments, releases, projects, environments, and other DevOps resources to transform AI into your ultimate DevOps wingmate.
What is Octopus Deploy?
Octopus Deploy is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to inspect, query, and diagnose problems within octopus deploy instances. provides read-only access to deployments, releases, projects, environments, and other devops resources t...
Enables AI assistants to inspect, query, and diagnose problems within Octopus Deploy instances. Provides read-only access to deployments, releases, projects, environments, and other DevOps resources to transform AI into your ultimate DevOps wingmate.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI assistants to inspect, query, and diagnose proble
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @octopusdeploy/mcp-serverManual Installation
npx -y @octopusdeploy/mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Octopus Deploy
The Octopus Deploy MCP Server gives AI assistants read (and optionally write) access to your Octopus Deploy instance, covering deployments, releases, projects, environments, runbooks, infrastructure, tenants, and Kubernetes live status. It transforms your AI into a DevOps copilot that can diagnose failed deployments, summarise release histories, run runbooks, and manage feature toggles — all through natural language without leaving your chat interface.
Prerequisites
- Node.js v20.0.0 or later (for the npx installation method)
- A running Octopus Deploy instance (self-hosted or Octopus Cloud)
- An Octopus API key (Settings → API Keys in your Octopus instance) — or a short-lived access token for automation
- The Octopus server URL (e.g. https://your-company.octopus.app)
- An MCP client such as Claude Desktop, Cursor, or VS Code with Copilot
Generate an Octopus API key
Log into your Octopus Deploy instance, go to your user profile, select API Keys, and create a new key. Copy the key — it starts with API- and is shown only once.
Test the server from the command line
Run the server once manually to confirm connectivity before wiring it into your MCP client. Supply your real URL and API key.
OCTOPUS_API_KEY=API-XXXXXXX npx -y @octopusdeploy/mcp-server --server-url https://your-company.octopus.appAdd the server to your MCP client configuration
Open your MCP client config file (for Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json on macOS) and add the octopusdeploy entry. The server will start automatically when the client launches.
{
"mcpServers": {
"octopusdeploy": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@octopusdeploy/mcp-server"],
"env": {
"OCTOPUS_SERVER_URL": "https://your-company.octopus.app",
"OCTOPUS_API_KEY": "API-XXXXXXXXXXXXXXXXXXXXXXXX"
}
}
}
}Restrict to read-only mode (recommended for production)
Pass the --read-only flag to prevent any write operations. This is the safest configuration for production Octopus instances and for sharing access with teammates.
{
"mcpServers": {
"octopusdeploy": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@octopusdeploy/mcp-server", "--read-only"],
"env": {
"OCTOPUS_SERVER_URL": "https://your-company.octopus.app",
"OCTOPUS_API_KEY": "API-XXXXXXXXXXXXXXXXXXXXXXXX"
}
}
}
}Restart your MCP client and verify the connection
Restart Claude Desktop or your chosen client. The AI should now have access to Octopus tools. Ask it to list your projects to confirm connectivity.
Octopus Deploy Examples
Client configuration
Standard Claude Desktop configuration with read-only mode enabled for safe production use.
{
"mcpServers": {
"octopusdeploy": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@octopusdeploy/mcp-server", "--read-only"],
"env": {
"OCTOPUS_SERVER_URL": "https://your-company.octopus.app",
"OCTOPUS_API_KEY": "API-XXXXXXXXXXXXXXXXXXXXXXXX"
}
}
}
}Prompts to try
Use natural language to query and diagnose your Octopus Deploy instance.
- "Why did the last deployment of the Payments API to Production fail?"
- "List all releases for the Shopping Cart project created in the last 7 days"
- "Which deployment targets in the Production environment are unhealthy?"
- "Show me the variables configured for the Staging environment in the Orders project"
- "What is the Kubernetes live status for the frontend deployment in Production?"Troubleshooting Octopus Deploy
Authentication error: 401 Unauthorized
Verify that OCTOPUS_API_KEY is set correctly and the key has not expired. The key must start with API-. Also confirm OCTOPUS_SERVER_URL matches your instance URL exactly, including the protocol (https://).
Tools are not appearing in the AI client after configuration
Fully restart your MCP client (Claude Desktop, Cursor, etc.) after editing the config file. If using --toolsets, ensure the toolset names are valid (core, projects, deployments, runbooks, infrastructure, tenants). Remove the flag to load all toolsets.
Write operations fail even though the API key has permission
If you passed --read-only, all write tools are disabled by design. Remove the flag for write access. For confirmation prompts on write operations, set OCTOPUS_SKIP_ELICITATION=true if your client does not support elicitation.
Frequently Asked Questions about Octopus Deploy
What is Octopus Deploy?
Octopus Deploy is a Model Context Protocol (MCP) server that enables ai assistants to inspect, query, and diagnose problems within octopus deploy instances. provides read-only access to deployments, releases, projects, environments, and other devops resources to transform ai into your ultimate devops wingmate. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Octopus Deploy?
Install via npm with the command: npx -y @octopusdeploy/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Octopus Deploy?
Octopus Deploy works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Octopus Deploy free to use?
Yes, Octopus Deploy is open source and available under the Mozilla Public License 2.0 license. You can use it freely in both personal and commercial projects.
Octopus Deploy Alternatives — Similar Cloud Services Servers
Looking for alternatives to Octopus Deploy? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan 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
★ 11.8kA 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.
Set Up Octopus Deploy in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Octopus Deploy?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.