Octopus Deploy Official

Octopus Deploy Official MCP Server

typescript

92

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "octopusdeploy-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "octopusdeploy/mcp-server",
        "--server-url",
        "https://your-octopus.com",
        "--api-key",
        "YOUR_API_KEY"
      ],
      "env": {
        "OCTOPUS_API_KEY": "YOUR_API_KEY",
        "OCTOPUS_SERVER_URL": "https://your-octopus.com"
      }
    }
  }
}

You can empower your AI assistants to interact with and troubleshoot your Octopus Deploy instance by running the Octopus MCP Server. It exposes a standardized interface that lets your models query spaces, projects, deployments, releases, and more, and even trigger write operations when explicitly enabled. This enables proactive monitoring, diagnostics, and guided automation across your Octopus environment.

How to use

Use a client that supports MCP to connect to the Octopus MCP Server. You will choose between a local, stdio-based setup or a remote HTTP-based deployment, depending on how you host the server. In practice, you will run the MCP server as part of your AI tooling workflow and configure it with your Octopus Server URL and API key. Once connected, you can query for lists of spaces, environments, and projects, inspect deployments and releases, manage tenants, and, if you enable write operations, create releases and trigger deployments. Tools are exposed as distinct functions, each with its own purpose and input shape.

Tool usage patterns

General pattern: connect to Octopus through the MCP server, request a data surface (for example, a list of projects), then drill into a specific item (such as deployments for a given release). You can also investigate issues by supplying a deployment URL or a task URL, which the MCP server can parse to fetch the corresponding context and logs.

Available tools

get_deployment_from_url

Retrieve deployment details from a deployment URL and obtain a taskId for follow-up actions.

get_task_from_url

Fetch task details directly from a task URL.

list_spaces

List all spaces in the Octopus Deploy instance.

list_environments

List all environments within a given space.

list_projects

List all projects within a given space.

deploy_release

Deploy a release to environments (tenanted or untenanted).

list_deployments

List deployments within a space with optional filtering.

create_release

Create a new release for a project.

find_releases

Find releases in a space or by specific ID.

list_releases_for_project

List all releases for a specific project.

get_task_by_id

Get details for a server task by its ID.

get_task_details

Get detailed information for a server task.

get_task_raw

Get raw details for a server task.

find_tenants

Find tenants in a space or search with filters.

get_tenant_variables

Get tenant variables by type (all, common, or project).

get_missing_tenant_variables

Identify tenant variables that are missing values.

get_kubernetes_live_status

Get live status of Kubernetes resources for a project and environment.

find_deployment_targets

Find deployment targets in a space.

find_certificates

Find certificates in a space.

find_accounts

Find accounts in a space.

get_deployment_process

Fetch deployment process by ID for projects or releases.

get_branches

Get Git branches for a version-controlled project.

get_current_user

Get information about the current authenticated user.