spinnaker-mcp
MCP server exposing Spinnaker CD platform via Gate API for pipeline and deployment management
Spinnaker-MCP
A bridge that exposes any Spinnaker instance as an MCP v1 server via the Gate API, written in Go.
What you get
| Category | Tool | Description |
|---|---|---|
| Applications | list_applications | List all Spinnaker applications |
get_application | Get detailed application info (accounts, clusters, attributes) | |
| Pipelines | list_pipelines | List pipeline configurations for an application |
get_pipeline | Get a specific pipeline's full configuration | |
trigger_pipeline | Trigger a pipeline with optional parameters | |
save_pipeline | Save/create a pipeline definition | |
update_pipeline | Update an existing pipeline definition | |
delete_pipeline | Delete a pipeline definition | |
get_pipeline_history | Get revision history for a pipeline config | |
| Executions | list_executions | List recent executions, filterable by status |
get_execution | Get full execution details (stages, outputs, timing) | |
search_executions | Rich search by trigger type, time range, status | |
cancel_execution | Cancel a running execution with optional reason | |
pause_execution | Pause a running execution at the current stage | |
resume_execution | Resume a paused execution | |
restart_stage | Restart a failed stage within an execution | |
evaluate_expression | Evaluate a SpEL expression against an execution | |
| Strategies | list_strategies | List deployment strategy configurations |
save_strategy | Create or update a deployment strategy | |
delete_strategy | Delete a deployment strategy | |
| Infrastructure | list_server_groups | List server groups (deployment targets) with instance counts |
list_load_balancers | List load balancers across all accounts and regions | |
list_clusters | List cluster names grouped by account | |
get_cluster | Get cluster details including server groups | |
get_scaling_activities | Get scaling activities for a cluster | |
get_target_server_group | Target-based server group lookup (newest, oldest, etc.) | |
list_firewalls | List all firewalls/security groups across accounts | |
get_firewall | Get firewall details by account, region, and name | |
get_instance | Get instance details (health, metadata, launch time) | |
get_console_output | Get instance console output for debugging | |
find_images | Search for machine images by tags, region, account | |
get_image_tags | List image tags for a repository | |
list_networks | List VPCs/networks by cloud provider | |
list_subnets | List subnets by cloud provider | |
list_accounts | List all configured cloud accounts/credentials | |
get_account | Get account details and permissions | |
| Tasks | get_task | Get orchestration task status (deploy, resize, rollback) |
Everything is exposed over JSON-RPC. LLMs and agents can: initialize -> listTools -> callTool and interact with your Spinnaker deployments.
Quick-start
npm (stdio transport)
npx spinnaker-mcp
Or install globally:
npm install -g spinnaker-mcp
spinnaker-mcp
This downloads the pre-built Go binary for your platform and runs it with stdio transport.
Docker
docker run --rm -e GATE_URL=http://spin-gate:8084 -e TRANSPORT=stdio drumsergio/spinnaker-mcp:0.3.1
Local build
git clone https://github.com/GeiserX/spinnaker-mcp
cd spinnaker-mcp
cp .env.example .env && $EDITOR .env
go run ./cmd/server
Configuration
| Variable | Default | Description |
|---|---|---|
GATE_URL | http://localhost:8084 | Spinnaker Gate API endpoint (without trailing /) |
GATE_TOKEN | (empty) | Bearer token for authentication |
GATE_USER | (empty) | Basic auth username (alternative to token) |
GATE_PASS | (empty) | Basic auth password |
GATE_CERT_FILE | (empty) | Path to x509 client certificate (PEM) |
GATE_KEY_FILE | (empty) | Path to x509 client key (PEM) |
GATE_INSECURE | false | Skip TLS certificate verification |
TRANSPORT | (empty = HTTP) | Set to stdio for stdio transport |
MCP_PORT | 8085 | HTTP transport port (ignored when TRANSPORT=stdio) |
MCP_BIND_ADDR | 127.0.0.1 | HTTP transport bind address (set to 0.0.0.0 to listen on all interfaces) |
Authentication priority: Bearer token > Basic auth > x509 client cert > No auth.
Put them in a .env file (from .env.example) or set them in the environment.
Claude Code / Claude Desktop configuration
{
"mcpServers": {
"spinnaker": {
"command": "npx",
"args": ["-y", "spinnaker-mcp"],
"env": {
"GATE_URL": "https://spin-gate.example.com",
"GATE_TOKEN": "your-token-here"
}
}
}
}
Testing
go test -v -race ./...
Tested with Inspector. Before making a PR, make sure this MCP server behaves well via that tool.
Credits
Spinnaker -- open-source continuous delivery platform
MCP-GO -- Go MCP implementation
GoReleaser -- painless multi-arch releases
Maintainers
Contributing
Feel free to dive in! Open an issue or submit PRs.
Spinnaker-MCP follows the Contributor Covenant Code of Conduct.
Other MCP Servers by GeiserX
- genieacs-mcp -- TR-069 device management
- cashpilot-mcp -- Passive income monitoring
- duplicacy-mcp -- Backup health monitoring
- lynxprompt-mcp -- AI configuration blueprints
- pumperly-mcp -- Fuel and EV charging prices
- telegram-archive-mcp -- Telegram message archive
관련 서버
MCP Kubernetes
Execute Kubernetes commands using kubectl from any MCP-compatible client. Requires a valid kubeconfig file.
sentry-mcp-rs
A fast, lightweight MCP server for Sentry, written in Rust.
AI Image MCP Server
AI-powered image analysis using OpenAI's Vision API.
Jumpseller
Manage your Jumpseller e-commerce store with AI. Create products with variants, process orders, search customers, and organize your catalog.
Gravatar
Interact with Gravatar avatars, profiles, and inferred interests.
MCP Status Observer
Monitors the operational status of major digital platforms.
AWS‑IReveal‑MCP
Provides a unified interface to AWS services for security investigations and incident response.
SharePoint MCP Server
Integrates with Microsoft SharePoint, allowing interaction with documents, folders, and other SharePoint resources.
Render
Manage your Render.com services, deployments, and infrastructure.
WaveGuard
Physics-based anomaly detection via MCP — send any data, get anomalies back using wave-equation dynamics. No training pipelines, no model files.