MCP SERVER · OFFICIAL PROJECTDrive Spinnaker from an agent — pipelines listed, triggered and edited, executions paused, resumed, cancelled and restarted, and the cloud infrastructure behind them read.
LABSCO SUMMARY
save_pipeline, update_pipeline, delete_pipeline and trigger_pipeline write to your delivery configuration and start real deploys, and the execution tools stop and restart work that is already in flight. Give it a Gate credential scoped to what you actually intend, and note the authentication order: with no token, user or certificate set, it connects unauthenticated rather than refusing. On the read side, evaluate_expression and get_console_output are the two that turn a failed deploy into an explanation instead of a screenshot.
A Go bridge that exposes a Spinnaker instance through its Gate API as an MCP server. It covers the continuous-delivery loop end to end: applications and pipeline configuration, execution control while a deploy is running, and the cloud resources a deploy targets — server groups, clusters, load balancers, firewalls, images, networks and accounts.
list_applications, get_applicationlist_pipelines, get_pipeline, save_pipeline, update_pipeline, delete_pipeline, get_pipeline_historytrigger_pipelinelist_executions, search_executions, get_executionpause_execution, resume_execution, cancel_execution, restart_stageevaluate_expressionlist_strategies, save_strategy, delete_strategylist_server_groups, list_clusters, get_cluster, list_load_balancers, get_scaling_activities, get_target_server_grouplist_firewalls, get_firewall, get_instance, get_console_outputfind_images, get_image_tags, list_networks, list_subnets, list_accounts, get_accountget_taskA reachable Spinnaker Gate endpoint in GATE_URL, which is the one required setting. Authentication is tried in a fixed order — bearer token in GATE_TOKEN, then basic auth via GATE_USER and GATE_PASS, then an x509 client certificate through GATE_CERT_FILE and GATE_KEY_FILE, then none at all — so an unset credential silently means unauthenticated rather than an error. Run it with npx spinnaker-mcp, which fetches the prebuilt Go binary for your platform, or from drumsergio/spinnaker-mcp on Docker, or build the Go source. Transport is HTTP unless TRANSPORT is set to stdio; MCP_PORT and MCP_BIND_ADDR control the HTTP listener, which binds to 127.0.0.1 by default. The published version is 0.3.3.
One command — npx spinnaker-mcp
USE CASES
Open the execution with its stages and timing, evaluate the SpEL expression that resolved wrongly, and pull the console output from the instance that would not come up.
Pause the running execution at its current stage, decide, then resume it or cancel it with a reason recorded.
Restart the failed stage within the existing execution rather than triggering the whole pipeline again.
Find the pipeline for the application, trigger it with the parameters you want, and follow the orchestration task until it settles.
Read its full configuration and its revision history to see what changed and when, before editing it.
List server groups with their instance counts, open the cluster, and read scaling activities to see whether capacity moved on its own.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
cancel_executionCancel a running pipeline execution by its ID, optionally providing a reason. Use this to stop a deployment in progress — for example, when a bad build was triggered. Does not roll back completed stages. Returns a confirmation message.
delete_pipelinePermanently delete a pipeline configuration from Spinnaker. Use this only when a pipeline is no longer needed — this action cannot be undone. Does not affect past executions. Returns a confirmation message on success.
delete_strategyPermanently delete a deployment strategy configuration from Spinnaker. Use this only when a strategy is no longer needed — this action cannot be undone. Returns a confirmation message on success.
evaluate_expressionEvaluate a Spring Expression Language (SpEL) expression against a pipeline execution context. Use this to inspect pipeline variables, stage outputs, or computed values during debugging. Dangerous patterns (reflection, class instantiation) are blocked for security. Returns the evaluated expression result as JSON.
find_imagesSearch for machine images (AMIs, GCE images, Docker images) available in Spinnaker for a given cloud provider. Use this to find images for a deployment or verify which image versions are available. Supports filtering by query string, region, and account. Returns JSON array of matching image objects.
get_accountGet details for a specific Spinnaker account by name, including its cloud provider type, permissions, and regions. Use this to verify account configuration or check permissions before deploying. Returns JSON with full account metadata.
get_applicationGet detailed information about a single Spinnaker application including its accounts, clusters, and custom attributes. Use this to inspect an application's configuration before modifying its pipelines or infrastructure. Returns JSON with application metadata, associated cloud accounts, and cluster details.
get_clusterGet details for a specific cluster in a Spinnaker application by account and cluster name. Use this to inspect server groups, load balancers, and instance counts within a cluster. Returns JSON with cluster metadata and its constituent server groups.
get_console_outputGet the console output (boot log) for a specific compute instance. Use this to debug instance startup failures or inspect early boot messages. Requires account, region, and instance ID. Returns the raw console output text.
get_executionGet the full details of a single pipeline execution by its ID, including all stage statuses, outputs, variables, and timing. Use this to debug a failed deployment or inspect execution progress. Returns comprehensive JSON with per-stage results. Obtain the execution_id from trigger_pipeline, list_executions, or search_executions.
get_firewallGet details for a specific firewall rule (security group) by account, region, and name. Use this to inspect inbound/outbound rules and associated resources. Returns JSON with the firewall's full rule set and metadata.
get_image_tagsGet available tags for a Docker image repository registered in Spinnaker. Use this to list version tags before triggering a pipeline with a specific image tag. Returns JSON array of tag strings for the specified repository.
get_instanceGet details for a specific compute instance by account, region, and instance ID. Use this to inspect instance health, metadata, launch time, and cloud-specific attributes. Returns JSON with full instance details including health indicators.
get_pipelineGet the full configuration of a specific pipeline by application and pipeline name. Use this to inspect pipeline stages, triggers, and parameters before triggering or modifying it. Returns the complete pipeline JSON definition including all stage configurations.
get_pipeline_historyGet the version history of a pipeline configuration showing past revisions. Use this to audit changes to a pipeline or compare previous configurations. Returns JSON array of historical pipeline versions ordered by update time.
get_scaling_activitiesGet scaling activities for a server group in a Spinnaker cluster. Use this to audit recent auto-scaling events (scale-up, scale-down) and diagnose capacity issues. Returns JSON array of scaling activity records with timestamps, descriptions, and status.
get_target_server_groupGet a specific server group in a Spinnaker cluster using a target selection strategy (e.g., newest, oldest, largest, smallest, fail). Use this when you need the most recently deployed or a specific server group without knowing its exact name. Returns JSON with the matched server group details.
get_taskGet the status and details of a Spinnaker orchestration task (e.g., deploy, resize, rollback, delete). Use this to monitor the progress of a long-running infrastructure operation. Returns JSON with task status, start/end times, retry info, and step-by-step execution details.
list_accountsList all configured Spinnaker accounts (cloud provider integrations). Use this to discover available cloud accounts before querying infrastructure or deploying. Returns JSON array of account objects with provider type, environment, and permissions.
list_applicationsList all Spinnaker applications with their metadata. Use this as a starting point to discover available applications before querying pipelines or infrastructure. Returns JSON array of application objects with name, email, accounts, and cloud providers.
list_clustersList all cluster names for a Spinnaker application, grouped by account. Use this to discover clusters before drilling into a specific one with get_cluster. Returns JSON object mapping account names to arrays of cluster names.
list_executionsList recent pipeline executions for a Spinnaker application, optionally filtered by status. Use this to monitor deployment activity or find a specific execution ID. Returns JSON array of execution summaries with status, timing, and trigger info. Use get_execution for full details of a specific run.
list_firewallsList all firewall rules (security groups) across all Spinnaker accounts and regions. Use this to audit network security posture or find a specific security group before inspecting it with get_firewall. Returns JSON array of firewall objects grouped by account and region.
list_load_balancersList all load balancers for a Spinnaker application across all accounts and regions. Use this to inspect network routing and health check configuration for an application. Returns JSON array of load balancer objects with listener, health check, and attached server group details.
list_networksList all networks (VPCs) across all Spinnaker accounts and cloud providers. Use this to discover available networks when configuring deployment targets or security groups. Returns JSON array of network objects with provider, account, and CIDR details.
list_pipelinesList all pipeline configurations for a Spinnaker application. Use this to discover available pipelines before triggering or inspecting a specific one. Returns JSON array of pipeline configuration objects with name, stages, triggers, and parameters.
list_server_groupsList all server groups (ASGs, instance groups, replica sets) for a Spinnaker application. Use this to view active deployment targets and their instance counts across regions and accounts. Returns JSON array of server group objects with instance counts, cloud provider details, and region info.
list_strategiesList all deployment strategy configurations for a Spinnaker application. Use this to discover available strategies (e.g., red/black, rolling, canary) before saving or modifying one. Returns JSON array of strategy configuration objects.
list_subnetsList all subnets for a given cloud provider across Spinnaker accounts. Use this to discover available subnets when configuring server groups or deployment targets. Returns JSON array of subnet objects with CIDR, availability zone, and VPC association.
pause_executionPause a running pipeline execution at the current stage boundary. Use this to temporarily halt a deployment for manual review before it continues to the next stage. The execution can be resumed later with resume_execution. Returns a confirmation message.
restart_stageRestart a specific failed or completed stage within a pipeline execution. Use this to retry a stage that failed due to a transient error without re-running the entire pipeline. Requires the execution ID and stage ID. Returns a confirmation message.
resume_executionResume a previously paused pipeline execution, continuing from where it was halted. Use this after pause_execution once the manual review or intervention is complete. Returns a confirmation message.
save_pipelineSave a new pipeline configuration to Spinnaker. Use this to create a brand-new pipeline definition — use update_pipeline instead to modify an existing one. Accepts a full pipeline JSON definition and returns a confirmation. This is a mutating operation that creates a new pipeline visible in the Spinnaker UI.
save_strategySave a new deployment strategy configuration to Spinnaker. Use this to create a reusable deployment strategy (e.g., red/black, rolling push, canary) — use delete_strategy to remove one. Accepts a full strategy JSON definition and returns a confirmation.
search_executionsSearch pipeline executions across an application with rich filters such as status, trigger type, and time range. Use this instead of list_executions when you need to find executions matching specific criteria. Returns JSON array of matching execution summaries.
trigger_pipelineTrigger a new pipeline execution with optional parameters. Use this to start a deployment, build, or any configured pipeline workflow. Returns the execution reference ID that can be passed to get_execution or list_executions to monitor progress. This is a mutating operation that starts a real pipeline run.
update_pipelineUpdate an existing pipeline configuration in Spinnaker. Use this to modify stages, triggers, or parameters of a pipeline that already exists — use save_pipeline instead to create a new one. Accepts a full pipeline JSON definition and returns a confirmation. This is a mutating operation that overwrites the current pipeline config.
BEFORE YOU INSTALL
37 tools when we connected. Writes include trigger_pipeline, save_pipeline, update_pipeline, delete_pipeline and cancel_execution.
npx on PATH
Both documented clients run the server on your machine.
CONTEXT COST
Rated by the size of the 37 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx spinnaker-mcp{
"mcpServers": {
"spinnaker": {
"command": "npx",
"args": [
"-y",
"spinnaker-mcp"
],
"env": {
"GATE_URL": "<YOUR_GATE_URL>",
"GATE_TOKEN": "<YOUR_GATE_TOKEN>"
}
}
}
}MCP servers
Daghis
NithishNithi
heniv96
bitrise-io