AWS CodePipeline MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | AWS region (e.g., us-east-1) | |
| AWS_PROFILE | No | AWS profile name for credentials | |
| AWS_ACCESS_KEY_ID | No | AWS access key ID | |
| AWS_SESSION_TOKEN | No | AWS session token (optional for temporary credentials) | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret access key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_pipelinesB | List all CodePipeline pipelines |
| get_pipeline_stateC | Get the state of a specific pipeline |
| list_pipeline_executionsC | List executions for a specific pipeline |
| approve_actionC | Approve or reject a manual approval action |
| retry_stageC | Retry a failed stage |
| trigger_pipelineC | Trigger a pipeline execution |
| get_pipeline_execution_logsC | Get logs for a pipeline execution |
| stop_pipeline_executionC | Stop a pipeline execution |
| get_pipeline_detailsC | Get the full definition of a specific pipeline |
| tag_pipeline_resourceC | Add or update tags for a pipeline resource |
| create_pipeline_webhookC | Create a webhook for a pipeline to enable automatic triggering |
| get_pipeline_metricsC | Get performance metrics for a pipeline |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Every tool has a clearly distinct purpose targeting specific CodePipeline operations with no ambiguity. For example, get_pipeline_details retrieves definitions while get_pipeline_state shows status, and list_pipeline_executions enumerates runs versus get_pipeline_execution_logs fetches logs. The descriptions reinforce non-overlapping functionality.
All tools follow a consistent verb_noun pattern with snake_case throughout, such as list_pipelines, get_pipeline_details, and stop_pipeline_execution. The naming is predictable and readable, making it easy for agents to infer functionality from the names alone.
With 12 tools, the server is well-scoped for managing AWS CodePipeline operations. Each tool earns its place by covering essential actions like listing, retrieving, triggering, stopping, and monitoring pipelines, without being overly sparse or bloated for the domain.
The tool set provides strong coverage for core pipeline workflows, including CRUD-like operations (list, get, trigger, stop) and lifecycle management (approve, retry, tag). A minor gap is the lack of tools for creating or deleting pipelines, which might require workarounds, but the existing surface supports most agent tasks effectively.