advanced-circleci-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CIRCLE_TOKEN | Yes | Your CircleCI Personal Access Token |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_configA | Fetch the CircleCI config for a project's latest pipeline (or a specific pipeline). Returns source YAML (as written) and compiled YAML (after orb expansion). Use this as the starting point for any config review. |
| validate_configA | Validate and compile a CircleCI config YAML string. Returns whether the config is valid, any errors, and the fully-expanded output YAML (with orbs resolved). Use this to verify a proposed config change before recommending it. |
| get_bottlenecksA | Identify the slowest and most credit-intensive jobs across all workflows in a project. Fetches Insights data for every workflow, then for every job within each workflow, and returns results sorted by total_credits_used. Use this to find resource_class over-provisioning, unnecessary serialisation, and credit hot-spots. |
| get_workflow_healthA | Return a combined health report for a specific workflow: duration/success/MTTR metrics, slowest and most-failed tests, and flaky tests. Use this to evaluate test splitting opportunities, flakiness, and overall reliability. |
| get_dagA | Return the job dependency graph (DAG) for a pipeline or workflow. Includes job requires/dependencies lists and (when include_resource_class is true) the actual resource_class that was assigned. Use this to identify unnecessary serialization, missing requires, and executor sizing. |
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 5 tools
Each tool has a clearly distinct purpose: bottlenecks, config retrieval, DAG, workflow health, and validation. No overlap in functionality.
Four of five tools follow the 'get_' prefix pattern (get_bottlenecks, get_config, get_dag, get_workflow_health), but validate_config uses a different verb, creating a minor inconsistency.
With 5 tools, the set is compact and well-scoped for an advanced CircleCI analysis server, covering essential diagnostic and validation operations without unnecessary bloat.
The tools cover core analytical tasks (config, bottlenecks, DAG, health) and validation, but may lack operational tools like triggering pipelines or managing contexts, which is acceptable for the stated focus.