woodpecker-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WOODPECKER_URL | No | URL of a Woodpecker CI instance (single instance configuration). | |
| WOODPECKER_TOKEN | No | Personal access token for the Woodpecker instance (required). | |
| WOODPECKER_SERVER | No | Alternative environment variable for the Woodpecker instance URL (official CLI variable). |
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 |
|---|---|
| list_instancesA | Lists the configured Woodpecker CI instances. Use |
| list_reposA | Lists repositories the token has access to on a Woodpecker instance. Returns repo ids usable with the other tools. |
| list_pipelinesA | Lists recent pipelines for a repository, newest first. Filter by branch, event or status to find e.g. the CI runs for a pull request branch. |
| get_pipelineA | Gets one pipeline with its workflows and steps (names, states, exit codes). Failed step ids are listed in |
| get_step_logsA | Fetches the log output of one pipeline step (use the step ids from get_pipeline). Returns the last |
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 targets a distinct resource: instances, repos, pipelines, pipeline details, and step logs. There is no overlap, and the descriptions clearly indicate the unique role of each tool.
Tool names follow a consistent list_/get_ convention, with plural nouns for collection listings (list_instances, list_repos, list_pipelines) and singular for item retrieval (get_pipeline, get_step_logs). The pattern is predictable and readable.
With five tools, the server is well-scoped for its purpose of inspecting Woodpecker CI instances, repositories, pipelines, and logs. Each tool fills a necessary role without redundancy.
The tool set forms a complete read-only workflow: from listing instances to listing repos, drilling into pipelines, getting pipeline details with step states, and fetching failed step logs. There are no dead ends or missing operations for the evident use case.