What Tekton resources does the server currently support?
The server initially supports `tektoncd/pipeline` objects: Pipelines, PipelineRuns, Tasks, TaskRuns, and StepActions. Support for other tektoncd projects will be added over time.
@tektoncd
Basic information
A Model Context Protocol server for the tektoncd projects
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This project provides a Model Context Protocol (MCP) server for the tektoncd projects, initially focusing on tektoncd/pipeline objects such as Pipelines, PipelineRuns, Tasks, TaskRuns, and StepActions. It will add support for other tektoncd projects over time. The server is intended for users who want to manage Tekton resources programmatically through an MCP-compatible client.
The README does not include explicit installation or configuration instructions. The server exposes a set of tools (functions) that can be invoked via an MCP client. Each tool requires parameters such as a namespace, resource name, or YAML definition. No specific command line or configuration key is mentioned.
kubectl usage.The server initially supports `tektoncd/pipeline` objects: Pipelines, PipelineRuns, Tasks, TaskRuns, and StepActions. Support for other tektoncd projects will be added over time.
List operations accept an optional `prefix` parameter for name filtering and an optional `label-selector` parameter. List operations for PipelineRuns and TaskRuns also support a `field-selector`.
Yes. The server integrates with Artifact Hub to search for tasks and pipelines, install them by package ID and version, and trigger them with parameters.
Use the `get_taskrun_logs` tool. It requires the name of the TaskRun and an optional namespace (default: “default”).
For `get_pipeline`, `get_task`, `get_pipelinerun`, and `get_taskrun`, you can specify `output` as either “json” or “yaml” (default: “yaml”).
Painless E2E Automation for Mobile and Web
不止于 CSS

Model Context Protocol Servers
Open-source MCP to use Blender with any LLM
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
Comments