MCP-серверы

Official CircleCI MCP server. Lets AI agents fetch build and pipeline status, retrieve failed build logs, and diagnose flaky or broken jobs so developers can fix CI failures without leaving their AI-powered tools.

MCP server for Jenkins CI/CD. Enables AI agents to trigger builds, inspect job and build status, stream console logs, and diagnose failing pipelines, bringing continuous integration workflows into AI-powered development environments.

Microsoft's official MCP server for Azure DevOps. Brings Azure DevOps capabilities to AI agents, including managing work items and boards, browsing Git repositories and pull requests, querying builds and pipelines, and accessing wikis and test plans. Lets teams drive their Azure DevOps workflows through natural language from MCP-compatible tools.

Buildkite's official MCP server for querying and operating CI/CD pipelines, builds, jobs, artifacts, and organization-level delivery workflows.

Dagster's MCP integration enables agents to inspect and operate data assets, jobs, schedules, and runs in modern data platforms.

A powerful, native Go implementation of a Kubernetes MCP server with support for Kubernetes and OpenShift. Unlike kubectl wrappers, it interacts directly with the Kubernetes API server — no external CLI tools required. Distributed as a single lightweight binary for Linux, macOS, and Windows. Supports multi-cluster configurations, Helm chart management, Tekton pipelines, pod exec, log streaming, and optional OpenTelemetry distributed tracing.

Harness' official MCP server for connecting agents to software delivery workflows, including deployment pipelines, services, environments, and delivery insights.