"Servers Offering MCP Prompts as Prompt Primitives" matching MCP servers:

A modular MCP server that extends GitHub Copilot's capabilities through intelligent context compression and dynamic model routing for long-lived coding sessions.

A Model Context Protocol server for Bitbucket Cloud that lets agents read pull request diffs, comments, and pipeline logs, as well as write PR comments and edit PR details.

Enables MCP clients to score retrieval quality with recall, precision, nDCG, hit rate and MRR, compare 2-3 configurations with seeded paired-bootstrap confidence intervals, audit agent tool calls against expected traces, and detect prompt regressions against golden sets. It also generates Markdown, JSON or JUnit reports with pass/fail gates, all deterministically and offline without paid API keys.

MCP server for JetBrains Space merge requests and Patronus CI dry runs, enabling creation, viewing, and management of merge requests as well as starting and monitoring CI dry runs.

Post-quantum readiness for AI coding agents: scans code for quantum-vulnerable cryptography (RSA/ECDH/ECDSA/DH) and returns NIST ML-KEM/ML-DSA/SLH-DSA (and hybrid) migration guidance, with fix verification and dependency checks. Content-based, advisory tools only; runs local (npx @quantakrypto/mcp) or as a hosted OAuth endpoint.

MCP server for CodeRocket Deploy providing AI-generated CI/CD workflows and AI code review as tools inside Claude Code.

Lets MCP clients such as Claude or ChatGPT find the pull requests waiting on your review, read their details and changed files, check CI status, post comments, and submit approve, request-changes, or comment reviews. It runs locally over stdio with a personal token or as a remote server with its own OAuth 2.1 authorization server (PKCE, dynamic client registration, per-client consent, and refresh-token rotation) so GitHub is only used to sign the user in.

Enables AI coding assistants to distribute iOS and Android builds to BetaDrop testers, manage share links, track releases, and manage API tokens entirely through natural language prompts.

Generates comprehensive API test plans (positive, negative, and boundary cases) from endpoint metadata and exports them as Excel files.

A local MCP server that packages LLM evaluation gates as reusable CI/CD primitives, enabling AI agents to run datasets against models, score responses, and enforce quality thresholds.

Enables real-time assessment of GitHub repository health by exposing tools and resources for repository metadata, open issues, recent commits, and GitHub Actions workflow runs, plus prompts for health reports and issue triage.

MCP server for Codecov that provides tools to get commit coverage totals and prompts to suggest tests to write.

MCP server for managing Netlify sites, enabling operations such as creating sites from GitHub repositories, listing, viewing details, and deleting sites.

Enables agents to inspect and manage Hydra CI instances, including projects, jobsets, evaluations, builds, logs, queues, and authenticated actions such as triggering evaluations, controlling builds, and editing projects and jobsets.

Self-hosted coding agent that runs Claude Code or Codex in your own infrastructure and works from Slack. Exposes codebase investigation, file edits, branch and PR creation, allowlisted command execution, CI status and an audit log as MCP tools, keeping every credential behind the tool layer instead of handing it to the model.

Exposes GitHub Actions state as four compact, read-only tools for triaging CI failures, letting agents answer why CI is red without leaving the chat.

Enables AI assistants to interact with Argo CD through its REST API, providing tools to triage application status, sync, roll back, inspect drift, read logs, and manage ApplicationSets, clusters, projects, and repositories. Supports read-only safeguards, curated GitOps resources, and workflow prompts for safe operations.

Enables inspecting local Git repositories and automating delivery tasks such as status checks, diffs, commits, pull requests, and deployments using git and GitHub CLI.

Enables LLM clients to access DevSecOps tooling such as CI/CD pipeline status, vulnerability triage, log search, and dependency scanning through MCP, turning AI copilots into security-aware engineering partners.

An MCP server for Azure DevOps that allows users to manage work items, sprints, iterations, and attachments. It supports custom WIQL queries and includes pre-defined prompts for common tasks like sprint planning, bug reporting, and daily standup generation.

Enables AI coding agents to drive developer workflows as BPMN processes on a local CIB seven engine, including starting releases, inspecting runs, and approving human-decision gates via MCP tools.

Datadog MCP — 165 tools for metrics, monitors, logs, APM, RUM, incidents, CI/CD, fleet automation. Includes incident-triage-snapshot aggregation tool and 4 workflow Prompts.

Enables AI agents to deploy applications to AWS with DevOps capabilities by automatically inferring infrastructure needs from code and generating inspectable Infrastructure as Code specifications.

Enterprise-grade MCP server exposing Ansible Automation Platform 2.x as a complete AI interface for LLMs, enabling natural language management of automation resources.

Enables SSH-based deployment operations such as git pull, command execution, script upload/run, and SSH config management.

Enables management of App Store Connect operations such as listing apps, managing builds, submitting for review, and handling in-app purchases through Claude Code.

Exposes Makefile targets as MCP tools, allowing AI agents to execute project automation tasks like build, test, and deploy through natural language.

A production-ready MCP server template that enables developers to quickly build and deploy MCP servers with dynamic tool/resource loading, YAML-based prompts, and seamless OpenShift deployment. Supports both local development with hot-reload and production HTTP deployment with optional JWT authentication.

MCP server that integrates GauntletCI to analyze behavioral change risk in commits, providing findings as text, JSON, or SARIF reports for AI assistants.

Security scanner and MCP server that catches dangerous patterns in MCP servers and AI agent projects, such as leaked secrets, shell execution, and prompt-injection text. Runs as both a CLI and MCP server with CI-friendly severity gates.