DevOps & CI/CD MCP servers

Generates Architecture Decision Records from Claude Code conversations, with quality review, duplicate detection, a dependency graph and stale ADR alerts.

Rust MCP server and CLI for Arcane Docker and container management.

Arcane Docker and Compose management over MCP and CLI with authenticated stdio and HTTP.

Wraps mcp-atlassian with Playwright SSO login to reach Atlassian Server/Data Center behind corporate SSO (Okta, SAML, ADFS) where API tokens are unavailable.

Read-only registry of animated companion packs (pets) for Codex: search, preview and install community pets and generate badges and embed cards.

Rust MCP server for homelab logs, syslog, Docker logs, FTS search, and AI transcript correlation.

C++26 paper reference backing a Claude Code plugin: paper lookup, fuzzy search and compiler support status over the ISO/IEC 14882:2026 corpus.

Host-level telemetry gateway letting sandboxed agents fetch container logs and track kernel resource metrics.

Look up SDKs, frameworks and dependencies used by macOS and Windows desktop apps, search by technology adoption and compare stacks via Desktop Insights.

Unified MCP server for Kubernetes, ArgoCD, Prometheus, PagerDuty, and Loki

Profiles how you use any MCP server into a reusable, read-only skill: workflows, call chains and each tool's safety class.

Version-aware docs for coding agents: finds llms.txt, OpenAPI and skill specs, resolves dependency versions, detects pitfalls and verifies code.

Workflow timing analysis, configuration audit and billing insight for GitHub Actions.

Query the Hirð compiler (typed actors on the BEAM): type inference, definition lookup, effect rows, IR fragments, actor protocols and supervision graphs.

CI for ink interactive-fiction stories: compiles, playtests every branch and finds runtime errors, unreachable knots and every distinct ending.

Enable AI agents to compile TeX files with LaTeX inside a Docker container.

Feedback loop for coding agents: CI monitoring, process watching, file change detection and HTTP polling.

NowSecure Platform mobile security testing: list applications, pull remediation findings and generate PDF reports locally.

Chat, generate, pull, list and inspect models with Ollama.

The largest Claude Code plugin marketplace. 500 plugins, 600+ developer tools in one MCP server. Security, testing, DevOps, CI/CD, databases, frontend, backend, API design, ML/AI, mobile, cloud, serverless, authentication, monitoring, and more.

Dynamic QR codes: create, update, track and retarget QR codes of various types without regenerating images.

AST-based codebase map, token compression and context packaging for AI coding agents and IDEs.

Read-only Nacos config and service discovery for Spring Cloud repos: finds environments from application/bootstrap files and diffs config keys across them.

A persistent Docker or Fly computer with a Three.js interface and optional live Xfce desktop.

Persistent pixel-art characters that reflect an agent's state in real time: report work state, mark tasks complete, signal errors and check status.

MCP server to create, read, update, list, and search GitHub Gists from your IDE

Build and edit Figma designs: JSX-like tree creation, variables and tokens, components, cross-page navigation and screenshot-based visual verification.

Model Context Protocol server for opn.onl — the open-source, self-hostable URL shortener. Lets AI assistants shorten links, read analytics, and manage links.

Audits website and API agent readiness: robots.txt AI rules, llms.txt, agent cards, MCP server cards and OAuth metadata, with maturity scores and fix plans.

Billing for MCP server operators: Stripe subscriptions, per-call credits, tiered pricing and x402 micropayments without writing billing code.

Local Python/TypeScript code graph: call tracing, multi-hop impact analysis, authz reachability audits, coupling metrics and architectural drift detection.

Code review via Groq: finds bugs, vulnerabilities and SQL injections, compares and explains code, generates tests and HTML reports.

Build smart-glasses apps: scaffold, validate and simulate Meta smart glasses integrations (camera capture, voice, audio) in Android and iOS apps.

Read-only static scanner that scores MCP and agent-gateway repos on RBAC, fail-closed behavior, supply chain, observability, cost and secrets handling.

GitLab CI/CD pipelines, jobs, schedules, merge requests and files, for GitLab SaaS or self-hosted instances.

Webhook callbacks for AI agents: create callback URLs, wait for signature-verified webhooks instead of polling, verify HMAC and list or replay callbacks.

Generate PWA, iOS and Android app icon sets from a text description with Google Imagen 4: all required sizes, maskable icons, splash screens and manifest.json.

Query Jaeger distributed tracing: list services and operations, search and fetch traces, and view service dependencies.

Multi-cluster Kubernetes monitoring and operations with safe access modes, namespace allowlists, gated delete/apply/exec, dry-run and audit logging.

Dead man's switch monitoring for AI agents, cron jobs and CI/CD pipelines: alerts when runs go silent, stall, fail or loop, with incident details.

LynxPrompt prompt management: create, search and organize AI prompts and AGENTS.md/CLAUDE.md configuration files.

Web design analysis: layout extraction, motion detection, quality scoring and semantic search, turning web pages into structured design knowledge.

Local, read-only scanner for GitHub Actions and CI maintenance issues in AI-built apps, with finding explanations and fix plans.

Checks source-context freshness against a Git working tree and retrieves source-linked code relationships to surface stale knowledge and cross-file impact.

VMware Avi Load Balancer (NSX ALB) management with AKO Kubernetes integration: virtual services, pools, analytics metrics and AKO lifecycle.

Semantic codebase search and persistent working memory: hybrid dense and BM25 search over AST-aware chunks, a symbol graph and notes that survive restarts.

Pin visual feedback on live web pages with the Yocoolab extension and hand it to coding agents with the element, selector and screenshot attached.

Design review of rendered UI for coding agents: submit a preview URL, get findings with element references and recheck after fixing. Read-only.