国内 MCP 服务推荐（飞书 / 高德 / 12306）

Deploy and operate Node, Python, Go, Rust, Elixir, and Docker apps on Fly.io with production-grade fly.toml authoring, Machines API orchestration, region selection (latency vs sovereignty vs egress), Fly Postgres clustering, LiteFS for SQLite replication, Upstash Redis bindings, Tigris object storage, persistent volumes, WireGuard private networking with 6PN, secrets via flyctl, blue/green deploys via auto-stopping machines, scale-to-zero strategies, scheduled scaling, preview deploys per PR, multi-region replicas, hot-config reload, machine SSH, log shipping to Better Stack/Axiom/Datadog/Logtail, and aggressive cost tuning. Triggers on "fly.io", "flyctl", "fly machines", "fly.toml", "fly postgres", "litefs", "tigris", "upstash on fly", "fly deploy", "migrate from heroku", "migrate from render", "migrate from railway", "scale to zero", "fly regions", "fly volumes", "fly wireguard", "6pn", "fly secrets".

Run a repeatable RDF4J performance loop against one JMH benchmark in Docker with Linux Java 26 and JFR CPU-time profiling. Use when working in this repo on benchmark-guided performance changes, hotspot triage, JFR reading, CPU bottleneck analysis, or repeated baseline, fix, and rerun loops. Trigger on requests mentioning benchmark, profiling, JFR, hotspot, perf loop, CPU bottleneck, or Docker benchmark runs in RDF4J.

Manage Docker containers, images, volumes, and networks via the Docker CLI and Dockerode API

Deploy to Cloudflare Workers, Netlify, Vercel, Node.js/Docker, Bun, Railway. Selective SSR (ssr option per route), SPA mode, static prerendering, ISR with Cache-Control headers, SEO and head management.

Documents how to use Chrome DevTools MCP to navigate authenticated web pages, extract data (tokens, configuration values), take screenshots, and handle login flows. Use when you need to interact with Buildkite, AWS Console, or other authenticated web UIs via the Chrome browser. Triggers when users ask about "browser auth", "extract token from browser", "navigate to buildkite", "chrome mcp", or need to scrape data from authenticated pages.

App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklists, and tracking ranking changes.

Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows. NOT for testing — use playwright-pro for that.

Use when the user asks to write SQL queries, optimize database performance, generate migrations, explore database schemas, or work with ORMs like Prisma, Drizzle, TypeORM, or SQLAlchemy.

Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test.

Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: create a tour, onboarding tour, architecture tour, PR review tour, explain how X works, vibe check, RCA tour, contributor guide, or any structured code walkthrough request.

Use this skill when helping users add MCP servers to their Warp configuration.

Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.

Kubernetes expert for cluster ops, manifests, kubectl debugging, RBAC, networking, workloads, storage. Auto-loads when kubectl/k8s mentioned with an action verb. Do NOT trigger on incidental "service"/"pod"/"cluster" or Terraform/Helm-only questions. Keywords kubernetes, kubectl, k8s, deployment, ingress, gateway api, networkpolicy, rbac, kustomize.

Add or update workspace MCP servers using holaOS mcp_registry syntax.

REST API server and MCP protocol integration

Intakes existing content from external sources, classifies each chunk against the PAI destination taxonomy, and commits approved chunks with provenance. Sources: .md/.markdown/.txt, stdin, PAI TELOS/MEMORY/KNOWLEDGE dirs, CLAUDE.md/.cursorrules/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports, journal dumps. MigrateScan.ts chunks and classifies, producing a routing table with per-target counts and confidence %. MigrateApprove.ts approval loop: --approve-all, --approve-target, --review, --dry-run. UNCLEAR never bulk-approved. Phase 6 delivers summary and /interview recommendation for sparse areas. Confidence: ≥70% auto-approve; 40-70% confirm; <40% walk-through. Destinations: TELOS (MISSION/GOALS/PROBLEMS/STRATEGIES/CHALLENGES/BELIEFS/WISDOM/MODELS/FRAMES/NARRATIVES/SPARKS), IDEAL_STATE (per-dimension explicit call), preferences (BOOKS/AUTHORS/MOVIES/BANDS/RESTAURANTS/FOOD_PREFERENCES/LEARNING/MEETUPS/CIVIC), Identity (PRINCIPAL_IDENTITY.md — always prompts), Knowledge (MEMORY/KNOWLEDGE/{Ideas,P

Docker container management

Bring src/mobile/android to feature and behavior parity with src/mobile/ios while keeping each app native. Use when comparing iOS Swift/SwiftUI/UIKit mobile behavior against Android Kotlin/Jetpack Compose behavior, implementing missing Android features, or validating parity with the Test Android Apps emulator QA workflow.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.

Execute upgrade Cursor versions and migrate settings. Triggers on "upgrade cursor", "update cursor", "cursor migration", "cursor new version", "cursor changelog". Use when working with cursor upgrade migration functionality. Trigger with phrases like "cursor upgrade migration", "cursor migration", "cursor".

Use Cursor safely across editor, CLI, rules, background agents, Bugbot, and MCP workflows with repo-aware context and reviewable execution.

Headless browser automation via agent-browser — Rust CLI daemon with persistent auth profiles for fast, scriptable, parallel browser work. Supports batch commands, network interception, device emulation, per-site profile auth (one-time headed login, headless forever after), and parallel isolated sessions via --session. Workflows: ReviewStories (fan out YAML user stories to parallel UIReviewers), Automate (load/run parameterized recipe templates), Update. Delegates to general-purpose agents with agent-browser instructions for background parallel scraping. Falls back to Interceptor if site has bot detection. USE WHEN headless browser, batch scrape, fast screenshot, dev server test, parallel browser, background automation, extract data, review stories, automate recipe, batch screenshots, scrape multiple pages in parallel. NOT FOR deploy verification or UI confirmation with real Chrome (use Interceptor). NOT FOR simple single-URL fetching (use WebFetch). NOT FOR CAPTCHA or bot-detection bypass (use BrightData or

Scrape social media platforms, business data, and e-commerce via Apify actors — Instagram profiles/posts/hashtags/comments, LinkedIn profiles/jobs/posts, TikTok profiles/hashtags/videos/comments, YouTube channels/search/comments, Facebook posts/groups/comments, Google Maps business search with contact/review/image extraction, Amazon products/reviews/pricing, and general-purpose multi-page web crawling with custom pageFunction extraction logic. File-based TypeScript wrappers (scrapeInstagramProfile, searchGoogleMaps, scrapeAmazonProduct, scrapeWebsite, etc.) filter and transform data in code before returning to model context, achieving 95-99% token savings over direct MCP protocol. Parallel multi-platform queries via Promise.all for social listening dashboards. Lead enrichment pipeline: Google Maps → qualified filter → optional LinkedIn enrichment. Competitive analysis across Instagram, YouTube, and TikTok simultaneously. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Faceboo

Headless browser automation via agent-browser — Rust CLI daemon with persistent auth profiles for fast, scriptable, parallel browser work. Supports batch commands, network interception, device emulation, per-site profile auth (one-time headed login, headless forever after), and parallel isolated sessions via --session. Workflows: ReviewStories (fan out YAML user stories to parallel UIReviewers), Automate (load/run parameterized recipe templates), Update. Delegates to general-purpose agents with agent-browser instructions for background parallel scraping. Falls back to Interceptor if site has bot detection. USE WHEN headless browser, batch scrape, fast screenshot, dev server test, parallel browser, background automation, extract data, review stories, automate recipe, batch screenshots, scrape multiple pages in parallel. NOT FOR deploy verification or UI confirmation with real Chrome (use Interceptor). NOT FOR simple single-URL fetching (use WebFetch). NOT FOR CAPTCHA or bot-detection bypass (use BrightData or

Scrape social media platforms, business data, and e-commerce via Apify actors — Instagram profiles/posts/hashtags/comments, LinkedIn profiles/jobs/posts, TikTok profiles/hashtags/videos/comments, YouTube channels/search/comments, Facebook posts/groups/comments, Google Maps business search with contact/review/image extraction, Amazon products/reviews/pricing, and general-purpose multi-page web crawling with custom pageFunction extraction logic. File-based TypeScript wrappers (scrapeInstagramProfile, searchGoogleMaps, scrapeAmazonProduct, scrapeWebsite, etc.) filter and transform data in code before returning to model context, achieving 95-99% token savings over direct MCP protocol. Parallel multi-platform queries via Promise.all for social listening dashboards. Lead enrichment pipeline: Google Maps → qualified filter → optional LinkedIn enrichment. Competitive analysis across Instagram, YouTube, and TikTok simultaneously. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Faceboo

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "search for existing solutions before implementing" approach. Use when starting new features or adding functionality.

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

Kubernetes expert: kubectl, manifests, RBAC, networking, Helm, troubleshooting. Use when deploying to Kubernetes, writing manifests, or debugging K8s issues.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation, and MCP-backed skills that need a durable command path.

Work with Effect v4 / effect-smol TypeScript code in this repo

Generate safe, correct SQL scripts for the Rock RMS database. Handles INSERT, UPDATE, DELETE, SELECT queries, data migrations, and seed scripts that respect Rock's schema conventions (PersonAlias, audit columns, FK constraints, DefinedType/DefinedValue lookups, Guid-based references). Use when the user says "create a sql script", "write sql", "insert data", "seed data", "data migration", "update records", "sql for Rock", "populate data", "add test data", "query Rock database", or any request involving direct SQL against the Rock RMS database. Also use when the user describes data they want to add, modify, or query in Rock — even if they don't explicitly say "SQL" — such as "add 100 attendance records", "create a new campus", "give Ted Decker some financial transactions", or "set up check-in data". If the task involves Rock database records and SQL is the right tool, use this skill.

Run a repeatable RDF4J performance loop against one JMH benchmark in Docker with Linux Java 26 and JFR CPU-time profiling. Use when working in this repo on benchmark-guided performance changes, hotspot triage, JFR reading, CPU bottleneck analysis, or repeated baseline, fix, and rerun loops. Trigger on requests mentioning benchmark, profiling, JFR, hotspot, perf loop, CPU bottleneck, or Docker benchmark runs in RDF4J.

Build and customise Gradio themes. Use when creating, editing, or publishing Python-based Gradio themes that control colours, typography, spacing, shadows, and dark mode.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Optimizes SQL queries, designs database schemas, and troubleshoots performance issues. Use when a user asks why their query is slow, needs help writing complex joins or aggregations, mentions database performance issues, or wants to design or migrate a schema. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis, covering index creation, recursive queries, EXPLAIN/ANALYZE interpretation, before/after query benchmarking, or migrating queries between database dialects (PostgreSQL, MySQL, SQL Server, Oracle).

Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies, NetworkPolicies, storage configuration, performance optimization, GitOps pipelines, and multi-cluster management.

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.