The verified map of the agent stack

Manage repositories, issues, pull requests, Actions and code search from your agent.

Create and look up customers, products, prices, invoices and payments, and search Stripe docs.

Search, read and update Notion pages and databases in the signed-in user's workspace.

Find, create and update Linear issues, projects and comments.

Pull Sentry issues, stack traces and events into the agent to debug production errors.

Manage Supabase projects: run SQL, apply migrations, inspect logs and generate types.

Give coding agents design context from Figma frames, components and variables.

Search and update Jira issues, Confluence pages, Loom and other Atlassian work.

Pulls current, version-specific library docs and code examples into the prompt.

Anthropic

17 skills

algorithmic-art, brand-guidelines, canvas-design, claude-api

OpenAI

38 skills

aspnet-core, chatgpt-apps, cli-creator, cloudflare-deploy

Vercel

9 skills

deploy-to-vercel, vercel-cli-with-tokens, vercel-composition-patterns, vercel-optimize

Hugging Face

25 skills

hf-cli, hf-cloud-aws-context-discovery, hf-cloud-python-env-setup, hf-cloud-sagemaker-deployment-planner

Cloudflare

16 skills

agents-sdk, basin, cloudflare, cloudflare-email-service

Supabase

2 skills

supabase, supabase-postgres-best-practices

Stripe

10 skills

connect-recommend, connect-required-verification-information, metronome, stripe-apps

Google

3 skills

gemini-api-dev, gemini-live-api-dev, gemini-omni-flash-api

Best MCP Servers in 2026 by Job: Scraping, Search, Browsers, Databases, Hosting, Monitoring, Payments, Auth and Design

Which MCP server should I use for web scraping, search, browser automation, databases, deploys, error tracking, payments, auth or design?

Web Scraping MCP Servers Compared (2026): Bright Data, Firecrawl, Apify, Tavily and Browserbase

Which web scraping MCP server should my AI agent use, and how do I set it up?

Web Search MCP Servers Compared (2026): Tavily, Exa, Brave Search, Perplexity, Parallel, SerpApi and Firecrawl

Which web search MCP server should my AI agent use, and how do I set it up?

Browser Automation MCP Servers Compared (2026): Playwright, Browserbase, Browserless, Browser Use, Bright Data and Chrome DevTools

Which browser automation MCP server should my AI agent use, and how do I set it up?

Database MCP Servers Compared (2026): Supabase, Neon, PlanetScale, Prisma Postgres, MongoDB, Redis, MotherDuck and ClickHouse

Which database MCP server should my AI coding agent use, and how do I keep it from breaking my data?

Deploy and Hosting MCP Servers Compared (2026): Vercel, Cloudflare, Railway, Cloud Run, Firebase, AWS and Netlify

Which deploy and hosting MCP server should my AI agent use, and how do I set it up safely?

Error Tracking and Observability MCP Servers Compared (2026): Sentry, Grafana, Honeycomb, New Relic, Axiom, Honeybadger, Dynatrace and PagerDuty

Which error tracking or observability MCP server should my AI agent use, what can it query or change, and how do I set it up?

Payments MCP Servers Compared (2026): Stripe, PayPal, Paddle, Square and Adyen

Which payments MCP server should my AI agent use, and how do I set it up safely?

Claude Code permissions: allow, ask and deny rules, rule syntax and allowed tools

How do Claude Code permissions work, and how do I allow or block specific tools?

The standard way to connect an agent to tools, data and services. One server works in every MCP client.

Lets independent agents discover each other, delegate tasks and stream results, whoever built them.

Portable folders of instructions, scripts and references that an agent loads only when a task needs them.

A README for coding agents: build steps, test commands and conventions in one file at the repo root.

Lets any editor drive any coding agent, the way LSP lets any editor use any language server.

Common building blocks for agents to discover products, build carts, check out and handle orders.