AgentHubAgentHub

Use cases/Cursor essentials

Essential MCP stack for Cursor

Starter stack for Cursor: files, GitHub, docs, browser—an AI coding workflow in minutes.

43,714 resources matched · Page 1 of 911

What is Cursor essentials?

Cursor ships first-class MCP support: paste a JSON block into Settings → MCP or .cursor/mcp.json in your project to connect any server. With AgentHub's 1-click config generator, discovery-to-running takes under a minute.

A solid starter stack covers four needs: Filesystem (project files), GitHub (PRs / issues / diffs), Context7 (fresh framework docs to curb hallucinations), and Playwright (browser verification and E2E).

Every resource listed here includes a Cursor-ready config snippet: open the resource page → Cursor tab → copy the JSON; install commands and auth env vars are provided alongside.

Good for

  • Full-stack dev
  • Open source
  • Learning frameworks
  • Small automation scripts

Not ideal for

  • Chat-only use cases
  • Locked-down corporate desktops
Common stack: Filesystem + GitHub + Context7 + Playwright

Related resources

Browse all →

GitHub

v1.2.5

SkillClawHub59819.3k

GitHub API integration with managed OAuth. Access repositories, issues, pull requests, commits, branches, and users. Use this skill when users want to interact with GitHub repositories, manage issues and PRs, search code, or automate workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a GitHub connection into automation, in the order they are used: the connection (the first step), a hosted function th

source
supabase-postgres-best-practices icon

supabase-postgres-best-practices

SkillGitHub431.8k

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.

source
neon-postgres icon

neon-postgres

SkillGitHub218.7k

Guides and best practices for working with Lakebase Postgres on Neon: connections, pooled vs direct, schema migrations, branching, autoscaling, scale-to-zero, instant restore, read replicas, IP allow lists, logical replication, and Lakebase Search. Use when the work is an existing DATABASE_URL, SQL, schema, inspect, or search. New backends, Auth, files, Functions, and LLM calls go to the parent `neon` skill. Also use for "@neondatabase/serverless", "@neondatabase/neon-js", "neon inspect db", "semantic search", "vector search", "full-text search", "BM25", or "hybrid search".

source

Playwright (Automation + MCP + Scraper)

v1.0.4

SkillClawHub1.3k43.9k

Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).

source

FAQ

Project-level or global MCP config in Cursor?

Both work: .cursor/mcp.json is shared with your team via the repo; ~/.cursor/mcp.json applies machine-wide. Keep secrets project-local or in env vars.

Do many MCP servers slow Cursor down?

Each enabled server injects tool definitions into context. Enable per project and disable unused servers to keep context for what matters.

Any Windows vs macOS differences?

Same JSON shape; differences are command paths and env-var quoting (npx vs absolute path). AgentHub resource pages distinguish stdio from remote (streamable-http/SSE) setups.

Setup guides for this scenario

Related scenarios

Essential MCP stack for Cursor - AgentHub