Best MCP Servers for Claude Code in 2026 (+ Exact Setup Commands)

Quick answer: The MCP servers worth connecting to Claude Code in 2026 are Filesystem, GitHub, Context7, and Playwright as the starter four, plus Supabase/Postgres if you have a database, and Sequential Thinking, Memory, Fetch and Sentry as situational additions. Remote servers install with claude mcp add --transport http <name> <url>; local ones with claude mcp add <name> -- npx -y <package>. Run 4 to 8 at a time, keep tokens in --env, and scope team servers to .mcp.json.

Skills make Claude Code consistent. MCP servers make it capable — they connect it to GitHub, your database, a browser, live docs, your error tracker. Connect a server whenever you catch yourself copying data into chat from another tool.

This is the servers-and-setup guide. For how skills and plugins work, see the skills & plugins guide; for project structure, the Claude Code projects hub.

Every claude mcp command below was verified against the official Claude Code MCP docs on 22 June 2026. Where a server's install varies (remote vs local, OAuth), I link its repo for the current exact line rather than risk a stale one.

Key Takeaways

• Starter four: Filesystem, GitHub, Context7 and Playwright cover file edits, repo work, accurate library docs and real browser verification.
• Two install shapes: Remote/HTTP uses claude mcp add --transport http <name> <url>; local/stdio uses claude mcp add <name> -- npx -y <package>.
• Keep the count low: Start with 4 to 8 servers and connect only what you actually use, even though Tool Search lazy-loads tool definitions by default.
• Scopes decide reach: --scope local is just you, --scope project writes a version-controlled .mcp.json that prompts each teammate for approval, --scope user applies across all your projects.
• Secrets go in --env: Pass tokens with --env, keeping at least one option between --env and the server name because of a CLI quirk.
• MCP is client-agnostic: The same server runs in Claude Code, Cursor and other MCP clients; only the registration command differs.
• Check the source for GitHub and Supabase: Their install lines vary between remote, OAuth and local, so take the current one from github/github-mcp-server and supabase/mcp.

What MCP is (in one paragraph)

The Model Context Protocol is an open standard for connecting AI tools to external systems. An MCP server exposes a system (GitHub, Postgres, a browser) as tools Claude can call. It's client-agnostic — the same server works in Claude Code, Cursor, and other MCP clients. Skills are knowledge; MCP servers are reach.

The MCP servers worth connecting

Curated and checked against live GitHub on 22 June 2026.

Server	What it does	Repo (stars)
Filesystem	Sandboxed read/write outside the working dir	modelcontextprotocol/servers (~88k)
GitHub	PRs, issues, code search, repo actions	github/github-mcp-server (~31k)
Context7	Live, version-specific library docs (less hallucination)	upstash/context7 (~58k)
Playwright	Real browser automation + E2E testing	microsoft/playwright-mcp (~34k)
Supabase / Postgres	Query tables, inspect schema, run migrations	supabase/mcp (~3k)
Sequential Thinking	Structured multi-step reasoning	modelcontextprotocol/servers
Memory	Persistent knowledge graph across sessions	modelcontextprotocol/servers
Fetch	Lightweight web content fetching	modelcontextprotocol/servers
Sentry	Pull error stack traces into a session	getsentry/sentry-mcp

The honest starter four: Filesystem + GitHub + Context7 + Playwright covers most real coding work — edit files, manage your repo, get accurate library docs, and verify in a real browser. Add Supabase/Postgres if you have a database.

Exact setup — the verified commands

There are two shapes: remote (HTTP) and local (stdio).

Remote / HTTP server (then authenticate with /mcp if it uses OAuth):

claude mcp add --transport http <name> <url>
# real example from the docs:
claude mcp add --transport http stripe https://mcp.stripe.com

Local / stdio server — everything after -- is the command that runs the server:

# Context7 — live library docs
claude mcp add context7 -- npx -y @upstash/context7-mcp

# Filesystem — give it the path it may touch
claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/projects

# Playwright — browser automation
claude mcp add playwright -- npx @playwright/mcp@latest

# Sequential thinking
claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking

Passing secrets — use --env, and keep at least one option between --env and the name (the CLI quirk):

claude mcp add --env SOME_TOKEN=xxxx --transport stdio myserver -- npx -y some-mcp-server

Complex config — add-json (the type accepts streamable-http as an alias for http):

claude mcp add-json context7 '{"type":"stdio","command":"npx","args":["-y","@upstash/context7-mcp"]}'

Manage them:

claude mcp list            # all servers + status
claude mcp get context7    # details (or ⏸ Pending approval / ✗ Rejected)
claude mcp remove context7

In a session, /mcp shows tool counts per server, lets you authenticate OAuth servers, and reconnects dropped ones (HTTP/SSE auto-reconnect with backoff; stdio doesn't).

For GitHub and Supabase specifically, the current install (remote, OAuth, or local) is best taken from the source — see github/github-mcp-server and supabase/mcp. The claude mcp add shape is the same; only the URL/package differs.

Scopes — where the config lives

• --scope local (default) — just you, this project.
• --scope project — writes to a version-controlled .mcp.json so your team gets it. Claude Code prompts each user for approval before using project servers (a security feature; reset with claude mcp reset-project-choices).
• --scope user — available across all your projects.

claude mcp add --transport http stripe --scope project https://mcp.stripe.com

Keeping many servers without context bloat

• Tool Search is on by default — Claude Code lazy-loads tool definitions instead of dumping them all into context, so a few servers cost far less than they used to. (Disable only if you must, via ENABLE_TOOL_SEARCH=false.)
• Start with 4–8, not 20. Connect what you use.
• Prefer read-only configs where a server supports it.
• Keep tokens in --env, never in chat.
• Scope deliberately — project servers for the team, user scope for your always-on tools.

Put it to use

• Wire MCP into a properly structured project: the Claude Code projects hub.
• Pair it with the right skills: the skills & plugins guide.
• New to the tool? The beginner tutorial.
• Built something with a slick MCP stack? List it free on SaaSCity.

FAQ

How do I add an MCP server? Remote: claude mcp add --transport http <name> <url>. Local: claude mcp add <name> -- npx -y <package>. Manage with claude mcp list/get/remove or /mcp.

How many should I run? 4–8 to start. Tool Search (default on) keeps the context cost low, but connect only what you use.

Are they safe? They access real systems — prefer read-only, trust the source, keep tokens in --env, and review project-scoped servers before approving.

Cross-client? Yes — MCP is an open standard; the same server works in Claude Code, Cursor, and other MCP clients.