Guide · MCP servers
Claude MCP servers: the ones worth installing
Educational guide · updated June 2026.
# add a local (stdio) server
claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/projects
# add a remote (HTTP) server
claude mcp add --transport http pagelive https://app.pagelive.io/api/mcp
# inside Claude Code: list servers + finish OAuth
/mcpThe short answer
What are MCP servers?
MCP servers are programs that give Claude tools and data through the Model Context Protocol, an open standard for connecting AI assistants to outside systems. In Claude Code you add one with a single claude mcp add command; on claude.ai, remote MCP servers show up as connectors you enable in Settings.
One standard, two doors
MCP servers vs claude.ai connectors
| claude.ai connectors | MCP servers in Claude Code | |
|---|---|---|
| Where you use it | claude.ai (web, desktop, mobile) | Claude Code (terminal) and other MCP clients |
| How you add it | Customize → Connectors → enable or paste a URL | claude mcp add … or a shared .mcp.json |
| What runs | Remote, hosted MCP servers | Local (stdio) or remote (HTTP) servers |
| Auth | OAuth sign-in in the browser | OAuth via /mcp, env vars, or API keys |
| Protocol underneath | MCP, the same standard | MCP, the same standard |
Not a developer? The connector side has its own guide: Claude connectors, the list.
The list
Widely-used MCP servers for Claude
Filesystem
Read and write files in directories you allow (the reference server for local file access).
GitHub
Search repos, read code and issues, and manage pull requests from the conversation.
Google Drive
Search and read your Drive files so Claude can work from real documents.
Slack
Search messages and channels in your Slack workspace and draft updates with that context.
Postgres
Run read-only SQL queries against your database and inspect schemas.
Playwright / Puppeteer
Drive a real browser: navigate, click, fill forms, and take screenshots.
Sentry
Pull issues, errors, and stack traces from your Sentry projects for debugging.
Stripe
Search Stripe’s documentation and work with customers, products, and payments via the API.
Cloudflare
Manage Workers, DNS records, and account resources, and query docs and analytics.
Notion
Search, read, and update pages and databases in your Notion workspace.
Pagelive
Publish the HTML Claude builds as a live, tracked, noindex-by-default link, update it at the same URL, and read the comments people leave on it.
See the connector →Install pattern
How to add a server to Claude Code
# add a local (stdio) server
claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/projects
# add a remote (HTTP) server
claude mcp add --transport http pagelive https://app.pagelive.io/api/mcp
# inside Claude Code: list servers + finish OAuth
/mcpServers added with --scope project land in a shared .mcp.json, so the whole team gets them on checkout.
Publish & share what you build
The Pagelive MCP server, tool by tool
publish_page Publish an HTML document and get its link back.
update_page Change a page at the same URL, with targeted edits or a full rewrite.
list_pages List your pages with their links, folders and view counts.
get_page_stats Views, unique viewers and top countries for one page, plus which sections were read on Solo and Team.
list_form_submissions Read the replies sent through a form on a page.
create_recipient_link Give one person their own link, so their opens show under their name.
list_recipient_links The recipient links on a page, each with its opens and reading time.
list_comments Read the comments people left on a page, with the text or element each one points at.
create_comment Start a comment thread on a page, or an internal note only your team sees.
reply_comment Reply to a comment thread; the commenter gets it by email.
resolve_comment Mark a comment thread resolved once the page addresses it.
apply_suggestion Apply a suggested edit to the page and close its thread.
reopen_comment Reopen a resolved comment thread.
list_decisions Who approved a page and who requested changes, with their notes.
list_workspaces Your personal workspace and any teams, to publish into.
list_domains Your connected custom domains, to publish onto.
list_folders The folders in a workspace, with page counts.
create_folder Create a folder to group related pages.
move_page File a page into a folder, or back to the root.
It’s a remote server: https://app.pagelive.io/api/mcp. Add it to Claude Code with the command above, or one-click connect on claude.ai via Customize → Connectors. Setup details in the MCP quickstart; the bigger picture is on the connector page and publish from Claude.
Free for 2 public pages; Solo is $15/mo ($150/yr) for your own domain and full tracking. See pricing.
Claude MCP servers: FAQ
An MCP server is a program that gives Claude tools and data through the Model Context Protocol, an open standard for connecting AI assistants to outside systems like files, databases, browsers, and APIs. Claude calls the server’s tools during a conversation; the server does the work and returns the result.
They’re the same technology. A connector is claude.ai’s packaging of a remote MCP server: you enable it in Customize → Connectors and sign in with OAuth. In Claude Code you add servers yourself with claude mcp add, and you can also run local servers that work with your filesystem or database directly.
Run claude mcp add <name> -- <command> for a local server, or claude mcp add --transport http <name> <url> for a remote one. Then run /mcp inside Claude Code to check status and complete OAuth where needed. Project-level servers can be checked into .mcp.json so your team shares them.
It depends on the job. For most developers the staples are filesystem and GitHub access, a browser-automation server like Playwright or Puppeteer for testing, Sentry for debugging production errors, and a database server like Postgres for read-only queries. If you publish what you build, Pagelive turns Claude’s HTML output into a live, tracked link.
An MCP server can do whatever its tools allow with the access you give it, so treat servers like any dependency: install only from developers you trust, prefer official servers, and scope credentials narrowly (read-only database users, least-privilege API keys). Local servers run on your machine; remote servers authenticate with OAuth and can be disconnected at any time.
Prefer the claude.ai side? Start with Claude connectors. For Pagelive specifically: the connector · quickstart.