Comparison · November 16, 2026

Best MCP Servers in 2026: 14 Picks, Measured and Vetted

The official MCP registry lists 64,116 active servers. You need about four. Here are the 14 worth knowing, grouped by job, with the context cost and the safety switch for each, plus what our census of the registry turned up.

TL;DR
The best MCP servers for most developers are Context7, GitHub, and Playwright, plus Sentry and a read-only database server when you need them. Pick by job, install three to five, and vet each one: 58 tools can eat about 55,000 tokens of context, and 18 registry entries carry the Notion name while only one comes from Notion.

Every list of the best MCP servers names the same ten tools. None of them measures anything.

The best MCP servers in 2026 are the ones that do one job well, come from the vendor that owns the data, and cost little context. For coding that means Context7, GitHub, and Playwright. For data work it means a read-only database server and one search server. Marketing teams can now add GA4, DataForSEO, and AI visibility servers to the same agent.

Best MCP servers in 2026, measured: the official MCP registry held 64,116 active servers on November 16, 2026; Anthropic measured 58 tools from five servers at about 55,000 tokens of context; 18 active registry entries use the Notion name and one is published by Notion.

I did two things the other lists skip. On November 16, 2026, I pulled every entry in the official MCP registry through its public API, 652 pages of it. I also measured the tool definitions of one server end to end, so the context numbers below come from data I collected.

Disclosure: we build MentionsAPI, and its MCP server is one of the 14 picks. It sits in the marketing section, where it belongs, and I describe it the same way as the others.

How I picked the best MCP servers

I picked each MCP server on four tests: it does one clear job, the company that owns the data publishes it, it has a safety switch such as read-only mode or OAuth scopes, and its tool definitions are small enough to keep loaded. Popularity alone did not count, because the registry is full of near-identical names, and a popular wrapper from an unknown publisher fails the second test.

I checked every install path, URL, and price against the vendor's own repo or docs on November 16, 2026. Where a vendor publishes no price, I say so.

I also left things out on purpose. Several famous servers from the original reference repo, including GitHub, Slack, Postgres, and Sentry, are now archived there, according to the MCP servers repository. The vendors now publish their own versions, and those are what I list.

What are the best MCP servers right now?

The best MCP servers right now are GitHub, Context7, Playwright, Sentry, and Filesystem for coding, Supabase and Postgres MCP Pro for databases, Exa and Firecrawl for the web, Linear and Notion for team tools, and Google Analytics, DataForSEO, and MentionsAPI for marketing data. The table below shows who publishes each one, how it connects, and the setting to turn on first.

ServerJobConnects viaTurn on first
GitHubRepos, issues, PRsRemote or localRead-only, fewer toolsets
Context7Current library docsRemote or localFree API key for limits
PlaywrightBrowser testingLocal (npx)Separate browser profile
SentryProduction errorsRemote, OAuthScope to one project
FilesystemLocal filesLocalAllow only named folders
SupabasePostgres + backendRemote, OAuthread_only and project_ref
Postgres MCP ProAny PostgresLocalRestricted access mode
ExaWeb searchRemoteDefault tools only
FirecrawlScraping pagesRemote or localAllowed hosts list
LinearIssuesRemote, OAuthRead-only endpoint
NotionDocs and wikisRemote, OAuthShare fewer pages
Google AnalyticsGA4 reportsLocal or HTTPRead-only is default
DataForSEOSEO dataRemote, OAuthDaily spend limit
MentionsAPIBrand visibility in AI answersRemote, OAuthCached checks first
The 14 best MCP servers grouped by job: coding (GitHub, Context7, Playwright, Sentry, Filesystem), data (Supabase, Postgres MCP Pro, Exa, Firecrawl), team tools (Linear, Notion), and marketing (Google Analytics, DataForSEO, MentionsAPI).
Pick one or two per job you actually do.

Best MCP servers for coding agents

GitHub, Context7, and Playwright are the best MCP servers for coding agents in Claude Code, Cursor, or Codex. GitHub handles repository work, Context7 supplies current documentation, and Playwright checks the UI in a real browser. Add Sentry when you debug production errors, and the reference Filesystem server when your client has no file access of its own.

GitHub MCP server

The official GitHub server reads and writes issues, pull requests, and code. Connect remotely at api.githubcopilot.com/mcp/ or run it locally.

It is also the heaviest server here. In Anthropic's example setup, its 35 tools took about 26,000 tokens. Load only the toolsets you need with --toolsets, and add --read-only until you trust the agent.

Context7

Context7, from Upstash, fetches current, version-specific docs for the library you are using. It cuts the most common coding-agent failure: confident code written against an API that changed last year.

It exposes two tools, resolve-library-id and query-docs, so its context cost is small. A free API key from the Context7 dashboard raises its rate limits. If you install only one server, make it this one.

Playwright MCP

Microsoft's Playwright MCP drives a browser through accessibility snapshots instead of screenshots, which keeps it fast and works with any model. Install it with claude mcp add playwright npx @playwright/mcp@latest.

One catch: Microsoft's server is not in the official registry, while 15 other entries use the Playwright name. Install it from Microsoft's repo or npm, not from a search result.

Sentry MCP

Sentry's server lets the agent read real stack traces and issues before it guesses at a fix. Connect to mcp.sentry.dev/mcp with OAuth, and scope it to one organization and project.

Filesystem

The Filesystem server is one of seven reference servers still maintained by the MCP steering group. Use it in clients without built-in file access, and pass only the folders the agent should touch.

Best MCP servers for databases and web data

Use Supabase's hosted server or Postgres MCP Pro when the agent needs your database, and Exa or Firecrawl when it needs the web. Run database servers read-only by default, because an agent with write access to production is one bad prompt from a deleted table. Pick one web server: Exa for finding pages, Firecrawl for reading them in full.

Supabase MCP

Supabase hosts its server at mcp.supabase.com/mcp with OAuth sign-in. Add read_only=true and project_ref to the URL, and the agent can query one project's schema and data without changing it.

Postgres MCP Pro

For any other Postgres, Crystal DBA's Postgres MCP Pro adds health checks and index tuning to plain queries. Run it with --access-mode=restricted for read-only transactions with a time limit.

Exa

Exa is a search engine built for agents. Its remote server at mcp.exa.ai/mcp exposes web search and page fetch by default, and the free tier gives $10 in credits each month with no card.

Firecrawl

Firecrawl turns pages into clean markdown. Its pricing page lists 1,000 free credits a month, then $19 a month for 5,000, at one credit per scraped page.

Best MCP servers for team tools

Linear and Notion are the best MCP servers for team tools. Both now host official remote servers with OAuth, so there is no key to paste and no local process to run. They let an agent read the ticket or spec behind a task before it writes code. Start both read-only and widen access later.

Linear runs at mcp.linear.app/mcp and offers a separate read-only endpoint, according to Linear's MCP docs. Notion runs at mcp.notion.com/mcp, and Notion says its older open-source server is no longer maintained.

That second point matters in the registry. Searching for Notion returns 18 active entries, and only one, com.notion/mcp, comes from Notion.

Best MCP servers for marketing, SEO, and AI visibility

The best MCP servers for marketing work are the Google Analytics server for GA4 reports, DataForSEO's server for keyword, SERP, and backlink data, and MentionsAPI for checking whether AI engines mention and cite a brand. Few lists cover this category. In our census, only 584 of 64,116 active registry entries mention SEO at all.

Google Analytics MCP

The Google Analytics MCP server is read-only by default and signs in with your Google Cloud credentials. Writes need an explicit --allow-write flag. Google has no official Search Console server yet, so treat the community ones with care.

DataForSEO MCP

DataForSEO's official server connects at mcp.dataforseo.com/v3/mcp. It exposes a docs search and one general api_request tool, so the agent can call any DataForSEO endpoint.

Accounts need a $50 minimum top-up after a $1 trial credit, per DataForSEO's pricing page. Set a daily spending limit before you hand it to an agent.

MentionsAPI MCP

Our server checks whether ChatGPT, Claude, Gemini, Perplexity, and Google's AI surfaces mention, rank, and cite a brand for a prompt. It has four tools: mentions_check, mentions_watch, mentions_discover, and mentions_compare.

Add the remote server at api.mentionsapi.com/mcp as a custom connector with OAuth, or run the npm package locally. A quick check costs 150 credits fresh or 5 when cached, and signup includes 300 free credits.

If you are not sure which prompts to check, our AI visibility audit guide shows how to build the prompt set first.

How many MCP servers should you install?

Install three to five MCP servers for daily use. In clients that load tools up front, each server puts its tool names, descriptions, and input schemas into the model's context before you type a word, and Anthropic measured 58 tools from five servers at about 55,000 tokens. Past that point you pay for unused tools on every request, and the model picks the wrong tool more often.

Tool counts vary more than server counts. In Anthropic's measurement, GitHub's 35 tools took about 26,000 tokens and Slack's 11 tools about 21,000. Sentry's five took about 3,000.

I measured our own server the same way, by listing its tools over stdio. The four tool definitions came to 2,864 characters, roughly 700 tokens at four characters per token.

Context tokens used by MCP tool definitions before the first message: GitHub 35 tools about 26,000 tokens, Slack 11 tools about 21,000, Sentry 5 tools about 3,000, Grafana 5 tools about 3,000, Splunk 2 tools about 2,000 (Anthropic, November 2025), and MentionsAPI 4 tools about 700 (measured November 16, 2026).
Context spent on tool definitions before the first message.

Clients are starting to load tools on demand instead of all at once. With Anthropic's tool search enabled, Claude Opus 4.5 picked the right tool 88.1% of the time on a large tool library, up from 79.5% without it.

Claude Code already works this way. Its MCP docs say tool search is on by default, so MCP tool definitions are deferred and discovered when needed.

Other clients may still load every definition up front, so trim by hand there. Keep a short default list, enable project-specific servers in that project's config, and switch off toolsets you never call.

Deferred loading fixes the context bill. The other costs stay: every extra server is another publisher to trust and another set of tools the model can pick by mistake.

For heavy data work, Anthropic suggests a different pattern: let the agent write code that calls MCP tools and filters results before they reach the model. In its example, that cut one workflow from 150,000 tokens to 2,000.

~55Ktokens for 58 tools from five servers (Anthropic, 2025)
~700tokens for the four MentionsAPI tools (our measurement)
88.1%tool-pick accuracy with tool search, from 79.5% (Anthropic)

Are MCP servers safe? How to vet one before you install it

MCP servers are as safe as their publisher and the permissions you grant them. A study of 1,899 open-source servers found 5.5% with MCP-specific tool poisoning, where hidden instructions sit inside a tool description. A 2026 scan of 7,973 live remote servers found 40.55% exposed tools without any authentication. Vet every server before it reaches your agent.

The first figure comes from Hasan and colleagues, who also found general vulnerabilities in 7.2% of servers. The second comes from Zhou and colleagues, published in May 2026.

Clients do not catch much either. A March 2026 study of seven MCP clients found that five ran no static validation on tool descriptions.

Here is the five-minute check I run before adding any server:

  1. Match the publisher to the vendor. In the registry, com.notion/mcp is Notion; com.mcparmory/notion is not.
  2. Prefer the vendor's hosted endpoint with OAuth over a third-party package holding your key.
  3. Read every tool description before connecting, since that is where poisoned instructions hide.
  4. Turn on read-only mode, scopes, or allowed folders first, then widen them.
  5. Pin the package version in shared team configs, so an update cannot change tools silently.
  6. Check that the repo is still maintained and not one of the archived reference servers.
  7. Remove servers you stopped using, since each one is attack surface and context cost.
Five-minute MCP server vetting checklist: match publisher to vendor, prefer hosted OAuth endpoints, read tool descriptions, start read-only or scoped, pin versions in team configs, confirm the repo is maintained, and remove unused servers. Risk figures: 5.5 percent of 1,899 open-source servers had tool poisoning; 40.55 percent of 7,973 live remote servers exposed tools without authentication.
Run it once per server, and again after major updates.
The MCP specification makes authorization optional. HTTP servers should follow the spec's OAuth 2.1 flow, but nothing forces them to, so check for sign-in before you trust a remote URL.

What our census of the official MCP registry found

The official MCP registry held 65,157 server entries on November 16, 2026, of which 64,116 were active. Most are new: 56.5% of active entries had their current version published after October 1. The registry proves a server exists and who published it. It does not rank, review, or security-check anything, so it is a phone book, not a buyer's guide.

Remote servers now dominate. 68.2% of active entries offer a hosted endpoint, against 38.1% that ship a package, mostly on npm (16,935) and PyPI (5,261).

A few publishers produce a large share. The registry has 39,825 publisher namespaces, yet the top 10 account for 16.2% of all active entries, and the largest single publisher lists 2,366 servers.

Census of the official MCP registry on November 16, 2026: 65,157 entries, 64,116 active and 1,041 deprecated; 68.2 percent offer a remote endpoint and 38.1 percent ship a package; 56.5 percent of active entries were published or updated after October 1; the top 10 of 39,825 publishers hold 16.2 percent of entries; 18 entries use the Notion name and one is from Notion.
Pulled through the registry's public API, 652 pages, November 16, 2026.

Interest is still running ahead of use. Postman's 2025 State of the API report found 70% of developers aware of MCP but only 10% using it regularly.

The registry tells you a server exists. It never tells you the server is the real one.What the census taught me
Give your agent AI visibility data in one connector
Add the MentionsAPI MCP server to Claude, Cursor, or Windsurf and check whether ChatGPT, Claude, Gemini, Perplexity, and Google's AI surfaces mention and cite your brand. 300 free credits, no card.

Which MCP servers to start with, by role

Pick a starter stack by the work you do. A solo developer needs docs, repos, and a browser. A product team adds tickets and errors. A marketing engineer swaps the browser for analytics, SEO, and AI visibility data. Each stack below stays at four servers or fewer, and each server has one narrow job, so you always know which tool the agent should reach for.

RoleStarter stackWhy
Solo developerContext7, GitHub (read-only), PlaywrightCurrent docs, repo context, and a way to check the UI
Product teamGitHub, Linear, Sentry, Supabase (read-only)Ticket to fix with real errors and schema
Research agentExa or Firecrawl, NotionFind sources, read them, and save notes
Marketing engineerGoogle Analytics, DataForSEO, MentionsAPITraffic, search data, and AI answer visibility
MCP server starter stacks by role: solo developer uses Context7, GitHub read-only, and Playwright; product team uses GitHub, Linear, Sentry, and Supabase read-only; research agent uses Exa or Firecrawl and Notion; marketing engineer uses Google Analytics, DataForSEO, and MentionsAPI.
Three or four servers per role, each with a narrow job.

How to add a server in Claude Code or Cursor

In Claude Code, add a hosted server with one command, for example claude mcp add --transport http notion https://mcp.notion.com/mcp. Add --scope project to write it to a .mcp.json file you can commit for your team.

Run claude mcp list to see what is connected, and /mcp inside a session to check status and sign in to OAuth servers.

In Cursor, put the same server in .cursor/mcp.json for one project or ~/.cursor/mcp.json for every project, with the endpoint under a url key. Use the project file for anything a teammate should inherit.

For a worked example of the marketing stack, our guide to building an AI brand-visibility agent in Claude Code wires the MentionsAPI server into a standing agent step by step.

Frequently asked questions

What are the best MCP servers for Claude Code?
For most developers, start with three: Context7 for current library docs, the official GitHub MCP server for repos and pull requests, and Microsoft's Playwright MCP for browser testing. Add Sentry if you debug production errors, and a database server in read-only mode if your agent needs your schema. Add marketing or search-data servers only when a task needs them.
How many MCP servers should I install?
Three to five for daily use. Clients that load tools up front put every definition into the context window, and Anthropic measured 58 tools across five servers at about 55,000 tokens. Claude Code defers tool definitions by default, but more servers still mean more publishers to trust and more tools to confuse. Keep a small default set and enable the rest per project.
Are MCP servers safe to install?
They are as safe as the publisher and the permissions you grant. A 2025 study of 1,899 open-source servers found 5.5% had tool-poisoning issues, and a 2026 scan found 40.55% of live remote servers exposed tools without authentication. Use vendor-published servers, prefer OAuth, start read-only, and read the tool descriptions before you connect.
What is the difference between an MCP server and an API?
An API is an interface your code calls. An MCP server wraps one or more APIs as tools that an AI client such as Claude Code or Cursor can discover and call on its own, with names, descriptions, and input schemas the model reads. Most MCP servers call the vendor's API underneath, so you usually need an account and key either way.
Do MCP servers cost money?
The protocol and most servers are free, but many call paid services. Firecrawl gives 1,000 free credits a month and Exa gives $10 in free monthly credits, then both charge per use. DataForSEO needs a $50 minimum top-up. Context costs money too, since every tool definition adds input tokens to each request your agent makes.
Is there an MCP server for SEO or tracking brand mentions in ChatGPT?
Yes. DataForSEO publishes an official MCP server for keyword, SERP, and backlink data, and a Google Analytics MCP server exposes GA4 reports. For brand visibility in AI answers, the MentionsAPI MCP server checks whether ChatGPT, Claude, Gemini, Perplexity, and Google's AI surfaces mention and cite a brand. Google has no official Search Console MCP server yet.

Install three servers this week, then measure

Start with the three MCP servers that match your daily work, in read-only mode, from the vendor's own namespace. Run the five-minute vetting check on each one before you connect it. After a day, open /mcp or your client's equivalent and look at what each server costs you. Add a fourth server only when a real task fails without it.

The registry will keep growing faster than anyone can review it. A short, vetted list will serve you better than any count.

Nikhil Kumar
Founder, MentionsAPI

Growth marketer at the intersection of marketing, product, and technology. 8+ years across startups and scale-ups in India, Switzerland, and the Netherlands. Founder of Landkit (landkit.pro).

Put AI visibility data inside your agent.

Connect the MentionsAPI MCP server and ask whether ChatGPT, Claude, Gemini, Perplexity, and Google's AI surfaces mention and cite your brand. 300 free credits, no card.