Top 10 MCP Servers 2026: Most Starred, Not Most Downloaded

Context7, Chrome DevTools MCP and codebase-memory-mcp lead the 10 most starred MCP servers on GitHub on 17 November 2026, while Playwright MCP leads weekly npm downloads: stars, downloads and what each server does, chosen by a stated rule over 514 repositories.

By TopCitedPublished
Back to Blog

Context7, Chrome DevTools MCP, codebase-memory-mcp, Playwright MCP, MCP for Blender, GitHub MCP Server, Serena, n8n-MCP, xiaohongshu-mcp and MCP Toolbox for Databases were the 10 most starred MCP servers on GitHub on 17 November 2026, while Playwright MCP led weekly npm downloads among them. The ranking uses GitHub API records and a stated selection rule applied to 514 active repositories. npm API download counts appear alongside the stars as a separate measure.

GitHub stars measure attention, not use or quality. Ranked by weekly npm downloads instead, the order changes: Playwright MCP, fourth by stars, was installed 10,698,162 times in a week, four times as often as Chrome DevTools MCP and more than nine times as often as Context7. The comparison below keeps those measures separate.

What are the top 10 MCP servers by GitHub stars in 2026?

RankServerGitHub starsnpm downloads/weekLanguageWhat it does
1Context765,0111,166,420TypeScriptCurrent library docs and code examples
2Chrome DevTools MCP58,0072,648,086TypeScriptChrome DevTools: debugging, network, performance
3codebase-memory-mcp48,7749,610CPersistent code knowledge graph
4Playwright MCP39,79910,698,162TypeScriptBrowser control via accessibility tree
5MCP for Blender34,801not publishedPython3D modelling and scenes in Blender
6GitHub MCP Server34,546not publishedGoRepos, issues, pull requests, Actions
7Serena31,481not publishedPythonSemantic code retrieval and editing
8n8n-MCP23,27541,928TypeScriptBuild and debug n8n workflows
9xiaohongshu-mcp17,182not publishedGoSearch and post on Xiaohongshu (RedNote)
10MCP Toolbox for Databases16,89754,434GoDatabase queries and tools

Star counts were read on 17 November 2026 at 20:43 UTC. npm counts cover the week 2026-11-10 to 2026-11-16. Both move daily, so treat the table as a dated snapshot, not a standing fact.

What does each of the top 10 MCP servers do?

1. Context7 — current library documentation and code examples

Context7 ranks first with 65,011 stars. It serves current documentation and code examples for a library into the model's context, so an agent writing against a framework gets that framework's present API rather than a recalled one. Created 2025-03-26. 1,166,420 weekly downloads.

2. Chrome DevTools MCP — browser debugging and performance analysis

Chrome DevTools MCP ranks second with 58,007 stars. It is the Chrome DevTools team's server and lets a coding agent control and inspect a live Chrome browser for automation, debugging and performance analysis. It is also available as a CLI. Created 2025-09-11, the second-newest in the top 10, and 2,648,086 weekly downloads.

3. codebase-memory-mcp — a persistent code knowledge graph

codebase-memory-mcp ranks third with 48,774 stars. It builds a persistent local knowledge graph of a repository, from source code to documentation, configuration and infrastructure, and exposes it to agents as MCP tools. Its README calls the MCP server "the core of the project". Written in C.

4. Playwright MCP — browser control through the accessibility tree

Playwright MCP ranks fourth with 39,799 stars. It is Microsoft's browser automation server and drives a browser through its accessibility tree rather than through screenshots, so an agent works on page structure instead of pixels. 10,698,162 weekly downloads, the most of any server here.

5. MCP for Blender — 3D modelling and scene creation

MCP for Blender ranks fifth with 34,801 stars. It provides prompt-driven 3D modelling, scene creation and manipulation in Blender. It was formerly named blender-mcp; it is a third-party integration, not made by the Blender Foundation. Distributed on PyPI.

6. GitHub MCP Server — repositories, issues, pull requests and Actions

GitHub MCP Server ranks sixth with 34,546 stars. It is GitHub's own server for repositories, issues, pull requests and Actions. Written in Go and distributed as a binary and a container rather than on npm. 5,362 forks, the most of any server here.

7. Serena — semantic code retrieval and editing

Serena ranks seventh with 31,481 stars. It provides semantic code retrieval, editing and refactoring tools that work at the level of symbols rather than lines, "the IDE for your coding agent". Written in Python.

8. n8n-MCP — building and debugging n8n workflows

n8n-MCP ranks eighth with 23,275 stars. It lets an AI assistant operate n8n: read failed executions, edit workflows in place, validate them and build new ones. 41,928 weekly downloads.

9. xiaohongshu-mcp — search and publishing on Xiaohongshu

xiaohongshu-mcp ranks ninth with 17,182 stars. It gives an AI assistant access to Xiaohongshu (RedNote): search, read and publish posts. Written in Go, and the only server in the top 10 built around a single consumer platform.

10. MCP Toolbox for Databases — database queries and tools

MCP Toolbox for Databases ranks tenth with 16,897 stars. It is Google's open-source MCP server for databases and works both as a ready-made server for agents and IDEs and as a framework for defining safe custom database tools. Created 2024-06-07, the oldest repository in the top 10. 54,434 weekly downloads.

Which of the top 10 MCP servers lead by weekly npm downloads?

Stars and downloads measure different things. A star is one person signalling interest once. A download is a machine installing the package, repeatedly, often inside CI or every time an agent starts a server with npx.

The six top-10 servers that publish to npm rank like this:

ServerRank by starsRank by downloadsnpm downloads/week
Playwright MCP4110,698,162
Chrome DevTools MCP222,648,086
Context7131,166,420
MCP Toolbox for Databases10454,434
n8n-MCP8541,928
codebase-memory-mcp369,610

Playwright MCP is the clearest case. It is fourth by stars, and its 10,698,162 weekly downloads are more than the other five combined. A browser server that agents start on demand is installed far more often than it is starred.

codebase-memory-mcp runs the other way. Third by stars at 48,774, it has the fewest downloads of the six at 9,610. It is written in C and its main install path is a native binary from a shell script, so the npm package is one of several ways to get it. Its repository was created on 2026-02-24, the newest in the top 10.

Figma Context MCP, outside the top 10, shows the same gap. It is twelfth by stars at 16,232, but its 144,185 weekly downloads would place it fourth among the eight servers in this list that publish to npm.

Four of the top 10 publish nothing to npm: GitHub MCP Server and xiaohongshu-mcp ship Go binaries and containers, and MCP for Blender and Serena are Python packages. An empty download column means npm is the wrong place to count them, not that nobody uses them.

Where can you verify the MCP server ranking and download counts?

Every figure below links to the API record it was read from. Each link returns the raw record for the corresponding repository or npm package.

How were these 10 MCP servers selected?

The candidate list was built by a stated rule rather than picked by hand. The ranking separates MCP servers from directories, SDKs, frameworks and applications that also ship an MCP server:

  1. Find every candidate. Search GitHub, sorted by stars, for repositories tagged with the mcp-server topic, and for repositories with "MCP server" in their name or description. That gave 514 active repositories. The topic alone is not enough: Playwright MCP and MCP for Blender do not carry it.
  2. Keep a repository if it names itself an MCP server. It qualifies if it has the mcp-server topic, has "mcp" in its repository name, or calls itself an MCP server in its description.
  3. Drop what is not a server you add to an MCP client. Three kinds of repository pass step 2 but are not servers, and they are listed below.

Why are directories, SDKs and applications excluded?

Directories are not servers. The two most-starred repositories in this space are catalogues: punkpeye/awesome-mcp-servers at 97,818 stars and modelcontextprotocol/servers at 92,075. Both outrank every entry in the table. Listing them first would be like ranking a bibliography above the papers in it.

SDKs and frameworks are not servers either. PrefectHQ/fastmcp has 28,633 stars, modelcontextprotocol/python-sdk 24,885 and modelcontextprotocol/typescript-sdk 13,778, with 90,522,817 weekly downloads on @modelcontextprotocol/sdk. That download figure dwarfs every server here, and it should: it is the library most of them are built on.

Apps that also ship an MCP server are left out. Large applications such as n8n and Gemini CLI carry the mcp-server topic because they can speak MCP, but the thing you install is the application. next-ai-draw-io, at 37,024 stars, describes itself as "Web app, desktop app, and an MCP server", so it is out for the same reason.

Which excluded repositories would change the top 10?

Two repositories could reasonably go either way, and each would enter the top 10 if counted:

  • context-mode, 34,230 stars, carries the mcp-server topic but describes itself as "a free, local plugin for 11 coding agents". Counted, it would be seventh.
  • XERJ, 19,200 stars, calls itself an "AI search engine and MCP server": the engine comes first. Counted, it would be ninth.

Both were left out because the thing you install is a plugin or a search engine, with MCP as one way in. If you count both, Serena drops to eighth and n8n-MCP to ninth, and xiaohongshu-mcp and MCP Toolbox for Databases fall out of the top 10.

Which MCP servers just missed the top ten?

  • Apify MCP Server, 16,706 stars, 191 behind MCP Toolbox for Databases. Web scraping through Apify Actors; 48,662 weekly downloads.
  • Figma Context MCP, 16,232 stars. Figma layout data for coding agents; 144,185 weekly downloads, more than MCP Toolbox for Databases and n8n-MCP combined.
  • Unity MCP, 16,037 stars. Assets, scenes and scripts in the Unity Editor, written in C#.

Positions nine to thirteen are separated by little more than a thousand stars, so this end of the list can reorder within weeks.

What do stars, forks and weekly downloads actually measure?

MeasureWhat it counts, and what it misses
GitHub starsOne signal of interest per account, kept forever. Counts attention at any point since creation; never decays when a project is abandoned.
ForksCopies made to modify. High forks against stars usually means a tool people adapt rather than adopt.
npm downloads/weekInstalls by machines, often CI or npx starting a server, counted over seven days. Reflects current use, but misses anything distributed as a binary, a container or a Python package.
Last pushedThe most recent commit. The cheapest check on whether a star count is describing something still alive.

What are the limits of ranking MCP servers this way?

  • Stars never go down. A server that was popular in 2025 and abandoned in 2026 keeps its count. All ten servers here were pushed to within the week the figures were read.
  • npm is one channel. Go binaries, Docker images and PyPI packages are invisible to it. Four of the top 10 show nothing in the download column.
  • Selection is a rule, and rules have edges. The two close calls above would change positions seven to ten. The rule is stated so you can disagree with it specifically.
  • Both counts are snapshots. They were read on 17 November 2026 and were already changing while being read.
  • Neither measures quality. Nothing here says which server is well built, well documented or safe to give write access to.

How is this ranking different from AI search visibility?

Stars and downloads tell you how many people adopted a tool. They tell you nothing about whether an AI assistant will name it when someone asks "what's the best MCP server for browser automation". That is a different kind of visibility, and it is measured differently: across a set of real queries, which products the assistants mention, and your share of voice against the competitors mentioned alongside you. If that is the question you care about, start with what AI visibility is or how to track brand mentions in AI search.

FAQ

Frequently asked questions

By GitHub stars on 17 November 2026: Context7 (65,011), Chrome DevTools MCP (58,007), codebase-memory-mcp (48,774), Playwright MCP (39,799), MCP for Blender (34,801), GitHub MCP Server (34,546), Serena (31,481), n8n-MCP (23,275), xiaohongshu-mcp (17,182) and MCP Toolbox for Databases (16,897).

It depends on the measure. By GitHub stars, Context7 leads with 65,011. By weekly npm downloads for 2026-11-10 to 2026-11-16, Microsoft's Playwright MCP leads with 10,698,162, against 2,648,086 for Chrome DevTools MCP and 1,166,420 for Context7.

Because it is a directory of servers, not a server. It has 92,075 stars and punkpeye/awesome-mcp-servers has 97,818, so both would top the table, but ranking a catalogue above the things it catalogues would make the list mean something other than its title. SDKs and frameworks such as FastMCP are excluded for the same reason.

Among servers, Playwright MCP, at 10,698,162 weekly npm downloads. The @modelcontextprotocol/sdk package is far larger at 90,522,817, but it is the SDK most servers are built on rather than a server itself.

No. codebase-memory-mcp is third by stars at 48,774 but has 9,610 weekly npm downloads, while Playwright MCP is fourth by stars with 10,698,162. Stars count attention accumulated since a repository was created; downloads count recent installs through one channel.

It does not measure it. Adoption counts say how many developers installed a tool; AI search visibility is whether an assistant names your product when someone asks a buying question. The second kind is tracked across a set of queries, by which brands get mentioned and how your share of voice compares with the competitors mentioned beside you.

What is the short version of the top 10 MCP servers ranking?

On 17 November 2026 the top 10 MCP servers by GitHub stars were Context7, Chrome DevTools MCP, codebase-memory-mcp, Playwright MCP, MCP for Blender, GitHub MCP Server, Serena, n8n-MCP, xiaohongshu-mcp and MCP Toolbox for Databases. Ranked by weekly npm downloads instead, Playwright MCP leads by four times. The list comes from a stated rule over 514 GitHub repositories, and every figure on this page links to the API record it came from.