Developers Published 574 MCP Servers for SEO Data on GitHub in 2026, More Than Double the 272 in All of 2025

Summary

Picture an agency owner who asks Claude to pull last month's Search Console clicks and compare them with keyword data from an SEO tool. Two years ago that took exports and spreadsheets. Now an AI agent can call both tools directly through small connectors called MCP servers.

MCP, the Model Context Protocol, is an open standard that lets AI assistants plug into outside tools and data. Each MCP server is a connector. Since late 2024, developers have published hundreds of thousands of them on GitHub, and a growing share give agents access to search results, SEO data and websites.

In 2026 so far developers published 574 MCP servers for SEO data alone. That is more than double the 272 in all of 2025, with more than two months of the year still to go.

What we measured

We used GH Archive, the public log of GitHub events, in Google BigQuery. We kept repositories with MCP as a separate word in their name, first seen from November 2024, when the protocol was released. We removed probable forks: repos with no forks and at most two stars whose short name matches an earlier repo that had been forked.

We sorted MCP repos into four web-data groups by name: SEO data (Search Console, keyword and SEO tool connectors), web analytics, web search, and web fetching, crawling or browser control. Everything else counts as other MCP. We report new repos by month and recorded stars. Named projects appear only in adoption counts.

SEO data connectors are the fastest-growing web MCP group

New web-data MCP servers per month, by group.

SEO data servers went from a handful a month in early 2025 to 137 in May 2026. The dip after July 2026 coincides with gaps in GH Archive's own event collection, so we treat August to October as incomplete.

Half of web-data MCP servers fetch pages or drive a browser

Share of each group among web-data MCP servers, by year.

SEO data more than doubled its share of the group, from 7.2% to 16.8%. Fetch and browser tools still dominate, likely because almost every agent needs to read web pages.

A few company-built servers hold most of the attention

Recorded GitHub stars for web-data MCP servers published by the companies behind the underlying service.

Across the whole group, recorded stars are thin. In 2025, 53 of 272 SEO data servers (19.5%) earned a star. Most connectors look like personal builds that wrap one API for one person's workflow.

What this means

AI agents can now pull search results, rankings and analytics on demand. Marketers who use them can check your site and your competitors' sites far more often than any human researcher did. Agents also fetch pages to answer questions directly, so the content an agent can read on your site matters more each month. Expect any AI search optimization agency worth hiring to test your pages the way these agents read them.

Make sure your key pages load their main text without heavy scripts, and that facts like prices, hours and service areas appear as plain text. Where AI tools come up short on your site today is the to-do list for LLM optimization, and a free AI visibility audit writes that list for you.

Limits

We matched repo names only. MCP servers without MCP in their name are missed, and group assignment uses name keywords, so some repos land in the wrong group.

GH Archive recorded far fewer star events in 2026 and had collection gaps in October 2025 and August to October 2026. Counts for those months and all 2026 star figures are understated.

First seen is the first recorded public event, not the exact creation date. Fork removal is a name-based heuristic.

Programming language is not part of the event data, so we do not report it.

Frequently asked questions

Related studies

• The open-source tooling around AI searchGEO and AI SEO Repos on GitHub Hit 322 a Month in 2026
• The open-source tooling around AI searchOne List Holds 81% of AI Bot Blocklist Stars on GitHub
• The open-source tooling around AI searchAI Browser Agent Repos on GitHub Grew 22-Fold Since 2024
• The open-source tooling around AI searchllms.txt GitHub Projects: 83.1% Never Got a Star