SEO Data MCP (SteadyScrape)
● Activeio.github.steadyscrape/seo-data-mcp
Keyword volume, live SERP ranks, domain traffic, ranked keywords, backlinks, Google Trends, YouTube.
Connect this server
One click to install, or copy the config below. Suits: Cursor · HTTP clients.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"seo-data-mcp": {
"url": "https://mcp.steadyscrape.dev/seo/mcp"
}
}
}claude mcp add --transport http seo-data-mcp https://mcp.steadyscrape.dev/seo/mcpcode --add-mcp '{"name":"seo-data-mcp","type":"http","url":"https://mcp.steadyscrape.dev/seo/mcp"}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Marketing & SEO
- Version
- 1.1.0
- Registry
- active
- Published
- 11/20/2026
Is it safe? Is it maintained?
Serverdex check: Nov 22, 2026Looks healthy: SEO Data MCP (SteadyScrape) is maintained, open source, hosted endpoint answering without a key.
- Maintained
- Active
- Last commit today (Nov 20, 2026), 0 open issues.
- Official registry
- Active
- Published as io.github.steadyscrape/seo-data-mcp in the official MCP registry, version 1.1.0.
- Source
- Open source, MIT
- Public repository under the MIT licence, 0 stars, 0 forks.
- Runs
- Hosted by the publisher
- Your client talks to mcp.steadyscrape.dev: prompts and tool arguments leave your machine for that host.
- Credentials
- None needed to connect
- The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
- Owner
- Unclaimed
- Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.
Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.
Live check
checked Nov 22, 2026, 07:08 UTCStatus history & uptime →The endpoint answered the MCP handshake as "SteadyScrape SEO Data" and listed 9 tools. Answering since Nov 21, 2026.
Context cost ≈ 2.1k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 9 tools.
Tools (9)
keyword_metrics3 paramsGoogle search volume, CPC, competition, keyword difficulty (0-100), search intent and the last 12 months of volume for up to 100 keywords in one country. Keywords without data are listed in noData and not charged. Billed per started block of 10 keywords that have data.
Show parametersHide parameters
keywordsarrayrequired1-100 keywords.countrystring2-letter country code (US, GB, DE...) or English name. Default US.languagestringLanguage code, e.g. en, es, de. Default en.
google_serp6 paramsLive Google organic results for one keyword: position, title, URL, domain and snippet, plus which SERP features appear (AI Overview, People Also Ask, local pack, video...) and the AI Overview text. Optionally give target_domain to get that domain's best position (rank check). Billed per 10 results of depth.
Show parametersHide parameters
keywordstringrequiredThe search query.countrystring2-letter country code (US, GB, DE...) or English name. Default US.languagestringLanguage code, e.g. en, es, de. Default en.devicestringDefault desktop.depthintegerResults to fetch: 10-100 (default 10). Deeper is slower (100 takes ~15 s).target_domainstringOptional domain to find in the results, e.g. example.com.
rank_check6 paramsWhere one domain ranks on live Google for up to 10 keywords in one country: best position, ranking URL and the top 3 domains for each keyword, plus SERP features. Same data and price as google_serp, billed per 10 results of depth for each keyword that returns results.
Show parametersHide parameters
keywordsarrayrequired1-10 search queries.target_domainstringrequiredDomain to find, e.g. example.com (subdomains count).countrystring2-letter country code (US, GB, DE...) or English name. Default US.languagestringLanguage code, e.g. en, es, de. Default en.devicestringDefault desktop.depthintegerResults checked per keyword: 10-100 (default 10).
domain_overview3 paramsFor up to 100 domains: estimated monthly organic traffic and number of ranking keywords in one country (Google), paid keywords, plus backlink profile: domain rank (0-1000), backlinks, referring domains, spam score, first seen. Billed per started block of 10 domains that have data.
Show parametersHide parameters
domainsarrayrequiredcountrystring2-letter country code (US, GB, DE...) or English name. Default US.languagestringLanguage code, e.g. en, es, de. Default en.
ranked_keywords4 paramsThe Google keywords a domain (or URL) ranks for in one country, sorted by estimated traffic: keyword, position, ranking URL, search volume, CPC and estimated visits. Up to 100 keywords per call, plus position distribution totals. Billed per call with data.
Show parametersHide parameters
domainstringrequiredDomain (example.com) or page URL.countrystring2-letter country code (US, GB, DE...) or English name. Default US.languagestringLanguage code, e.g. en, es, de. Default en.limitintegerKeywords to return (default 20).
backlinks4 paramsBacklinks or referring domains pointing to a domain or page URL, strongest first: linking page/domain, anchor, dofollow, first/last seen and rank. Up to 100 rows per call, plus the target's totals. Billed per call with data.
Show parametersHide parameters
targetstringrequiredDomain (example.com) or page URL.modestringDefault backlinks.limitintegerRows to return (default 20).dofollow_onlybooleanBacklinks mode only: return only dofollow links (default false).
google_trends4 paramsGoogle Trends interest over time (0-100) for up to 5 keywords compared, in a country or worldwide, for web, YouTube, news, images or shopping search, plus each keyword's average. Billed per call with data.
Show parametersHide parameters
keywordsarrayrequiredcountrystring2-letter country code or 'worldwide'. Default US.time_rangestringDefault past_12_months.search_typestringDefault web (froogle = shopping).
youtube_search4 paramsYouTube search results for a query in ranked order: video ID, title, channel, views, publish date, duration and whether it is a Short. Up to 40 results. Billed per 20 results of depth.
Show parametersHide parameters
querystringrequiredcountrystring2-letter country code (US, GB, DE...) or English name. Default US.languagestringLanguage code, e.g. en, es, de. Default en.max_resultsintegerDefault 20.
youtube_video3 paramsPublic stats for one YouTube video (views, likes, comment count, channel subscribers, tags, category, description, duration, publish date) and optionally its transcript. Billed per video; the transcript is billed separately and only if the video has captions.
Show parametersHide parameters
videostringrequiredYouTube URL or 11-character video ID.include_transcriptbooleanAlso return the captions text (default false).languagestringLanguage code, e.g. en, es, de. Default en.
Checked by Serverdex with a plain initialize + tools/list call to mcp.steadyscrape.dev/seo/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 21, 2026- Stars
- 0
- Forks
- 0
- Last push
- Nov 20, 2026
- License
- MIT
ai-agentsapifybacklinkskeyword-researchmcpmcp-servermodel-context-protocolremote-mcpseoserp
From the README
SEO Data MCP: live SEO data for AI agents A remote MCP server (Streamable HTTP) that gives Claude, Cursor, VS Code and other MCP clients live SEO data: Google keyword volume and difficulty, live SERP rank checks, domain traffic, ranked keywords, backlinks, Google Trends and YouTube stats. It is hosted on the SteadyScrape MCP gateway. Tools run in your own Apify account. Endpoint: Auth: clients that support MCP OAuth (Claude.ai, VS Code, Cursor) open an Apify sign-in the first time, or send Authorization: Bearer (get a token). Pay per successful call, billed to your Apify account. Tools Client setup Cursor / Windsurf (mcpServers): Claude Code: Registry files • server.json: official MCP Registry entry (io.github.steadyscrape/seo-data-mcp), published by the GitHub Actions workflow in .github/workflows/ • glama.json: Glama maintainer claim More SteadyScrape examples: steadyscrape-examples. Acceptable use You may not use results from this service to build or operate a search engine, or any product or service that competes with or harms the business of search engine providers. — SteadyScrape License MIT. This repo contains configuration and docs only; the tools are paid services on Apify.
Read the full README on GitHub →Remotes
- streamable-http
https://mcp.steadyscrape.dev/seo/mcp
Alternatives to SEO Data MCP (SteadyScrape)
All SEO Data MCP (SteadyScrape) alternatives →Best Marketing & SEO servers →The most-starred Marketing & SEO servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| Google Ads + Meta Ads + SEO/GEO MCP | 8,313 | Oct 2026 | Needs sign-in |
| AdsAgent | 4,227 | Nov 2026 | Needs sign-in |
| Open Design | 1,168 | Nov 2026 | Local / not checked |
| TryPost | 870 | Nov 2026 | Needs sign-in |
| SEO Skill | 641 | Nov 2026 | Needs sign-in |
SEO Data MCP (SteadyScrape): questions people ask
- Is SEO Data MCP (SteadyScrape) a remote or a local MCP server?
- According to its entry in the official MCP registry, SEO Data MCP (SteadyScrape) ships as a hosted endpoint (streamable-http) that your client connects to by URL.
- Does SEO Data MCP (SteadyScrape) need an API key?
- Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
- Is SEO Data MCP (SteadyScrape) safe to use?
- Looks healthy: SEO Data MCP (SteadyScrape) is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
- Is SEO Data MCP (SteadyScrape) still maintained?
- Active: the repository's last commit today. Last push Nov 20, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
- What tools does SEO Data MCP (SteadyScrape) expose?
- 9 tools as listed by the server itself during the live check, including keyword_metrics, google_serp, rank_check, domain_overview, ranked_keywords. The full list with parameters is in the Live check section above.
- How do I add SEO Data MCP (SteadyScrape) to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More from steadyscrape
All 2 servers by steadyscrape →More Marketing & SEO servers
Browse all Marketing & SEO →Agentzia
stoyan-stoyanov
Test how AI assistants recommend your product and improve your landing page with evidence.
Google Webtools MCP
stufently
Google Search Console + GA4 for AI agents: properties, reports, indexing, verification, SEO.
Yandex Direct MCP
stufently
MCP server for Yandex Direct API v5 — campaigns, ads, keywords, reports
Mutagen (mutagen.ru), unofficial
SVorobiev-ru
Unofficial MCP server for the Mutagen SEO API: Wordstat frequencies, competition, semantic core
Taisly Social Media Posting
taisly
Publish videos to TikTok, Reels, Shorts, X, and Facebook through Taisly.
goflag
tancredesimonin
SEO and i18n audit of the site an agent is editing: localhost or protected preview, with sources.
Add the badge to your site
Show visitors that SEO Data MCP (SteadyScrape) is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-steadyscrape-seo-data-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="SEO Data MCP (SteadyScrape) — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-steadyscrape-seo-data-mcp?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.
Install buttons — for your README
[](https://serverdex.io/install/cursor/io-github-steadyscrape-seo-data-mcp) [](https://serverdex.io/install/vscode/io-github-steadyscrape-seo-data-mcp) [](https://serverdex.io/install/claude-code/io-github-steadyscrape-seo-data-mcp)One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.
Install buttons — HTML for your docs
<a href="https://serverdex.io/install/cursor/io-github-steadyscrape-seo-data-mcp"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-steadyscrape-seo-data-mcp"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-steadyscrape-seo-data-mcp"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>Same buttons as plain links for a docs page or website.
Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).