Semrush MCP. Run deep SEO forensics directly in your chat.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Semrush MCP Server gives your AI agent direct access to Semrush’s massive SEO database. You can analyze competitor backlink profiles, check domain rank performance against rivals, and research profitable keywords without opening a browser tab.
It lets you pull specific data—like organic search volume or site audit scores—directly into your chat context for immediate analysis.
What your AI agents can do
Domain overview
Gets a domain's overall SEO score and estimates its organic and paid traffic volume for a specified region.
Domain vs domain
Compares the core SEO metrics of two distinct domains to show which one has higher visibility.
Get backlinks
Pulls an overview of all inbound links pointing to a domain, helping gauge its authority level.
It tells you which of two websites performs better in search engine visibility across various metrics.
The tool pulls an overview for any given website, including its estimated organic and paid traffic volume.
It retrieves a list of external links pointing to a domain so you can gauge its overall authority.
The tool finds related keywords for a topic and provides key metrics like search volume, CPC, and competition difficulty.
It fetches the current organic keyword rankings for a site or tracks specific keywords over time.
It generates an audit score and flags underlying issues (like missing metadata) that impact SEO performance.
The tool provides specific data points like visits, bounce rate, and pages viewed per visit for a target domain.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Semrush MCP Server: 8 Tools for Digital Marketing
Use these eight tools to analyze everything from competitor backlink profiles to granular keyword difficulty and site technical audits.
019d7605domain overview
Gets a domain's overall SEO score and estimates its organic and paid traffic volume for a specified region.
019d7605domain vs domain
Compares the core SEO metrics of two distinct domains to show which one has higher visibility.
019d7605get backlinks
Pulls an overview of all inbound links pointing to a domain, helping gauge its authority level.
019d7605keyword overview
Provides detailed keyword metrics like search volume, cost-per-click (CPC), and competition difficulty for specific terms.
019d7605organic keywords
Retrieves the list of keywords a domain currently ranks for, useful for checking performance gaps.
019d7605related keywords
Finds new keyword ideas related to a topic, along with their search volume and difficulty metrics.
019d7605site audit
Generates a technical quality overview for a website project, flagging specific SEO errors that need fixing.
019d7605traffic analytics
Gets granular traffic data like visits, bounce rate, and average pages per visit for any given site.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Semrush, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're getting direct access to Semrush’s massive SEO database through your AI agent. Forget switching tabs or running multiple API calls—your agent pulls raw, actionable data right into the chat context for immediate analysis. This server lets you run complex forensic queries that used to take hours of manual work.
Comparing Websites and Analyzing Core Health
The domain_overview tool gives you a site's overall SEO score, plus estimates for its organic and paid traffic in any region you specify. If you wanna know how two sites stack up against each other, the domain_vs_domain tool compares core metrics side-by-side so you can instantly tell which one has better search engine visibility.
You can also check a site's technical quality with the site_audit tool; it generates an audit score and flags specific underlying issues—like missing metadata or broken schema—that are actively hurting SEO performance.
For deep traffic insights, the traffic_analytics tool provides granular data points: you get visits counts, bounce rate percentages, and average pages viewed per visit for any target domain. To gauge a site's overall authority and credibility, you run get_backlinks, which pulls an overview of all inbound links pointing to that domain; this lets you see the size and quality of its link profile.
Keyword Strategy and Ranking Analysis
When you need keyword ideas, the related_keywords tool finds new suggestions for a topic. It provides key metrics like search volume and difficulty right away. For specific terms, the keyword_overview function gives detailed data—you'll see things like cost-per-click (CPC), competition level, and total monthly search volume. The agent can use this info to help you build out keyword briefs in minutes.
To track what a site is already doing well, the organic_keywords tool retrieves the list of keywords that domain ranks for right now. You'll use that data to check for performance gaps or see if they're hitting their ranking targets over time. If you want to know how much traffic specific keywords generate, you can run a dedicated query for those terms.
How It Works in Practice
Your agent executes the tool call based on your prompt, pulls all that raw data into the context window, and then writes the analysis for you. You don't just get a number; you get the whole picture. For example, if you ask it to compare two competitors using domain_vs_domain, the AI handles the query, grabs the metrics, and then structures a full report showing where one site is losing traffic compared to the other.
It’s like having an SEO analyst sitting next to your agent's terminal.
It's built for speed. You prompt: "Check Domain X's backlink profile using get_backlinks." The AI executes it, pulls the link data, and you get the authority assessment instantly. It handles everything from finding technical flaws via site_audit to mapping out profitable new ideas with related_keywords. You talk to your agent like you're talking to a teammate who knows every database trick off the top of their head.
You'll use this server for competitive auditing, content gap analysis, and site health checks without ever leaving the chat window.
How Semrush MCP Works
- 1 You instruct your AI agent to run a comparison or analysis (e.g., 'Run
domain_vs_domainon X and Y'). - 2 The server executes the tool, querying Semrush's massive database for raw data points.
- 3 Your AI client receives structured JSON output containing metrics like traffic volume or backlink counts, which it then summarizes into plain English.
The bottom line is: you talk to your agent, and the agent gets the hard data needed from Semrush instantly.
Who Is Semrush MCP For?
SEO Strategists who are tired of spending hours in competitor dashboards. Content Marketers needing instant keyword ideas for articles that actually rank. Digital Analysts who need to compare five different startups' traffic metrics side-by-side before making a pitch.
Uses domain_vs_domain and get_backlinks to map out competitive gaps between client sites and industry leaders.
Runs related_keywords with a seed topic, then has the AI populate an article outline with high-volume, low-competition terms.
Commands the bot to run traffic_analytics on multiple potential clients simultaneously to assess their current site performance (bounce rate, visits/visit).
What Changes When You Connect
- Stop guessing about keywords. Use
keyword_overviewandrelated_keywordsto get actual search volumes, CPCs, and competition scores instantly, giving you concrete data for content planning. - Assess competitor authority without leaving your workflow. Running
domain_vs_domaintells you exactly where a rival leads—is it backlinks? Traffic volume? Or something else? - Fix technical SEO issues immediately. The
site_audittool pulls the quality score and lists exact errors, letting your agent draft fix instructions for missing metadata. - Build out content strategy with confidence. By running
get_backlinks, you can validate a domain's authority before committing to a large-scale campaign. - Compare performance across multiple targets. Use
traffic_analyticson five different startups and see their bounce rates or pages/visit side-by-side, saving hours of manual reporting.
Real-World Use Cases
Evaluating a new competitor
A digital analyst needs to know if Competitor X is gaining ground. They run domain_vs_domain and see that while their own site has higher total traffic, the competitor scores 15% better on non-brand long-tail queries overall. This tells them exactly where they need to pivot their content focus.
Writing a highly targeted article
A content marketer starts with 'best mechanical keyboard'. They run related_keywords, which suggests 'buy tactile mechanical keyboard red switches.' The agent uses this specific term, along with its low competition score, to write a niche guide that is guaranteed to rank faster.
Auditing client site technical health
The SEO strategist suspects the client's metadata is wrong. They run site_audit, get a poor quality score, and ask the agent to explain the flagged 'missing canonical tags.' The agent then drafts three specific fixes for the development team.
Assessing market entry viability
A growth team needs quick data on five potential new markets. They run traffic_analytics on all five domains, immediately comparing their bounce rates and average pages/visit to determine which site is already engaged with users.
The Tradeoffs
Using single-source data
Just checking organic_keywords for a domain gives you a list of what they rank for, but doesn't tell you if that traffic is high quality or low volume.
→
Don't just check the keywords. Run keyword_overview on those top-ranked terms to confirm their search volume and competition difficulty. This validates if the ranking actually matters.
Ignoring technical debt
Writing a ton of great content (content quality) but failing to notice that site_audit flagged critical missing metadata, meaning Google can't index it properly.
→
Always run site_audit first. Fix the foundational errors before writing more copy. A perfect article means nothing if the site structure is broken.
Only focusing on direct competitors
Comparing only two big brands (domain_vs_domain) and assuming that's enough to cover the market landscape.
→
Use get_backlinks on both domains, but then cross-reference with related_keywords. This shows you who is linking to them and what topics are generating interest in the wider industry.
When It Fits, When It Doesn't
Use this server if your primary need is forensic data: comparing metrics (A vs. B), diagnosing technical failure, or finding quantifiable keyword gaps. It’s a diagnostic powerhouse. Don't use it if you just need qualitative advice—like general content ideas without numbers. If all you want is 'write me an article about X,' this tool won't help directly. You still have to give the AI the structure and the prompts. The power here isn't writing; it's giving your agent undeniable proof (data) to write with. Never use this if your core problem is internal team workflow—it’s purely external market intelligence.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Semrush API. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Wasting time clicking between Google Analytics, Ahrefs, and Semrush dashboards?
Right now, analyzing a site's health means opening one tool to check rankings, switching tabs to another to see traffic volume, then jumping into a third service just to pull backlink counts. You spend more time copying data than actually analyzing the signal.
With Semrush MCP Server, you feed your agent all three requests in one prompt. The AI executes `domain_overview`, pulls the raw numbers for rank and traffic, runs `get_backlinks` for authority, and summarizes it—all without you leaving the chat window.
Semrush MCP Server: Get full SEO data context with Semrush.
You no longer need to manually check if a keyword has volume, competition, and related ideas. You run `related_keywords` on your seed topic; the tool returns ten viable options, complete with their respective search volumes and difficulty scores.
It changes everything: you move from 'I think this is a good topic' to 'We are targeting these five high-volume, low-competition keywords.' That's the difference between guessing and executing.
Common Questions About Semrush MCP
How do I compare two websites using domain_vs_domain? +
You simply prompt your agent to run domain_vs_domain on both domains. The AI will then tell you which site leads in specific metrics, like total organic traffic or referring domains.
What is the best way to find new keywords with related_keywords? +
Give related_keywords a core topic (e.g., 'best mechanical keyboard'). The tool returns dozens of ideas, and you can immediately filter them by volume or difficulty score.
Do I need to worry about technical SEO with site_audit? +
Yes. Running site_audit pulls the quality overview and highlights specific errors—like missing metadata. Your agent can then draft actionable instructions for your developers to fix it.
How do I get general traffic data with domain_overview? +
Use domain_overview by specifying the target domain and the region (e.g., 'us'). The tool pulls estimated organic and paid traffic metrics for that site.
When should I use `get_backlinks` to audit a domain's authority? +
Use get_backlinks when you need an overview of a site’s inbound link profile. This lets you gauge the domain's overall authority by counting the unique linking sources and analyzing their diversity.
What specific data points does `keyword_overview` provide for research? +
It returns four key metrics: search volume, Cost Per Click (CPC), competition difficulty, and SERP feature flags. This helps you filter keywords based on commercial potential versus achievable rank difficulty.
How do I interpret the results from `traffic_analytics`? +
The tool delivers visits, bounce rate, and pages per visit. If the bounce rate is high but pages/visit is low, it signals a poor user experience or an irrelevant landing page.
Does `domain_overview` require me to specify a region? +
Yes, you must specify the target database (e.g., 'us' for United States). Omitting the regional scope restricts your data and makes the results unusable for other markets.
Are there additional charges for querying Semrush from my agent? +
The Semrush API inherently consumes 'API Units' based on the weight of each request line (Keyword ranks, Domain analytics). You are completely bound to your established Semrush Business subscription rules. Vurb/MCP itself doesn't impose surcharges.
Can I filter SEO performance based on different global markets or languages? +
Yes. Most core functions such as domain_overview and keyword_overview optionally accept a targeted string code array for Regional Databases (such as 'uk', 'fr', 'de', 'es', or strictly 'us'). Just specify it organically in your LLM chatting window.
Can it check a website's technical health natively? +
Yes, through the specific site_audit directive. The AI agent will ingest the aggregated technical score corresponding directly to your preconfigured Semrush Project IDs, returning high-level data regarding crawled warnings and crawler fatal errors.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Algolia Analytics
Search performance intelligence — audit CTR, conversions, and top searches via AI.
SendGrid
Deliver transactional and marketing emails at massive scale with industry-leading deliverability and real-time analytics.
X Ads (Twitter)
Manage your X Ads campaigns — audit accounts, line items, and analytics via AI.
You might also like
Fulcrum
Manage field data collection, track form records, and query datasets via AI agents with Fulcrum.
Google Play Developer
Manage your Android apps - respond to reviews and check subscriptions via AI.
Learn Amp
Combine learning, engagement, and performance in one people development platform that helps employees grow and organizations thrive.