What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Semrush MCP connects compatible AI assistants to Semrush data, letting you ask questions in natural language and have the assistant retrieve relevant metrics for its response. The assistant supplies the interpretation; MCP supplies the requested data. What you can retrieve depends on your Semrush subscription, API access, and the AI client you use.
What Semrush MCP does
MCP is a connection between an AI assistant and Semrush data. You ask a question; the assistant identifies the relevant information, requests it through the connection, and uses the returned data to form an answer. Semrush describes the connection as read-only: assistants can retrieve Semrush data but cannot modify or delete it. See Semrush’s MCP overview.
Available data can include keyword search volume and difficulty, ranking positions, SERP features, related keywords, organic and paid search metrics, estimated traffic, CPC, ad-copy analysis, competitor keyword overlap, traffic share, backlinks and referring domains, traffic sources, geographic performance, audience insights, and market trends. Access depends on the subscription and API permissions associated with your account.
What you can ask an AI assistant to do
Use MCP for exploratory tasks where retrieving relevant SEO data is easier than exporting it manually. Examples include:
#1 Best Overall
- Build a keyword strategy for a specified country, topic, and set of competitors.
- Find potential content gaps between your domain and named competitors.
- Compare keyword or traffic trends over a stated reporting period.
- Prepare a draft report showing landing pages and keyword movement.
Semrush’s product page includes example prompts for keyword strategy, content refreshes, and monthly SEO reports: Semrush MCP. For answers you can interpret reliably, ask the assistant to identify the database or geography, date range, filters, and result count used. Check important figures in Semrush before treating an AI-generated interpretation as a confirmed conclusion.
Connect Semrush MCP to your AI tool
Semrush lists ChatGPT, Claude, Gemini, Perplexity, Cursor, VS Code, and Claude Code among supported platforms. The connection method differs: some use an app or connector flow, while developer tools use MCP server configuration. Platform interfaces and support can change; Semrush’s setup guide has the platform-specific directions.
Rank #2
ChatGPT
- Open the Semrush app in ChatGPT and choose the option to connect.
- Review the requested permissions and approve the connection.
- In a prompt, call the connected tool with
@Semrushand describe the data and scope you need.
Claude
- Connect the Semrush app in Claude.
- Review the permissions and approve the connection.
- Use
@Semrushin a prompt to ask for the desired Semrush data.
Claude Code
- Run
claude mcp add semrush https://mcp.semrush.com/v2/mcp -t http. - Run
/mcpand complete authentication when prompted.
Cursor
- Open Settings → Cursor Settings → Tools & MCP.
- Add an MCP server using the Semrush endpoint
https://mcp.semrush.com/v2/mcp, then save the configuration.
Visual Studio Code
- Create or edit
.vscode/mcp.jsonin your workspace. - Add a server named
semrushwith the Semrush endpoint and"type": "http", following the configuration format in Semrush’s setup guide.
Gemini CLI
- Configure an HTTP MCP server with the Semrush endpoint and an API-key header:
Authorization: Apikey YOUR_API_KEY. - Verify the configured server with
gemini mcp list. This route requires a Semrush API key.
Perplexity
- Add the Semrush connector in Perplexity and approve the connection.
- Perplexity requires a paid account for custom MCP connectors, according to Semrush’s setup guide.
Authentication, API access, and usage limits
Semrush’s developer documentation specifies the MCP endpoint https://mcp.semrush.com/v2/mcp and streamable HTTP transport. OAuth is the default documented authentication method and redirects you to Semrush to authenticate. If your client does not support OAuth, Semrush documents API-key authentication using an Authorization: Apikey YOUR_API_KEY header. See the Semrush MCP developer documentation.
Plan terms can change. Semrush’s MCP knowledge base says Semrush One Starter, Semrush One Pro+, SEO Classic Pro, and SEO Classic Guru include 50,000 MCP API units, refreshed on the subscription renewal date. It says Semrush One Advanced and SEO Classic Business require an MCP API units package for the expanded access path; listed packages are 2 million, 5 million, 10 million, and 20 million units. Check Semrush’s current MCP plan guidance and your account before relying on a particular allowance.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Rank #3
Traffic and market data require a Trends API plan, according to Semrush’s developer documentation. Standard SEO API access and Trends API access cover different data needs; the Semrush API overview provides additional API context.
Semrush says each MCP query consumes API units and recommends making requests narrower, caching strategically, and keeping related follow-ups together. Its example contrasts a focused request for the top 50 keywords in the US with a global request for all keywords. This is usage guidance, not a universal unit-cost formula: specify a database, result count, and relevant filters rather than assuming each question has the same cost.
Use retrieved data carefully
- Tell the assistant the target country or database, domain, date range, and comparison set when those details matter.
- Ask it to show the source figures behind a recommendation, not just its conclusion.
- Check key numbers and consequential decisions in Semrush or the underlying report.
- Review the authentication permission screen and follow your organization’s credential-handling practices.
The connection reduces manual copying and exporting, but it does not make the assistant’s analysis a Semrush metric or an independent audit of the data. Semrush’s pages do not establish broad claims about data retention, privacy guarantees, or security certifications; evaluate those separately against your organization’s requirements.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Is Semrush MCP a good fit?
It is useful when conversational exploration of Semrush data fits your workflow and your account and AI client provide the required access. A dashboard or export may remain preferable for a repeatable reporting process where you need a fixed layout, predictable scope, or a review trail. Decide based on the data your plan exposes, the client’s connection method, API-unit requirements, and whether your work is exploratory or standardized. The available Semrush documentation describes its own integration, not a comparative ranking of other MCP services.
Recommended Free Tools
Semrush’s MCP landing page also publishes data-scale figures—28.4 billion keywords, 142 geographic databases, 808 million domain profiles, 28 million total users, and more than 36 million unique brands—without stating a year on the page. These are vendor-published figures, not independently validated statistics: Semrush MCP.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
