Semrush AI Tool MCP
An MCP server retrieves Semrush keyword, domain and backlink data so an agent can compare competitors and prepare SEO analysis.
- 536 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The server uses a Semrush key and consumes API units for analytics requests.
Install
- Works in
Manual install
mkdir -p 'semrushai' && cd 'semrushai' && npm install github:springvoiceswell/semrush-ai-toolThe first README method installs the package locally for MCP. Global CLI installation appears later.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The server uses a Semrush key and consumes API units for analytics requests.
This is third-party code. Review the repository files before installing.
What it does
Semrush AI Tool connects an AI client to the Semrush API. Agents request keywords, traffic estimates, rankings, backlinks and competitor data for site analysis. Users can select a regional database and compare domains. The package also includes a terminal reporting CLI. An API-unit balance check is available before large jobs. The MCP server runs locally and sends requests to Semrush with the user’s own key. Retrieved metrics become available in the agent conversation.
Who it is for. For SEO specialists and marketers with Semrush API access who want analysis through an AI client.
Good fit when
- Compare site and competitor keyword portfolios.
- Inspect a domain’s backlinks.
- Retrieve a keyword SERP for a regional database.
- Check API units before a large report.
Not a fit when
- Semrush API access is unavailable.
- You require actual visits rather than service estimates.
- Domains and queries cannot be sent to Semrush.
Example request
Compare these domains in one Semrush database, first showing API units and limiting the report to ten rows.MCP
- Transport
- stdio
- Authentication
- API key
Environment variables
SEMRUSH_API_KEYrequired, secret- Semrush API key.
Limitations
Node.js 18 or later and a Semrush key with access to the required reports are needed. Requests consume API units; limit row counts and inspect the balance before bulk retrieval. Keyword, traffic and backlink data depend on regional coverage, so compare matching periods and databases. Keep the key in the local MCP process environment, out of shared project settings, published files and agent messages.
How to disable. Remove the MCP connection and local package. Revoke an unused Semrush key and remove it from the environment.
FAQ
Which key is required?
`SEMRUSH_API_KEY` from your own Semrush account.
How does MCP start?
Use `npx -y github:springvoiceswell/semrush-ai-tool` over stdio.
Is there a CLI?
Yes. The package exposes terminal report commands.
Is Trends traffic available?
Tools use Semrush .Trends; verify access in your plan.
Can it edit the website?
Its documented tools retrieve analytics; website edits are separate.
Discussion
No questions or reviews yet.
Related
MCP serversAn MCP server with SEO data: backlinks, keyword difficulty and traffic estimates from the free Ahrefs tools
crawlseo MCP compares the latest 28 days of site metrics with the preceding 28 days, alongside results from the latest crawl.
DataForSEO MCP filters API responses to selected fields, so an agent receives only the data needed for the current analysis.
Search Console MCP: Google, Bing and GA4 data for agents
Search Console MCP
An MCP server that gives an agent Google Search Console, Bing Webmaster, GA4 and AdSense data with ready SEO checks
An open MCP server and agent skill set for SEO: keyword research, competitors, backlinks and site audits powered by DataForSEO
Google Search Console MCP
Google Search Console MCP Server for SEOs
An MCP server for Google Search Console: queries and pages with clicks and positions, URL indexing checks, sitemaps and ready SEO skills
README in short
The same reports are exposed through MCP and CLI. The client choice does not change Semrush access or quotas.