Reference & Lookup Data · Integration
Semrush
Add Semrush to your product for your customers, and give your AI agents governed access to it.
Semrush is a search and competitive dataset with an API in front of it, and reading it well means understanding two things about how it is shaped. Results are per database, meaning per country and per search engine, so the same keyword returns different volumes and positions depending on which one you ask, and picking the wrong database is the most common way to get a plausible but wrong answer. And the API is metered in units charged per row returned, so a wide query is genuinely expensive and your product should ask for the columns it needs rather than everything. Each customer connects their own Semrush account, so units, limits and cost land on them. Their own position tracking and site audit projects hold the domains and keywords they chose to watch, mapped as configuration. fastn keeps the credentials and paces the requests.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Semrush account so queries run on their units rather than on a shared key you have to meter.
Query domain and keyword data against the right country database, so the numbers your product shows match the market it means.
Read a customer's own position tracking and site audit projects so your product reports on the domains they actually watch.
Request only the columns your product uses, since the API charges by row returned and a wide query spends units fast.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent pulls keyword and competitor data for one customer's domain and explains where the visibility gap is.
An agent reads a site audit project's findings and reports the issues worth fixing first, with every call logged.
An agent checks position tracking movement before it answers whether a change had any effect.
Example prompt
For this domain in the UK database, which tracked keywords lost positions this month and who gained them?
Set up Semrush in 4 steps
- 01Enable the Semrush connector in your fastn dashboard.
- 02Have each customer supply their own Semrush API key so units and limits are charged to them.
- 03Choose the databases, reports and columns your product queries, and map their position tracking and site audit projects.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Semrush integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Semrush integration without building it. Your customers connect their own Semrush account inside your product and work their lookups, results and reports there, with no per-customer code on your side.
- Handle the part that actually costs time: these are metered read sources, so an uncached lookup on every page view burns the customer's allowance. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Semrush update is not your on-call problem.
- One integration serves your product and your agents. The same governed Semrush connection powers in-product features and gives AI agents scoped, audited access, so you answer questions from an authoritative outside source without holding that data yourself without wiring it twice.
Used by these teams
Compare with
Clearbit
Dun & BradstreetWorks well with
HubSpotOften used alongside
Tools the same teams tend to run next to Semrush, across other categories.
Salesforce
Notion
Snowflake
BoxSemrush integration FAQ
How do I add a Semrush integration to my product?
Enable the Semrush connector in your fastn dashboard, then let each customer authenticate their own Semrush account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Semrush client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Semrush account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Semrush account and only ever sees their own lookups, results and reports. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Semrush integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent pulls keyword and competitor data for one customer's domain and explains where the visibility gap is.
Who maintains the Semrush integration?
fastn does. When Semrush changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose credentials does a Semrush lookup run under?
Each customer's own. Quota and cost land on the customer that caused them rather than on a shared key you have to meter and re-bill, and one heavy customer cannot exhaust another's allowance.
How should Semrush results be cached?
Per tenant, with a window that matches how fast the underlying data actually moves. Semrush is a read source rather than a system of record, so the same query returns the same answer until the source changes, and caching is the difference between a sustainable integration and one that exhausts a customer's allowance on a busy page.
What can I build with the Semrush integration?
A common starting point: let each customer connect their own Semrush account so queries run on their units rather than on a shared key you have to meter. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Semrush integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Semrush does not change your per-connector cost. You can start free with 3 connected accounts.
Add Semrush to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.