Reference & Lookup Data · Integration
Exa
Add Exa to your product for your customers, and give your AI agents governed access to it.
Exa is a search API built for retrieval by models rather than by people, and the difference is real: you can ask for results by meaning rather than by keyword, and request the page contents alongside the result so a second fetch is unnecessary. That matters because the usual failure of a search-then-scrape pipeline is the scrape, not the search. Results are computed per request rather than stored, so there is nothing to sync and the objects worth naming are the query, the results and the extracted contents. Keys are per account, so a customer bringing their own keeps usage and cost on their side. fastn scopes the key per tenant and audits each lookup.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer bring their own Exa key so web lookups run on their account and their budget.
Search by meaning rather than keyword, which is what makes retrieval useful to a model.
Fetch page contents with the result, avoiding a separate and failure-prone scrape step.
Constrain a search to a domain or a date range so results stay relevant to the customer's question.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent researches a question and cites the pages it used, with every lookup audited per tenant.
An agent fetches contents for a shortlist of results rather than the whole result set.
An agent restricts a search to a customer's competitor list before summarising.
Example prompt
Find recent pages about this topic and pull the contents of the three most relevant.
Set up Exa in 4 steps
- 01Enable the Exa connector from your fastn dashboard.
- 02Have each customer authorise their own Exa account, so calls run under their credentials rather than a shared key.
- 03Decide which lookups, results and reports your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Exa integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an Exa integration without building it. Your customers connect their own Exa 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 an Exa update is not your on-call problem.
- One integration serves your product and your agents. The same governed Exa 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
Google Search Console
SemrushWorks well with
OpenAIOften used alongside
Tools the same teams tend to run next to Exa, across other categories.
Salesforce
HubSpot
Notion
SnowflakeExa integration FAQ
How do I add an Exa integration to my product?
Enable the Exa connector in your fastn dashboard, then let each customer authenticate their own Exa account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Exa client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Exa account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Exa 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 Exa 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 researches a question and cites the pages it used, with every lookup audited per tenant.
Who maintains the Exa integration?
fastn does. When Exa 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 an Exa 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 Exa results be cached?
Per tenant, with a window that matches how fast the underlying data actually moves. Exa 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 Exa integration?
A common starting point: let a customer bring their own Exa key so web lookups run on their account and their budget. 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 Exa integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Exa does not change your per-connector cost. You can start free with 3 connected accounts.
Add Exa to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.