Data & Storage · Integration
Algolia
Add Algolia to your product for your customers, and give your AI agents governed access to it.
Algolia is hosted search, so what you work with is an index, the records inside it, and the settings that decide how those records rank. Relevance is not requested at query time: searchable attributes and their order, custom ranking, synonyms and query rules are index-level settings, and a search behaves the way it does because of how its index was configured. Records also have to be flattened before they can be searched, so a nested object graph is denormalised into the attributes a query can match on, and deciding what to duplicate into each record is the real design work. Sorting by another attribute means a replica index rather than an order clause. fastn stores each application's keys per tenant and maintains the search API surface.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Algolia application so their content is indexed under keys they hold themselves.
Push and update records as your product's data changes, flattened into the attributes a query has to match on.
Set searchable attributes, custom ranking and synonyms per index, so relevance is tuned rather than hoped for.
Add a replica index when a customer wants results sorted differently, and query rules for the results they want pinned.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent searches a customer's index and cites the records it used to answer.
An agent adds a synonym or edits a query rule inside the permissions granted, with the index it changed logged.
An agent explains why a record ranks where it does by reading that index's own ranking settings.
Example prompt
Why does this record not come back when I search that term, and which attributes are searchable on the index?
Set up Algolia in 4 steps
- 01Enable the Algolia connector from your fastn dashboard.
- 02Have each customer authorise their own Algolia account, so calls run under their credentials rather than a shared key.
- 03Decide which indices, records, searchable attributes and synonyms your product needs, and remember that relevance is decided by index settings rather than at query time.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Algolia integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an Algolia integration without building it. Your customers connect their own Algolia account inside your product and work their records, datasets and fields there, with no per-customer code on your side.
- Handle the part that actually costs time: schemas differ per customer and change without notice, and volumes can be large. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so an Algolia update is not your on-call problem.
- One integration serves your product and your agents. The same governed Algolia connection powers in-product features and gives AI agents scoped, audited access, so you read and write your customers' data where it already lives without wiring it twice.
Used by these teams
Compare with
Elasticsearch
Bonsai Elasticsearch
PineconeOften used alongside
Tools the same teams tend to run next to Algolia, across other categories.
Anthropic Claude
OpenAI
Azure OpenAI
Hugging FaceAlgolia integration FAQ
How do I add an Algolia integration to my product?
Enable the Algolia connector in your fastn dashboard, then let each customer authenticate their own Algolia account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Algolia client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Algolia account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Algolia account and only ever sees their own records, datasets and fields. 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 Algolia 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 searches a customer's index and cites the records it used to answer.
Who maintains the Algolia integration?
fastn does. When Algolia 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.
Does the Algolia integration adapt when a customer's schema changes?
Schema and field mapping is configuration per customer, so a change on their side is a mapping update rather than a code change and a release on yours.
How are large Algolia reads handled?
Pagination and throttling are handled for you, and initial backfills are rate-limited so a large import does not exhaust a customer's API allowance.
What can I build with the Algolia integration?
A common starting point: let each customer connect their own Algolia application so their content is indexed under keys they hold themselves. 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 Algolia integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Algolia does not change your per-connector cost. You can start free with 3 connected accounts.
Add Algolia to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.