AI & Models · Integration
Skyvern
Add Skyvern to your product for your customers, and give your AI agents governed access to it.
Skyvern drives a browser with a vision model instead of a selector script, which is why it survives a redesign that would break a scraper. You give a run a prompt, a starting URL and optionally a schema for the answer, and it navigates, fills forms and returns the structured result along with the artefacts it produced on the way. An embedded Skyvern integration starts runs, reads their status and output, and reacts to the webhook when one completes. Two things change when you embed it rather than script it. Every run costs money and uses somebody's credentials, so it should be the customer's own key and quota instead of a shared one you re-bill. And because a model decided what to click, the run's input, output and artefacts are the only record of what happened, which makes per-tenant auditing the point rather than a nicety. fastn holds the keys and exposes the same governed connection to your agents.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Skyvern account so browser runs are billed to them and use their own credentials.
Start a run inside your workflow, such as retrieving a document from a portal that has no API at all.
Read structured output against a schema you define so the result lands in your own data model.
React to the completion webhook so the next step runs the moment an agent finishes rather than on a poll.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent kicks off a browser run to fetch something only a website exposes, then works from the result.
An agent reads a failed run's output and artefacts to explain where the browser got stuck.
An agent runs an approved workflow within scoped permissions, with the prompt and the result recorded per tenant.
Example prompt
Fetch this month's statement from the supplier portal and give me the totals as structured data.
Set up Skyvern in 4 steps
- 01Enable the Skyvern connector in your fastn dashboard.
- 02Have each customer supply their own Skyvern API key so runs are metered and billed to them.
- 03Define the runs your product starts, the schema you want the output in, and where the completion webhook lands.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Skyvern integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Skyvern integration without building it. Your customers connect their own Skyvern account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Skyvern update is not your on-call problem.
- One integration serves your product and your agents. The same governed Skyvern connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
OpenAIWorks well with
Automation AnywhereOften used alongside
Tools the same teams tend to run next to Skyvern, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeSkyvern integration FAQ
How do I add a Skyvern integration to my product?
Enable the Skyvern connector in your fastn dashboard, then let each customer authenticate their own Skyvern account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Skyvern client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Skyvern account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Skyvern account and only ever sees their own models, requests and outputs. 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 Skyvern 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 kicks off a browser run to fetch something only a website exposes, then works from the result.
Who maintains the Skyvern integration?
fastn does. When Skyvern 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 Skyvern API key and quota does each call use?
Each customer authorises their own Skyvern account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the Skyvern integration?
A common starting point: let each customer connect their own Skyvern account so browser runs are billed to them and use their own credentials. 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 Skyvern integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Skyvern does not change your per-connector cost. You can start free with 3 connected accounts.
Add Skyvern to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.