Workflow & Automation · Integration
Agenty
Add Agenty to your product for your customers, and give your AI agents governed access to it.
Agenty runs are asynchronous jobs against a saved agent: you POST to https://api.agenty.com/v2/jobs/start with an agent_id in the body, and stopping is a GET on /v2/jobs/{job_id}/stop rather than a DELETE. The v2 root matters, because the older v1 paths now return 404 while v2 answers with a proper 401 when unauthenticated, and integrations copied from old tutorials fail silently on that alone. The job object is where the useful state lives: status, priority, and page counters for total, processed, succeeded and failed, which is the only reliable way to tell a finished run apart from one that completed with most pages failing. Results are fetched separately from the job record, so a job reaching a terminal status is not the same as having the data. fastn holds each customer's Agenty key, polls the job to completion, and keeps the connection maintained as keys change.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own Agenty account so scraping jobs run on their agents and their page allowance
Trigger a saved extraction agent when a customer adds a new source and store the output against that record
Show job progress in your UI using the processed and failed page counters rather than a spinner
Retry or stop a long running job from inside your product when a customer changes their mind
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent start a named Agenty agent and report back once the job reaches a terminal status
Have an agent check a running job and explain why the failed page count is climbing
Audit per tenant which jobs an agent started and stopped, since page volume is billed to that tenant
Example prompt
Start the pricing scraper and tell me how many pages succeeded when it finishes.
Set up Agenty in 4 steps
- 01Enable the Agenty connector from your fastn dashboard.
- 02Have each customer authorise their own Agenty account, so calls run under their credentials rather than a shared key.
- 03Decide which processes, runs and queues 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 Agenty integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an Agenty integration without building it. Your customers connect their own Agenty account inside your product and work their processes, runs and queues there, with no per-customer code on your side.
- Handle the part that actually costs time: runs are asynchronous and can fail long after they are accepted, so an outcome that never arrives must look different from one that succeeded. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so an Agenty update is not your on-call problem.
- One integration serves your product and your agents. The same governed Agenty connection powers in-product features and gives AI agents scoped, audited access, so you start work in the automation platform your customers already run, and get the outcome back without wiring it twice.
Used by these teams
Compare with
Ansible
Automation Anywhere
Microsoft Power AutomateOften used alongside
Tools the same teams tend to run next to Agenty, across other categories.
Amazon SES
Resend
Mailgun
PostmarkAgenty integration FAQ
How do I add an Agenty integration to my product?
Enable the Agenty connector in your fastn dashboard, then let each customer authenticate their own Agenty account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Agenty client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Agenty account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Agenty account and only ever sees their own processes, runs and queues. 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 Agenty integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Let an agent start a named Agenty agent and report back once the job reaches a terminal status
Who maintains the Agenty integration?
fastn does. When Agenty 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.
Can my product start an Agenty run and read its outcome?
Yes. Your product can trigger a process in the customer's own Agenty account, pass it input, and take the result back as an event rather than polling for it.
What happens when an Agenty run is slow or fails?
The failure surfaces with its error rather than as a silent timeout, and the run keeps its own identifier so a retry can be matched to the original. That matters more here than in most integrations, because a run that half-completed is not the same as one that never started.
What can I build with the Agenty integration?
A common starting point: let a customer connect their own Agenty account so scraping jobs run on their agents and their page allowance. 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 Agenty integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Agenty does not change your per-connector cost. You can start free with 3 connected accounts.
Add Agenty to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.