Meetings & Voice · Integration
Fathom
Add Fathom to your product for your customers, and give your AI agents governed access to it.
Fathom sits in a meeting, records it, and hands back the parts people actually reuse: the full transcript, a structured summary, the action items it heard, the participants it saw and the CRM records the meeting was associated with. The API is read-shaped, which is the honest framing, you list meetings over a date range and fetch what each produced. Two details shape the build. A transcript can be inlined on the meeting response or requested on its own, and the separate call switches to asynchronous delivery when you hand it a destination URL, which is what you want for a long call. And nothing exists until processing finishes, so the new meeting content webhook is the trigger rather than a schedule that is always slightly early. The per-minute request limit is modest, so a first backfill has to be paced. Each customer connects their own key, and fastn keeps it scoped to them.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Fathom account so your product reads only the meetings that account recorded.
Take the new meeting content webhook as the trigger, since a transcript does not exist until processing has finished.
Pull the action items and the summary rather than the whole transcript when that is all your product needs.
Pace a first backfill against a modest per-minute limit instead of pulling a year of meetings in one go.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent answers a question about what was agreed by quoting the transcript it came from.
An agent turns the action items off a call into work in the tool the team actually uses.
An agent reports which meetings this week have no follow-up recorded against them.
Example prompt
What did we commit to on the calls with this account this month, and has any of it been followed up?
Set up Fathom in 4 steps
- 01Enable the Fathom connector in your fastn dashboard.
- 02Have each customer create their own API key, so your product reads only the meetings their account recorded.
- 03Subscribe to the new meeting content webhook, choose whether transcripts are inlined or delivered asynchronously, and set the pace of your first backfill.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Fathom integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Fathom integration without building it. Your customers connect their own Fathom account inside your product and work their meetings, calls and participants there, with no per-customer code on your side.
- Handle the part that actually costs time: a call or a meeting is a real-time event, so a missed join or a dropped recording cannot be retried later. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Fathom update is not your on-call problem.
- One integration serves your product and your agents. The same governed Fathom connection powers in-product features and gives AI agents scoped, audited access, so you let your product act on the conversations that happen by voice and video, not just the written ones without wiring it twice.
Used by these teams
Compare with
Gong
Chorus.ai
ZoomOften used alongside
Tools the same teams tend to run next to Fathom, across other categories.
Slack
Microsoft Teams
Twilio
CalendlyFathom integration FAQ
How do I add a Fathom integration to my product?
Enable the Fathom connector in your fastn dashboard, then let each customer authenticate their own Fathom account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Fathom client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Fathom account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Fathom account and only ever sees their own meetings, calls and participants. 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 Fathom 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 answers a question about what was agreed by quoting the transcript it came from.
Who maintains the Fathom integration?
fastn does. When Fathom 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 schedule or act on Fathom conversations automatically?
Yes. Within the permissions each customer grants, your product can create a meeting, place or route a call, add participants, or react when one ends, all inside their own Fathom account rather than through a shared one.
Can I get recordings, transcripts and outcomes back from Fathom?
Yes, scoped per tenant and audited. This matters more here than in most integrations, because the substance of a call usually exists only in its recording or transcript, so a read that fails silently loses the thing you wanted.
What can I build with the Fathom integration?
A common starting point: let each customer connect their own Fathom account so your product reads only the meetings that account recorded. 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 Fathom integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Fathom does not change your per-connector cost. You can start free with 3 connected accounts.
Add Fathom to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.