AI & Models · Integration
Anthropic Claude
Add Anthropic Claude to your product for your customers, and give your AI agents governed access to it.
Embed an Anthropic Claude integration so your product can call the Messages API on each customer's own API key rather than pooling everything through yours, with usage attributable per tenant and every call logged. Model selection, system prompts, and tool definitions are configuration per customer, so supporting a customer who wants a different model is not a release. fastn handles credential storage and API upkeep.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer bring their own Anthropic API key so model usage and spend sit with them.
Send messages with your product's system prompt and tool definitions, and stream responses back to the user.
Choose the model per customer or per feature as configuration rather than a code change.
Submit and poll batch requests for the bulk work your product runs in the background.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent uses Claude to summarise or classify data it has already fetched from other connected systems.
An agent runs a scoped tool-use loop where the available tools are governed by your permissions.
An agent reacts to a queued job and processes the batch, with token usage logged per tenant.
Example prompt
Summarise the tickets this account opened this month and group them into recurring themes.
Set up Anthropic Claude in 4 steps
- 01Open the Anthropic Claude connector from your fastn dashboard.
- 02Have each customer add their own Anthropic API key.
- 03Configure the models, system prompts, and tools your product uses, then enable actions.
- 04Call them from your product, or expose them to an agent through the MCP server.
Why teams use the Anthropic Claude integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an Anthropic Claude integration without building it. Your customers connect their own Anthropic Claude 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 an Anthropic Claude update is not your on-call problem.
- One integration serves your product and your agents. The same governed Anthropic Claude 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
Works well with
GitHub
Notion
SlackOften used alongside
Tools the same teams tend to run next to Anthropic Claude, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeAnthropic Claude integration FAQ
How do I add an Anthropic Claude integration to my product?
Enable the Anthropic Claude connector in your fastn dashboard, then let each customer authenticate their own Anthropic Claude account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Anthropic Claude client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Anthropic Claude account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Anthropic Claude 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 Anthropic Claude 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 uses Claude to summarise or classify data it has already fetched from other connected systems.
Who maintains the Anthropic Claude integration?
fastn does. When Anthropic Claude 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 Anthropic Claude API key and quota does each call use?
Each customer authorises their own Anthropic Claude 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 Anthropic Claude integration?
A common starting point: let each customer bring their own Anthropic API key so model usage and spend sit with them. 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 Anthropic Claude integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Anthropic Claude does not change your per-connector cost. You can start free with 3 connected accounts.
Add Anthropic Claude to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.