X-API-KEY header. One-shot extraction charges credits per call, so extractor.extract and extractor.parse are marked as writes.
Agent extractions and async scraper runs answer 202 with an id: poll agent.getTask (statuses pending, running, completed, failed, stopped) or scrapers.getRun (running, completed, completed_partial, failed), and stop a running extraction with agent.stopTask. The plugin declares these as jobs, so the agent can follow them with get_job.
Every extraction result is an open record: its keys are the attribute names you sent, or whatever structure the prompt produced. The docs publish no fixed result schema, so the plugin does not invent one.
Every operation is described in the official docs: https://parsera.org/docs/api
What you get:
- 15 typed API operations
Setup
1
Install
2
Add the plugin
corsair.ts
multiTenancy: true, scope calls with corsair.withTenant(id). See Quick start for KEK + Hub keys, and Multi-tenancy for account isolation.3
Choose authentication
- API Key (Recommended)
Store the Parsera API key before the first call: More: API Key
pnpm corsair setup --plugin=parsera --tenant=acme api_key=<your-key> (leave out --tenant without multiTenancy), or pass it as key in the plugin options. With Hub, each tenant enters their own key on the connect page. See API key auth.4
Connect a tenant
Mint a connect link and send the tenant to it. Hub hosts the page and delivers the result to your app — see Connect / OAuth.
Example API calls
Read an extraction taskWhat’s next
API reference
Every
parsera.api.* operation with input and output types.Connect / OAuth
createLink, Hub delivery, and tenant connect flows.
Use with agents
Expose this plugin’s operations as MCP tools.