Quickstart
Create a key and make your first request in two minutes.
MCP server
Connect Claude, Cursor or any MCP client to Pav data.
API reference
Every endpoint, parameter and response schema.
OpenAPI and agents
Machine-readable spec for client generation and tool wiring.
What you can access
Current program and company counts are available at any time from
GET /v1/stats.
How the data connects
Every dataset joins through Pav ids.- A company (
company_id) owns programs (id). - A program lists its linked clinical trials (
nct_id). A trial lists the Pav programs and companies linked to it. - A deal lists its party companies; filter deals by
company_id. - A patent family lists its owner companies; filter patents by
company_id. - An FDA record carries its linked company; filter FDA records by
company_id. - A change records a program’s movement and carries its
company_id.
GET /v1/companies?q=..., then reuse the id
across every dataset.
API at a glance
- Base URL:
https://api.pav.bio - All endpoints are
GETand return JSON. - Authenticate with a Pav API key:
Authorization: Bearer <api_key>. See Authentication. - List endpoints return
{ "data": [...], "pagination": {...} }. See Pagination. q=runs relevance-ranked search on programs, companies and trials, and exact-term matching on deals and patents. See Search and filters.- 300 requests per minute per key. Errors share one envelope. See Rate limits and errors.
Built for
- Competitive landscapes by target, indication or modality.
- Deal screening and comparable-transaction work.
- Patent, exclusivity and loss-of-exclusivity checks.
- Pipeline monitoring and alerting.
- AI agents that answer biopharma questions with sourced data.