Can I search for people and run research with the Happenstance API?

Yes. An agent creates a search from a description and reads the ranked results, then calls find-more to widen the pool. Separately it can start a research job on a person and read the research back by its id once it is ready, so discovery and deep research are two distinct flows.

What are the rate limits for the Happenstance API?

The OpenAPI spec does not state a numeric rate limit, but it does expose a usage endpoint an agent can read to track its own consumption. Add retry and backoff around 429 responses, and check the Happenstance documentation at https://developer.happenstance.ai for any published limits.

Can I limit what my agent is allowed to do with the Happenstance API?

Yes. Write a rule that allows the search create and read operations for one search id, so the agent can run and widen a specific search while the research and account operations stay out of reach until you add them, and every call it makes is logged. Happenstance carries search and research ids in the URL path, which is what makes that per-resource boundary possible.

Is there a Happenstance MCP server?

You do not need an MCP server to give your agent the Happenstance API. Jentic connects it directly from the Jentic API Directory: import Happenstance, store your token once, and your agent calls the search and research operations on demand without loading another server's tool definitions into its context.

How do I search for people with the Happenstance API through Jentic?

Search Jentic by intent such as 'search people in my network', and Jentic returns the Happenstance search operation with its input schema so the agent sends the right fields. To run it on your own infrastructure, install Jentic One from its GitHub repo with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then add Happenstance from the directory.