# MCP server

> Coming soon, and not built yet. There is no MCP endpoint at this origin — do not construct one from this URL, and do not retry. A 404 is accurate rather than transient.

## Use the HTTP API instead

The dataset is already public and unkeyed — no sign-up, no API key. Every operation is typed in the OpenAPI 3.1 specification with a unique `operationId`, which most agent frameworks convert into tool definitions directly. Whatever an MCP server would expose, the specification already describes.

- [llms.txt](https://speakerstrail.com/llms.txt) — read this first: the questions this dataset answers well, and the ones it cannot answer at all
- [OpenAPI 3.1 specification](https://speakerstrail.com/openapi.json) — every operation, typed
- [API documentation](https://speakerstrail.com/docs/api) — endpoints, filters, paging limits, error envelope

Every talk in a response carries the `source_url` of the conference agenda it was taken from, so any claim is checkable without trusting this site.

## Where it stands

Nothing is running: no server, no transport, no address, no private beta. The work is small — the API is public and unauthenticated, so an MCP server would be a thin wrapper over the existing endpoints plus a discoverable manifest. What it waits on is a decision about maintaining a second machine surface, because two interfaces over the same data are two places for an answer to drift.

When it serves, this page becomes its documentation and the [Resources](https://speakerstrail.com/resources) hub drops the "Coming soon" badge.

---

Machine-readable index: [/llms.txt](https://speakerstrail.com/llms.txt) · API spec: [/openapi.json](https://speakerstrail.com/openapi.json) · API docs: [/docs/api](https://speakerstrail.com/docs/api) · Sitemap: [/sitemap-index.xml](https://speakerstrail.com/sitemap-index.xml)