One-time setup for an API. Discovers the API at url, uses an LLM to map its responses onto your target_model, and saves a reusable adapter; returns an adapter_id you then pass to liquid_fetch / liquid_query / liquid_estimate. Side effects: makes outbound HTTP(S) requests to url, calls the configured LLM (requires an API key), and persists the adapter + any credentials under ~/.liquid. Idempotent — re-connecting the same url+target_model reuses the existing adapter instead of duplicating it. Use this once per API. For a quick look without saving anything, use liquid_discover instead; to read data from an already-connected API, use liquid_fetch.

List the adapters already connected on this machine (read from ~/.liquid) — read-only, no network call, no LLM. Each entry has its adapter_id, service name, source url and endpoint paths. Call this to find an adapter_id for liquid_fetch / liquid_query / liquid_estimate, or to check whether an API is already connected before calling liquid_connect.

Fetch records through a connected adapter, mapped to the target_model you set at connect time — deterministic, no LLM call. Side effects: makes a read-only outbound HTTP(S) request to the connected API using the stored credentials; it is subject to that API's rate limits (Liquid throttles proactively and surfaces 429s with retry hints). Returns {records, data: [up to 100 mapped records], _meta}. Requires an adapter_id from liquid_connect. Use this to pull whole records; to filter/aggregate server-side and get a smaller answer use liquid_query instead; to size a pull before making it, call liquid_estimate first.

Run a server-side search or aggregation through an adapter and get just the answer instead of the full payload — deterministic, no LLM call, read-only. Two modes: set group_by/agg to aggregate (counts, sums, …), or where/fields/limit to filter and project. Side effects: a read-only outbound HTTP(S) request to the connected API, rate-limited like liquid_fetch. Returns search results {records, data, _meta} or an aggregation {result, _meta}. Prefer this over liquid_fetch whenever you only need a filtered slice, a count, or a summary — it returns far fewer tokens.

Inspect an API's shape — service name, discovery method, auth type and endpoint list — without creating or saving an adapter. Side effects: makes outbound HTTP(S) requests to url to probe it, and may call the configured LLM for APIs that publish no machine-readable spec (REST heuristic). Read-only: nothing is persisted. Use this to preview an unknown API; when you're ready to actually read data, call liquid_connect, which discovers and maps and saves a reusable adapter.

Pre-flight estimate for a fetch — predicted item count, bytes, tokens, credits and latency, each with a confidence and source — without making any HTTP call or LLM call. Read-only and free. Returns {estimate: {...}}. Check this before a potentially large liquid_fetch to decide whether to narrow the pull with liquid_query (filter/aggregate) first. Requires an adapter_id from liquid_connect.