Liquid

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/ertad-family-liquid

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

6 read · 1 write · 1 delete

Secrets

3 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Python package

Tools (8)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• liquid_connectConnect to an API (one-time setup)

  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…

• liquid_discoverInspect an API without saving an adapterread-only

  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.

• liquid_estimateEstimate a fetch (no call)read-only

  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.

• liquid_executeWrite to a database (insert/update/delete)can change or delete data

  Mutate data in a connected database: INSERT, UPDATE, or DELETE a row. Only database adapters (postgres/mysql/sqlite/duckdb/mssql) support this; API adapters are read-only here. `update` and `delete` require a non-empty `where` (no blanket mutations); columns are validated against the discovered schema and every value is parameterized. This tool is only available because the server was started with LIQUID_ALLOW_WRITES=1. Returns {success, op, endpoint, affected_rows}.

• liquid_fetchFetch records through an adapterread-only

  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 liqu…

• liquid_list_adaptersList connected adaptersread-only

  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.

• liquid_querySearch or aggregate through an adapterread-only

  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.

• liquid_senseCheck the agent's senses (poll for new events)read-only

  Perceive what's happened in the world since you last checked: poll an endpoint for events that occurred after `cursor` — new database rows, published messages, etc. Returns a batch of events (each with a `modality`, a `payload`, and a `cursor`) plus a `next_cursor` to resume from. This is the read side of the agent's senses — call it repeatedly, passing back the last `next_cursor`, to stay aware of changes without re-seeing old events. Bounded by `max_events` / `max_seconds` so it always returns promptly. Where liquid_fetch is a one-shot pull of current state, liquid_sense perceives what chang…

Signals

Stars

3

Forks

2

Open issues

13

Weekly downloads

42

Last commit

Jun 9, 2026 (4 months ago)

Last release

Jun 4, 2026 (4 months ago)

Last package publish

May 27, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.ertad-family/liquid

Version

0.2.0

Auth

API key

Packages

pypi liquid-mcp

License

License unknown

Repository

github.com/ertad-family/liquid

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql