Skip to main content
Glama

Connect to an API (one-time setup)

liquid_connect
Idempotent

Set up a reusable adapter for any HTTP API by providing its URL and desired data model. The tool discovers the API and uses an LLM to map responses to your target fields, saving the adapter for later data retrieval.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesBase URL or a specific endpoint of the API (e.g. https://api.example.com or https://api.example.com/v1/users). Also accepts a GraphQL endpoint, a WSDL URL, or grpc:// / wss:// targets.
target_modelYesThe record shape you want back: a flat map of field name -> type, e.g. {"name": "str", "price": "float", "in_stock": "bool"}. Liquid maps the API's raw response onto exactly these fields; everything else is dropped.
credentialsNoOptional secrets for an auth-walled API, e.g. {"api_key": "..."}, {"token": "..."}, or {"username": "...", "password": "..."}. Stored encrypted under ~/.liquid and applied automatically on every later fetch. Omit for public APIs.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNo"connected" or "review_needed".
adapter_idNoUse this id with liquid_fetch/liquid_query.
serviceNo
mapped_fieldsNo
endpointsNo
errorNo
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide idempotentHint=true, destructiveHint=false, readOnlyHint=false. Description adds: makes outbound HTTP(S) requests, calls LLM (requires API key), persists adapter and credentials under ~/.liquid, and idempotent behavior (reuses existing adapter). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph but each sentence contributes meaning: setup, side effects, idempotency, usage guidance. It is front-loaded with key information. Slightly dense but efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (API discovery, LLM mapping, persistence), the description covers purpose, side effects, idempotency, and alternatives. It references the return of adapter_id. With high schema coverage and annotations, it provides sufficient context for correct agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with good descriptions. Description adds value by explaining that url accepts various endpoint types, target_model is a flat map and extraneous fields are dropped, and credentials are stored encrypted. This exceeds the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verbs ('Discovers', 'maps', 'saves', 'returns') and clearly identifies the resource (API connection, adapter). It distinguishes from siblings by mentioning liquid_discover and liquid_fetch, making its unique role evident.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use this once per API.' and provides alternatives: 'For a quick look without saving anything, use liquid_discover instead; to read data from an already-connected API, use liquid_fetch.' Also notes idempotency implying no need to repeat for same url+target_model.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ertad-family/liquid'

If you have feedback or need assistance with the MCP directory API, please join our Discord server