Connect your agent to any HTTP API on the fly — discover, map, and fetch typed data.
Most database access work still happens through a UI a human drives. Liquid MCP server moves it into the conversation instead. Connect your agent to any HTTP API on the fly — discover, map, and fetch typed data.
Point Liquid at a URL or a database and it works out the interface for you: discovers its shape, maps it to the fields you asked for, and handles auth, pagination and normalization — typed records, no client code. When the upstream drifts, it re-maps and keeps going. The same small API — fetch · query · write · sense — reaches web APIs, databases, other agents (MCP/A2A), email, and even IoT and industrial systems (MQTT, Modbus, OPC UA, BACnet). An LLM does the learning at setup (and on drift); the data path itself makes no model call.
The server publishes 9 tools. What each one is for:
Interface — RuntimeGraphQL — ✅ query + Relay paginationgRPC — ✅ unary + server-streaming (reflection)WebSocket — ✅ bounded batch reads + subscribe + live senseSQLite — ✅ tables/views, filters, paginationDuckDB — ✅ tables/views, filters, paginationDiscovery — Where it looksDatabases — catalog introspection (postgres://, mysql://, mongodb://, redis://, neo4j://, …)Browser — Playwright capturing networkBecause this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Configuration is passed through the environment: OPENAI_API_KEY, GEMINI_API_KEY, ANTHROPIC_API_KEY, OPENAI_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Liquid's toolset — Interface, GraphQL, gRPC and 6 more — is a fair guide to whether it matches your workflow. It is maintained by ertad-family; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Liquid's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Interface | Runtime |
| GraphQL | ✅ query + Relay pagination |
| gRPC | ✅ unary + server-streaming (reflection) |
| WebSocket | ✅ bounded batch reads + subscribe + live sense |
| SQLite | ✅ tables/views, filters, pagination |
| DuckDB | ✅ tables/views, filters, pagination |
| Discovery | Where it looks |
| Databases | catalog introspection (postgres://, mysql://, mongodb://, redis://, neo4j://, …) |
| Browser | Playwright capturing network |
Claude Desktop / any MCP client:
```json
{ "mcpServers": { "liquid": {
"command": "uvx",
"args": ["liquid-mcp"],
"env": { "OPENAI_API_KEY": "sk-..." }
} } }Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_BASE_URL | Endpoint or connection string the server talks to. | Yes |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.