PluginBench
MCP Server
Maintained

Liquid MCP Server

io.github.ertad-family/liquid

RepositoryRegistry
How to choose

What this kind of tool is for

  • Automate a build, test, or deployment step you repeat by hand.
  • Review or refactor code in an existing repository without leaving your agent.
  • Bridge an internal service or CLI into the agent toolset.

How to compare servers like this

Scope of control:
Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
Environment fit:
Match the runtime it expects (Node, Python, a container) to what you actually run.
Maintenance signal:
Check the last-commit date — dev tooling that lags upstream breaks first.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Liquid MCP server?

Connect your AI agent to anything — APIs, databases, and agents; read and write, auto-discovered.

How to install Liquid

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OPENAI_API_KEY
    secret

    OpenAI (or compatible) API key for discovery

  • OPENAI_BASE_URL

    OpenAI-compatible base URL, e.g. local Ollama/vLLM

  • GEMINI_API_KEY
    secret

    Google Gemini API key (alternative)

  • ANTHROPIC_API_KEY
    secret

    Anthropic API key (alternative)

  • LIQUID_ALLOW_WRITES

    Set to 1 to expose the liquid_execute write tool (database insert/update/delete). Off by default — read-only.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "liquid": {
      "command": "uvx",
      "args": [
        "liquid-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "OPENAI_BASE_URL": "<YOUR_OPENAI_BASE_URL>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "LIQUID_ALLOW_WRITES": "<YOUR_LIQUID_ALLOW_WRITES>"
      }
    }
  }
}

Related MCP servers

Let AI agents interact with real BLE hardware — scan, connect, read, write, and subscribe to notifications.

16
Python
MIT
View repository →

Let AI agents interact with debug probes—connect, flash, read/write memory, and reset embedded targets.

10
Python
MIT
View repository →

AI agents interact with serial devices — list ports, connect, send, read, and automate test flows.

17
Python
MIT
View repository →

Semantic, format-aware diff of config files (JSON/YAML/TOML/INI/.env/XML/CSV) for AI agents

41
JavaScript
MIT
View repository →

Predictive dependency security engine. Trust scores, zombie detection, blast radius analysis.

0
TypeScript
MIT
View repository →

Give AI agents read/write access to your Obsidian vault locally or via cloud-synced CouchDB.

45
TypeScript
MIT
View repository →