Liquid
Connect your agent to any HTTP API on the fly — discover, map, and fetch typed data.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"liquid": {
"command": "uvx",
"args": [
"liquid-mcp"
],
"env": {
"OPENAI_API_KEY": "<your-openai_api_key>",
"OPENAI_BASE_URL": "<openai_base_url>",
"GEMINI_API_KEY": "<your-gemini_api_key>",
"ANTHROPIC_API_KEY": "<your-anthropic_api_key>"
}
}
}
}OPENAI_API_KEYOpenAI (or compatible) API key for discovery
OPENAI_BASE_URLOpenAI-compatible base URL, e.g. local Ollama/vLLM
GEMINI_API_KEYGoogle Gemini API key (alternative)
ANTHROPIC_API_KEYAnthropic API key (alternative)
Deterministic AI governance platform. Validates agent outputs, discovers patterns, solves math.
Visual AI for strategic thinking — SWOT, flowcharts, mindmaps, Gantt diagrams as polished SVG.
Your AI Product Manager. Surface insights, build roadmaps, and plan strategy with 30+ tools.