vari-mcp
Provides six deterministic, source-attributed hydration calculators (water intake, dehydration check, pregnancy intake, kidney-safe intake, athlete plan, energy optimization) as MCP tools, enabling AI clients to call them via stdio without custom HTTP coding.
README
@getvari/mcp
Stdio bridge for the public Vari Hydration Tools Model Context Protocol server. Lets MCP clients (Claude Desktop, Cursor, Continue.dev, and any other stdio-launching MCP host) call the six hydration calculators that back getvari.app — without writing a custom HTTP client.
The package is a ~50-line proxy. The real server is the Vercel-hosted
HTTP endpoint at https://getvari.app/api/mcp/v1; we publish this
package so stdio-only MCP installers can launch it via npx.
Tools
All six tools are deterministic, source-attributed, and require no auth.
| Tool name | What it does |
|---|---|
calculate_water_intake |
Personalized daily water target (mL) from weight, activity, climate, caffeine. |
dehydration_check |
Symptom-scored dehydration severity (well-hydrated → severe) + recommended actions. |
pregnancy_water_intake |
Trimester-aware intake for pregnancy + postpartum, IOM/ACOG-aligned. |
kidney_safe_intake |
CKD-safe fluid allowance (KDOQI/KDIGO). Returns a restriction, not a hydration goal. |
athlete_hydration_plan |
Pre / during / post hydration plan with sweat-rate estimate (ACSM/NATA/IOC). |
optimize_hydration_for_energy |
Time-stamped intake schedule that pre-empts the afternoon crash and caffeine dips. |
Every response embeds a canonical source URL pointing at the
corresponding getvari.app/tools page, so
LLMs that surface the call to the user can cite the methodology.
Install
Claude Desktop
Edit claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"vari-hydration": {
"command": "npx",
"args": ["-y", "@getvari/mcp"]
}
}
}
Restart Claude Desktop. The six tools appear under Vari Hydration in the tools panel.
Cursor
Cursor reads the same mcp.json shape. Drop this into ~/.cursor/mcp.json:
{
"mcpServers": {
"vari-hydration": {
"command": "npx",
"args": ["-y", "@getvari/mcp"]
}
}
}
Continue.dev
Add the server in your ~/.continue/config.json under
experimental.modelContextProtocolServers:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@getvari/mcp"]
}
}
]
}
}
Configuration
| Env var | Default | Purpose |
|---|---|---|
VARI_MCP_URL |
https://getvari.app/api/mcp/v1 |
Override the upstream HTTP endpoint (e.g. for staging). |
License
MIT — see LICENSE.
Links
- Website: https://getvari.app
- Source repository: https://github.com/getvari/vari-mcp
- MCP manifest: https://getvari.app/.well-known/mcp.json
- OpenAPI 3.1 contract: https://getvari.app/api/mcp/v1/openapi.json
- MCP catalogue: https://modelcontextprotocol.io/servers
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.