A
licenseA
qualityNot graded
maintenanceSupplement safety MCP server for AI agents. FDA FAERS signals, CYP450 pathways, 584 compound aliases. Works with Claude Desktop, LangChain, CrewAI.
5
1
-
Supplement Advisor MCP Server
by erinheit451
An evidence-based supplement advisor MCP server for AI clients, offering recommendations, comparisons, interaction checks, dosage guidance, and product form classification.
Get ranked supplement recommendations for a condition with clinical evidence, dosing, cost-per-dose, and purchase links for over 100 supplements (
recommend_supplement).Compare different forms of a supplement (e.g., magnesium glycinate vs citrate vs oxide) with absorption data, warnings, and buying advice (
compare_forms).Check if medications deplete nutrients, returning depleted nutrients, mechanisms, severity, and recommended supplements (
check_interactions).Retrieve evidence-based dosage recommendations by supplement and condition, with clinical trial doses, timing, and safety (
get_dosage).Classify any product name or ingredient list for supplement form quality, with verdict, absorption, and better alternatives (
classify_form).Access data sourced from NIH DSLD, PubMed, NSF, and USP, with rankings based on cost-per-effective-dose, certification, and clinical evidence.
Serves as a data source for clinical trial evidence behind supplement recommendations, providing PMID-cited research references for dosing, form comparisons, and condition-specific efficacy.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Supplement Advisor MCP Server Recommend supplements for better sleep"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Supplement Advisor MCP Server
Evidence-based supplement recommendation MCP server. Reads the live product catalog from verifiedsupplementdata.com (with an offline fallback), plus medication interaction checking and form comparisons. Data sourced from NIH DSLD, PubMed, NSF, and USP.
Built for use with Claude, Cursor, Windsurf, and any MCP-compatible client.
Tools
Tool | Description |
| Get ranked supplement recommendations for a condition with clinical evidence, dosing, cost-per-dose, and purchase links |
| Compare different forms of a supplement (e.g., magnesium glycinate vs citrate vs oxide) with absorption data and warnings |
| Check if medications deplete nutrients — covers statins, metformin, PPIs, birth control, and more |
| Get evidence-based dosage recommendations by condition, with clinical trial references and timing guidance |
| Paste any product name or ingredient list and get a quality verdict on the supplement form used |
Related MCP server: citedhealth-mcp
Supplements Covered
Magnesium (glycinate), Vitamin D3, Omega-3, Creatine, Iron (bisglycinate), Vitamin B12, CoQ10, Collagen, Multivitamin, Protein, Biotin, Calcium Citrate, Vitamin C, Methylfolate, Probiotics, Ashwagandha, L-Theanine, Tongkat Ali, Zinc
Quick Start (npx)
npx supplement-advisor-mcpClaude Desktop / Claude Code Configuration
Add to your MCP config:
{
"mcpServers": {
"supplement-advisor": {
"command": "npx",
"args": ["-y", "supplement-advisor-mcp"]
}
}
}Installation (from source)
git clone https://github.com/erinheit451/supplement-advisor-mcp.git
cd supplement-advisor-mcp
npm install
npm run build
npm startData Sources
PubMed — clinical trial references with PMIDs
NSF International — third-party certification data
USP (United States Pharmacopeia) — quality standards
Full comparison pages and product rankings: verifiedsupplementdata.com
How It Works
The server loads structured evidence data (clinical doses, form comparisons, medication-nutrient interactions) and exposes it through MCP tools. When an AI assistant receives a supplement question, it calls the appropriate tool and gets back formatted, citation-backed recommendations.
Product rankings are based on cost-per-effective-daily-dose, third-party certification status, and clinical evidence — not sponsorship.
License
MIT
Available Tools
5 toolscheck_interactionsA
Check if medications deplete nutrients, creating supplement needs. Returns depleted nutrients, mechanisms, severity, and recommended supplements.
Inputs: medication (required).
classify_formA
Check if a supplement product uses a good or bad form. Paste any product name or ingredient list and get a quality verdict. Example: 'Nature Made Magnesium Oxide 250mg' → verdict: poor, absorption: ~4%, better alternative: glycinate.
Inputs: category (required), product_text (required).
compare_formsA
Compare different forms of a supplement (e.g., magnesium glycinate vs citrate vs oxide). Shows absorption, best uses, warnings, and which form to buy.
Inputs: supplement (required).
get_dosageA
Get evidence-based dosage recommendations for a supplement, with clinical trial doses by condition, timing, and safety considerations.
Inputs: supplement (required), condition.
recommend_supplementA
Get evidence-based supplement recommendations for a specific condition. Returns ranked products with clinical evidence, dosing, cost-per-dose, and purchase links.
Inputs: supplement (required), condition.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.2/5.0
Scored across 5 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: recommending supplements for conditions, comparing forms, checking medication-induced depletions, providing dosage info, and classifying product forms. No two tools overlap in function.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern (recommend_supplement, compare_forms, check_interactions, get_dosage, classify_form). The verbs are descriptive and the pattern is uniform.
Tool Count5/5
Five tools is well-scoped for the domain, covering the key advisory workflows without bloat. Each tool addresses a distinct user need, making the set concise yet functional.
Completeness4/5
The tool set covers core workflows: condition-based recommendations, form comparisons, medication depletions, dosing, and product quality checks. A minor gap is lack of a tool for supplement-supplement interaction checking, but this is not a critical omission for the intended scope.
Related MCP Connectors
MCP server exposing supplements database used by iNutriPlan.com
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.
Cited supplement evidence, biomarker effects, interaction checks and brand quality
Related MCP Servers
citedhealth-mcpofficial
AlicenseNot gradedqualityDmaintenanceMCP server for CITED Health that allows AI assistants to query evidence-based supplement data, including ingredient evidence grades, health conditions, PubMed papers, glossary terms, and educational guides.MIT- FlicenseBqualityDmaintenanceAn MCP server that provides AI-assisted clinical decision support for medication safety, integrating trusted biomedical sources to detect drug interactions and suggest therapeutic alternatives.51-
- AlicenseAqualityCmaintenanceAn MCP server for longevity and metabolic medicine that provides a medication catalog, dosing protocols, contraindication screening, drug interaction checks, lab recommendations, and patient intake pathways across 35 compounds.971 npmMIT