elthio-mcp

Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
100%
Naming quality
93%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'verify_supplement_recommendation' name length outside 3-30 rangein verify_supplement_recommendation

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~990Tokens (tool definitions)
~1.1 KBTypical response size
Moderate attention impact (0.77% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "elthio-mcp": {
      "url": "https://elthio-production.up.railway.app/mcp"
    }
  }
}

Remote endpoints

https://elthio-production.up.railway.app/mcpstreamable-http

What it can do

Tool inventory

Tools (6)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢check_supplement_safety(supplement, medications, supplements)

Check if a supplement is safe with a user's medications and existing supplements. Returns interaction data, safety score, quality grade, filler detection, NIH verification, and timing recommendation. Use this whenever a user asks about supplement safety, drug interactions, or whether they can take a supplement with their medications.

Input Schema

{
  "type": "object",
  "properties": {
    "supplement": {
      "type": "string",
      "description": "The supplement to check. Include brand and form for best results. e.g. 'Magnesium Bisglycinate 400mg' or 'Fish Oil 1000mg'"
    },
    "medications": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "List of user's prescription medications. e.g. ['Warfarin', 'Levothyroxine']"
    },
    "supplements": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "User's existing supplements for interaction checking."
    }
  },
  "required": [
    "supplement"
  ]
}
🟢grade_supplement_quality(supplement, other_ingredients)

Get the quality grade (A-D) for a supplement based on bioavailability, filler detection, and NIH verification. Use this when a user asks about supplement quality, which form is best, whether a supplement has concerning fillers, or wants to compare brands.

Input Schema

{
  "type": "object",
  "properties": {
    "supplement": {
      "type": "string",
      "description": "Supplement name to grade. e.g. 'Magnesium Oxide' or 'NOW Foods Vitamin D3 5000IU'"
    },
    "other_ingredients": {
      "type": "string",
      "description": "Other ingredients text from the label for filler detection. Optional."
    }
  },
  "required": [
    "supplement"
  ]
}
🟢get_supplement_timing(supplement, medications)

Get the optimal time to take a supplement and why. Returns slot (morning/bedtime/with food/etc), clinical reasoning, and personalized instruction. Use this when a user asks when to take a supplement or how to build a timing schedule.

Input Schema

{
  "type": "object",
  "properties": {
    "supplement": {
      "type": "string",
      "description": "Supplement name. e.g. 'Magnesium Glycinate'"
    },
    "medications": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "User's medications — affects timing recommendations."
    }
  },
  "required": [
    "supplement"
  ]
}
🟢check_full_stack(medications, supplements, wake_time, breakfast_time, dinner_time, ...)

Check a complete supplement and medication stack for all interactions, conflicts, synergies, and generate a full daily timing schedule. Use this when a user wants to check their entire supplement regimen or build a complete daily schedule.

Input Schema

{
  "type": "object",
  "properties": {
    "medications": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "All prescription medications."
    },
    "supplements": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "All supplements and vitamins."
    },
    "wake_time": {
      "type": "string",
      "description": "Wake time in HH:MM format. e.g. '07:00'"
    },
    "breakfast_time": {
      "type": "string",
      "description": "Breakfast time HH:MM"
    },
    "dinner_time": {
      "type": "string",
      "description": "Dinner time HH:MM"
    },
    "bedtime": {
      "type": "string",
      "description": "Bedtime HH:MM"
    }
  },
  "required": [
    "supplements"
  ]
}
🟢verify_supplement_recommendation(supplement, medications, supplements_already_taking, context)

Verify whether a supplement is safe to recommend to a user given their medications and current supplements. Runs the same interaction check as /med-check plus pathway analysis on the full stack including the new supplement. Returns safe_to_recommend, agent_summary, confidence, severity, timing_recommendation, citation, full_interactions, and pathway_analysis. Use whenever an AI agent is about to suggest a supplement and needs a go/no-go safety verdict.

Input Schema

{
  "type": "object",
  "properties": {
    "supplement": {
      "type": "string",
      "description": "Supplement the agent wants to recommend. e.g. 'Omega-3 Fish Oil 1000mg'"
    },
    "medications": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "User's prescription medications."
    },
    "supplements_already_taking": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Supplements the user already takes (excluding the one being recommended)."
    },
    "context": {
      "type": "string",
      "description": "Optional — why the user wants this supplement (stored for audit only)."
    }
  },
  "required": [
    "supplement"
  ]
}
⚪verify_nih_label(supplement)

Verify if a supplement matches a record in the NIH Dietary Supplement Label Database (DSLD). Returns verification status, DSLD ID, and confidence level. Use this when a user asks if a supplement is legitimate or wants to verify label accuracy.

Input Schema

{
  "type": "object",
  "properties": {
    "supplement": {
      "type": "string",
      "description": "Supplement name to verify against NIH DSLD."
    }
  },
  "required": [
    "supplement"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded6 tools
verifiedversion not recorded5 tools
verifiedversion not recorded5 tools
verifiedversion not recorded5 tools
verifiedversion not recorded5 tools
verifiedversion not recorded5 tools
verifiedversion not recorded5 tools