Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Iomed-commits/elthio-mcp

REMOTE · ELTHIO-PRODUCTION.UP.RAILWAY.APP

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

0 this week 76 Trust /100

Last scanned (19 hours ago)

Scores higher than 66% of remote servers

Unreachable for 1 day in a row. Last reached 3 Nov 2026.

Category Health and Science

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security11
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
  • Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 5 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • HSTS header: fail → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • TLS certificate: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
  • 2 Nov 26 0
    • Schema quality: pass → fail ▼ functional
    • New tool “verify_supplement_recommendation” functional
  • 30 Sept 26 0
    • Stability: 0.97 → pass security
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 1 Sept 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 31 Aug 26 0

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Probed https://elthio-production.up.railway.app/mcp

TLS unreached
DNSSEC insecure

Validation of elthio-production.up.railway.app. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
railway.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://elthio-production.up.railway.app/mcp Unreachable
http (plaintext) http://elthio-production.up.railway.app/mcp HTTPS enforced
MCP tools · 6 exposed · ~748 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_full_stack ~134

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.

NameTypeReqDescription
bedtimestring–Bedtime HH:MM
breakfast_timestring–Breakfast time HH:MM
dinner_timestring–Dinner time HH:MM
medicationsarray–All prescription medications.
supplementsarrayyesAll supplements and vitamins.
wake_timestring–Wake time in HH:MM format. e.g. '07:00'

No output schema declared.

No examples provided.

check_supplement_safety ~152

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.

NameTypeReqDescription
medicationsarray–List of user's prescription medications. e.g. ['Warfarin', 'Levothyroxine']
supplementstringyesThe supplement to check. Include brand and form for best results. e.g. 'Magnesium Bisglycinate 400mg' or 'Fish Oil 1000mg'
supplementsarray–User's existing supplements for interaction checking.

No output schema declared.

No examples provided.

get_supplement_timing ~95

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.

NameTypeReqDescription
medicationsarray–User's medications — affects timing recommendations.
supplementstringyesSupplement name. e.g. 'Magnesium Glycinate'

No output schema declared.

No examples provided.

grade_supplement_quality ~114

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.

NameTypeReqDescription
other_ingredientsstring–Other ingredients text from the label for filler detection. Optional.
supplementstringyesSupplement name to grade. e.g. 'Magnesium Oxide' or 'NOW Foods Vitamin D3 5000IU'

No output schema declared.

No examples provided.

verify_nih_label ~73

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.

NameTypeReqDescription
supplementstringyesSupplement name to verify against NIH DSLD.

No output schema declared.

No examples provided.

verify_supplement_recommendation ~180

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.

NameTypeReqDescription
contextstring–Optional — why the user wants this supplement (stored for audit only).
medicationsarray–User's prescription medications.
supplementstringyesSupplement the agent wants to recommend. e.g. 'Omega-3 Fish Oil 1000mg'
supplements_already_takingarray–Supplements the user already takes (excluding the one being recommended).

No output schema declared.

No examples provided.

Install

How do I install the io.github.Iomed-commits/elthio-mcp server?

io.github.Iomed-commits/elthio-mcp is a hosted endpoint at https://elthio-production.up.railway.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · elthio-production.up.railway.app

# add to Claude Code
claude mcp add --transport http iomed-commits-elthio-mcp 'https://elthio-production.up.railway.app/mcp'
Common questions

What is the io.github.Iomed-commits/elthio-mcp server?

io.github.Iomed-commits/elthio-mcp is listed in the public MCP registry as io.github.Iomed-commits/elthio-mcp. Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D. This page covers its hosted endpoint (https://elthio-production.up.railway.app/mcp).

Is the io.github.Iomed-commits/elthio-mcp server safe to use?

io.github.Iomed-commits/elthio-mcp scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.Iomed-commits/elthio-mcp server expose?

io.github.Iomed-commits/elthio-mcp exposes 6 tools: check_supplement_safety, grade_supplement_quality, get_supplement_timing, check_full_stack, verify_supplement_recommendation, verify_nih_label. Their descriptions and schemas cost roughly 748 tokens of context every time the server is loaded.

Does the io.github.Iomed-commits/elthio-mcp server require authentication?

Its publisher declares no required credentials for io.github.Iomed-commits/elthio-mcp. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

Is the io.github.Iomed-commits/elthio-mcp server still maintained?

io.github.Iomed-commits/elthio-mcp is still listed in the MCP registry, though our most recent checks did not reach this channel. We last reached this channel on 3 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.