Skip to main content
Glama
MedData MCP Server

MedData MCP Server

by anthesiallc

MedData MCP Server

mcp-name: io.github.anthesiallc/meddata

A Model Context Protocol server that exposes the MedData API as tools, so any MCP client (Claude Desktop, Cursor, ChatGPT connectors, or an agent framework) can look up drug and supplement data and check interactions conversationally.

It's a thin wrapper: each tool maps to one MedData REST endpoint. All the data work happens in the API.

Tools

Tool

What it does

search_drugs

Search drugs by brand or generic name; returns RxCUI + details

get_drug

Full drug profile by RxCUI

get_drug_by_ndc

Drug profile by NDC package code

search_supplements

Search supplements by name; returns supplement IDs

get_supplement

Full supplement fact sheet by ID

check_interactions

Interactions across a mixed list of 2-10 drugs/supplements

assess_routine

Full assessment of a routine: per-pair coverage, sources, timing and food conditions

get_usage

Current billing period usage and plan limit

check_interactions vs assess_routine

check_interactions returns a flat list of interactions. assess_routine returns the reasoning: what each submitted name resolved to, what was consulted for every pair, and the document behind each finding. Reach for it when the answer will be explained or acted on rather than just displayed.

The distinction that matters most is in pairs_checked[].status:

status

means

finding

one or more grounded findings, listed in findings[]

no_finding_in_sources

a source covering this kind of pair was consulted and had nothing. Absence of a finding is not evidence of safety

not_covered

no source covers this kind of pair, so it was not assessed. Most supplement-supplement pairs land here

unresolved

an item did not resolve, so nothing could be checked

not_covered and no_finding_in_sources are different answers, and a flat empty list cannot tell them apart.

assess_routine also takes class_matching (default off). With it on, a drug matches the therapeutic classes a supplement record names, not only the drug names it lists; those findings carry basis.level: "class" and name the class, so an inferred match stays distinguishable from an explicit one. Findings also carry basis.level (formulation / ingredient / class) saying how closely the source matches what was submitted, three-state timing and food conditions where silence is not_documented rather than "no effect", and references[] with the document version and the verbatim passage.

Related MCP server: mcp-openfda

Get an API key

Free tier is 250 calls/month, no credit card:

curl -X POST https://meddata.anthesia.io/api/v1/signup \
  -H 'Content-Type: application/json' \
  -d '{"email":"you@example.com"}'

The key comes back in the api_key field of the response.

Install and run

The easiest way is with uv (no manual venv needed):

# stdio transport (default — for Claude Desktop, Cursor, most local clients)
MEDDATA_API_KEY=md_your_key uvx meddata-mcp

# streamable-HTTP transport (for remote / web clients)
MEDDATA_API_KEY=md_your_key uvx meddata-mcp --http

Or install with pip into its own environment:

pip install meddata-mcp
MEDDATA_API_KEY=md_your_key meddata-mcp

Note: install into a dedicated environment. The mcp SDK requires a newer starlette than the MedData API app pins, so the two will conflict if installed together.

Environment variables:

  • MEDDATA_API_KEY (required) — your MedData API key.

  • MEDDATA_BASE_URL (optional) — defaults to https://meddata.anthesia.io.

  • MEDDATA_TIMEOUT (optional) — request timeout in seconds, default 30.

Client configuration

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "meddata": {
      "command": "uvx",
      "args": ["meddata-mcp"],
      "env": { "MEDDATA_API_KEY": "md_your_key" }
    }
  }
}

Cursor

Add the same block to ~/.cursor/mcp.json (or the project .cursor/mcp.json).

Smithery (hosted, no install)

The server is hosted on Smithery, so MCP clients that support Smithery can connect without installing anything. You provide your MedData API key in the Smithery config and it routes to the server.

LangChain / LangGraph

Any LangChain or LangGraph agent can use these tools through langchain-mcp-adapters:

# pip install langchain-mcp-adapters langgraph "langchain[anthropic]"
from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient(
    {
        "meddata": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["meddata-mcp"],
            "env": {"MEDDATA_API_KEY": "md_your_key"},
        }
    }
)
tools = await client.get_tools()
# hand `tools` to a LangGraph/LangChain agent, e.g.
# from langgraph.prebuilt import create_react_agent
# agent = create_react_agent("anthropic:claude-opus-4-8", tools)

LlamaIndex works the same way via its MCP tool spec.

Develop from source

git clone https://github.com/anthesiallc/meddata-mcp && cd meddata-mcp
python -m venv .venv
.venv/Scripts/python -m pip install -e ".[http]"   # Windows; [http] adds uvicorn for --http
# .venv/bin/pip install -e ".[http]"                # macOS/Linux
MEDDATA_API_KEY=md_your_key .venv/Scripts/python -m meddata_mcp.server

Notes

  • Data is for informational purposes only and is not medical advice.

  • Interaction data comes from established medical databases; an empty result means none were found in those sources, not that a combination is proven safe.

Available Tools

7 tools
check_interactionsA

Check interactions across a mixed list of drugs and supplements.

Accepts 2-10 items (drug names, supplement names, or both) and returns known interactions among them. Interaction data comes from established medical databases; it is never generated or inferred, so an empty result means none were found in those sources, not that the combination is proven safe.

Args: items: 2-10 drug and/or supplement names, e.g. ["warfarin", "aspirin", "Fish Oil"].

Inputs: items (required). Returns: object

get_drugA

Get the full profile for a drug by its RxCUI.

Returns names, dosage forms, NDC codes, label sections, and related data. Get the RxCUI from search_drugs first if you only have a name.

Args: rxcui: RxNorm Concept Unique Identifier, e.g. "1191" for aspirin.

Inputs: rxcui (required). Returns: object

get_drug_by_ndcA

Get a drug profile by its NDC (National Drug Code) package code.

Use when you have an NDC from a label or packaging rather than a name.

Args: ndc_code: NDC code, e.g. "0363-0160".

Inputs: ndc_code (required). Returns: object

get_supplementA

Get the full fact sheet for a supplement by its ID.

Returns ingredients, recommended intake, and NIH reference data. Get the ID from search_supplements first.

Args: supplement_id: Numeric supplement ID from search_supplements.

Inputs: supplement_id (required). Returns: object

get_usageB

Show this API key's current billing period usage and plan limits.

Inputs: no named parameters. Returns: object

search_drugsA

Search for drugs by brand or generic name.

Returns matching drugs with their RxCUI (the identifier you pass to get_drug), generic and brand names, and dosage form/strength when known. Use this first when you have a drug name but need its details or RxCUI.

Args: name: Brand or generic drug name, e.g. "aspirin" or "Lipitor". limit: Max results to return (1-50).

Inputs: name (required), limit. Returns: object

search_supplementsA

Search for dietary supplements by name.

Returns matching supplements with their IDs (pass to get_supplement) and summary info. Use first when you have a supplement name like "Vitamin D" or "Fish Oil".

Args: name: Supplement name, e.g. "Vitamin D" or "magnesium". limit: Max results to return (1-50).

Inputs: name (required), limit. Returns: object

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 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: check_interactions for interactions, get_drug and get_drug_by_ndc for drug profiles by different identifiers, get_supplement for supplement profiles, search tools for lookup, and get_usage for billing. No overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case (e.g., search_drugs, get_drug_by_ndc, check_interactions). The naming style is uniform and predictable.

    Tool Count5/5

    With 7 tools, the server is well-scoped for its purpose of drug and supplement information retrieval and interaction checking. Each tool earns its place without overcomplicating the surface.

    Completeness4/5

    The tool set covers search and retrieval for both drugs and supplements, plus interaction checking. A minor gap is the lack of a direct way to check interactions involving a single drug or supplement against a broader set, but the core workflows are supported.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers