Mymedi AI MCP Server logo

Mymedi AI MCP Server

by MyMedi-AI

Medical coding, DME billing, prior authorization, claims, drug, provider, and clinical data tools over MCP.

Install Mymedi AI MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mymedi-ai-mymedi-ai-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@mymedi-ai/mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

MyMedi-AI/mymedi-ai-mcp-server connects MCP clients to medical coding, DME billing, claims, drug, provider, and public-health data tools. It supports local stdio execution through npx and a streamable HTTP endpoint, with six free tools available without an API key and additional tools using credits. Reach for it when an agent needs code lookup or validation, Medicare reimbursement data, prior-authorization checks, claims preparation, or healthcare reference data without sending patient identifiers.

Use cases

  • Validate HCPCS and ICD-10 codes before claim submission
  • Check DMEPOS prior-authorization and F2F/WOPD requirements
  • Compare Medicare reimbursement and state fee schedules
  • Extract medical codes from de-identified clinical text
  • Research providers, drugs, trials, and healthcare markets

Key features

  • ICD-10, CPT, and HCPCS lookup, suggestion, validation, and cross-reference
  • DMEPOS fee schedules with rental, purchase, rural, and state rates
  • Prior-authorization, claims, denial, modifier, and order-readiness tools
  • Drug, provider, clinical-trial, surveillance, and market data access
  • PHI-focused pattern scanning and de-identified text extraction
  • Free starter tools with credit-based paid operations

Tools32

What Mymedi AI MCP Server lets your agent do. Expand a tool for its parameters.

Verified live~5.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

20/24 checks healthy over the last 85d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @mymedi-ai/mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads797Package downloads in the last 30 days.
Last commit7d agoMost recent push to the default branch.
Tools exposed32Callable tools this server registers over MCP.
Directory activity7 viewsConfig copies, upvotes, and views on AllMCPs.

How Mymedi AI MCP Server works

What MyMedi-AI/mymedi-ai-mcp-server does

MyMedi-AI/mymedi-ai-mcp-server exposes healthcare billing and medical-data operations through MCP. Its coding coverage includes ICD-10-CM, CPT, and HCPCS records, with DMEPOS fee schedules, Medicare reimbursement values, code relationships, suggestions, and validation. Billing workflows cover prior-authorization requirements, face-to-face and written-order requirements, modifier guidance, denial-code explanations, claims checks, and supplier exposure reports.

The server also provides drug, provider, clinical-trial, disease-surveillance, and market data tools. Sources include CMS, OpenFDA, NIH RxNorm, ClinicalTrials.gov, NPPES, CMS Open Payments, CDC surveillance data, and the CodeReference database. Several tools add clearly labeled analysis or estimates to source data.

How it works

Run the package with Node.js 20 or later using npx -y @mymedi-ai/mcp-server. MCP clients can connect through stdio. The hosted streamable HTTP endpoint is https://mymedi-ai.com/mcp-stream; Claude authenticates through its custom connector flow rather than requiring a copied API key.

Without credentials, six tools are available: prior-authorization list checks, denial-code explanations, basic code metadata, basic reimbursement, order-readiness checklists, and modifier guidance. These free tools are rate-limited to 60 requests per hour per IP. Other operations use an API key or connector sign-in and consume credits. Batch code operations charge per code and impose limits of 25 codes, while exposure reports allow up to 100 HCPCS codes.

Setup and configuration

Install the package in an MCP client configuration and optionally set MCP_API_KEY. A key can be obtained by sending a registration request to the MyMedi-AI marketplace endpoint. MYMEDI_API_KEY is also accepted, but MCP_API_KEY takes precedence when both are set. New keys include starter credits, and the buy_credits tool returns a Stripe checkout link for adding more.

Claude Desktop, Cursor, VS Code, and Claude Code configurations use the package's npx command. Claude web users can add the hosted endpoint as a custom connector and complete the MyMedi-AI sign-in flow. A free demonstration endpoint provides basic code metadata and is limited to 60 requests per hour per IP.

Tools and capabilities

  • Look up, suggest, validate, batch-process, and cross-reference ICD-10, CPT, and HCPCS codes.
  • Retrieve national professional-service reimbursement, DMEPOS rental and purchase ranges, or state-specific fee schedule values.
  • Check prior-authorization, F2F/WOPD, SWO, modifier, denial, and documentation requirements.
  • Predict prior-authorization outcomes only when a qualifying historical cohort exists; otherwise return verifiable CMS facts without fabricating a probability.
  • Validate claims before submission and generate supplier-level exposure reports.
  • Extract codes and dates from de-identified text, or scan text for common SSN, MRN, and birth-date patterns.
  • Query drug, provider, payment, clinical-trial, surveillance, and healthcare-market datasets.

Limitations and notes

The tools are designed for codes, modifiers, dates of service, facts, and de-identified text rather than patient identifiers. The compliance tool is a pattern-based scan, not a complete HIPAA audit, and the drug-interaction results represent statistical FAERS co-reporting signals rather than proof of interactions. Prior-authorization tools are scoped to Original Medicare fee-for-service; pa_status tracks requests entered in the MyMedi-AI workspace and does not query payers. Editorial modifier guidance is not payer policy, and claims validation does not determine medical necessity or prior authorization.

Paid calls consume credits. compliance_audit costs 250 credits and is intended for samples rather than every record. Calls for empty code-suggestion results, missing prior-authorization cohorts, and certain all-miss batch lookups are refunded according to the tool behavior.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Mymedi AI MCP Server

MyMedi-AI/mymedi-ai-mcp-server is an MCP server that connects AI clients to medical coding, DME billing, Medicare reimbursement, prior-authorization, claims, drug, provider, and clinical data tools. Its main tools look up and validate codes, check billing requirements, inspect fee schedules, validate claims, and search healthcare datasets.

Install it with `npx -y @mymedi-ai/mcp-server` in your MCP client's stdio configuration. Node.js 20 or later is required. Set `MCP_API_KEY` to enable paid tools; omitting it still enables six free tools, subject to rate limits.

Yes. The package includes stdio configuration examples for Claude Desktop, Cursor, and VS Code, and a command for Claude Code. Claude web users can also connect through the hosted streamable HTTP endpoint as a custom connector.

It is designed for PHI-free use: send codes, modifiers, dates, documentation facts, and de-identified text rather than patient identifiers. Its compliance audit checks common identifier patterns, but it is not a complete HIPAA audit.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMymedi AI MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mymedi-ai-mymedi-ai-mcp-server?style=directory)](https://allmcps.com/mcp/mymedi-ai-mymedi-ai-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/mymedi-ai-mymedi-ai-mcp-server"><img src="https://allmcps.com/api/badge/mymedi-ai-mymedi-ai-mcp-server?style=directory" alt="Mymedi AI MCP Server on AllMCPs" /></a>