deploying-openmed-mcp

Expose clinical NLP tools via MCP server over stdio or HTTP.

5.0k|615|Updated Oct 4, 2025

Search Tags:#mcp #agent integration #de-identification #on-device ai #streamable http #clinical nlp #pii extraction

Ready to run

npx skills add https://github.com/maziyarpanahi/openmed --skill deploying-openmed-mcp

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deploying-openmed-mcp
Source: https://github.com/maziyarpanahi/openmed/tree/main/skills/deploying-openmed-mcp
Command: npx skills add https://github.com/maziyarpanahi/openmed --skill deploying-openmed-mcp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables coding agents and chat clients to access OpenMed's clinical NLP capabilities without sending sensitive clinical data to external cloud services.

Core Features & Use Cases

MCP Server Deployment: Run OpenMed over stdio or Streamable HTTP for local agents or shared team endpoints.
Clinical NLP Tools: Expose clinical NER, PII extraction, de-identification, model discovery, and model lifecycle management through seven MCP tools.
Agent Integration: Configure Claude Code, Codex, or compatible MCP clients with local or networked OpenMed access.
Production Operations: Configure model preloading, memory limits, keep-alive behavior, container deployment, and HTTP security boundaries.

Quick Start

Configure your MCP client to launch OpenMed with the stdio transport, then use its de-identification and clinical analysis tools on synthetic or locally controlled clinical text.

Frequently Asked Questions about deploying-openmed-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run clinical NLP tools locally without sending patient data to the cloud?▼

On-device clinical NLP execution is achieved by deploying an MCP server that exposes clinical NER, PII extraction, and de-identification tools directly to coding agents over stdio. This ensures sensitive clinical text remains locally controlled without external cloud dependencies.

How do I configure Claude Code or compatible chat clients to use a local clinical NLP server?▼

Agent integration for clinical NLP requires configuring compatible MCP clients to launch the server via local stdio transport. This setup exposes seven clinical NLP tools, enabling coding agents to execute de-identification and NER tasks directly.

Can I deploy a shared clinical NLP MCP server for my team over HTTP?▼

Shared team endpoints for clinical NLP are supported by deploying the MCP server using Streamable HTTP transport. This configuration requires appropriate authentication, TLS controls, and HTTP security boundaries to regulate network access.

What is de-identification and PII extraction in the context of clinical NLP agents?▼

De-identification and PII extraction are clinical NLP processes that identify and remove protected health information from clinical text. Exposing these capabilities as MCP tools allows agents to produce de-identified synthetic text locally.

Do I need to configure model lifecycle management for on-device clinical NLP?▼

Model lifecycle management, including model discovery, preloading, memory limits, and keep-alive behavior, is configurable for production operations. These settings optimize the performance of on-device clinical NLP deployments within containerized environments.

What are the limitations of using stdio vs Streamable HTTP for MCP agent integration?▼

Local stdio execution limits MCP agent integration to individual use, whereas Streamable HTTP supports shared networked deployments. Both transports provide identical clinical NLP tools but require distinct security and ServiceRuntime environment configurations.