MCP Ratchet Clinical Charting
M

MCP Ratchet Clinical Charting

The MCP server is used for clinical charting, helping home health nurses directly record patient visit information into the electronic medical record system, reducing administrative burden. Currently in simulation mode for development and testing.
2 points
5.6K

What is the Ratchet Clinical Record Assistant?

Ratchet is an AI assistant designed specifically for home health nurses. It can help nurses directly enter patient visit records into the electronic medical record system (EMR). It runs on the Claude AI platform and can search for patient information, create visit records, view patient history, etc., greatly reducing the nurses' paperwork time.

How to use the Ratchet Clinical Record Assistant?

Ratchet runs as an MCP server and needs to be used in conjunction with Claude Desktop. After installation and configuration, nurses can directly search for patients and record visit information in the Claude conversation, and the system will automatically handle the data entry work.

Applicable scenarios

Ratchet is particularly suitable for home health care scenarios. When nurses need to record patients' vital signs, visit conditions, nursing measures and other information after a home visit, they can directly input through voice or text, and Ratchet will automatically organize and enter the information into the system.

Main functions

Patient search
Quickly find patient information, including basic information, diagnosis status, and contact information, by name, ID, or phone number.
Visit record creation
Record patients' vital signs (blood pressure, heart rate, body temperature, etc.), nursing measures, and observation results during a visit.
Patient history view
View patients' historical visit records to understand the progress and trend changes of nursing care.
Simulation mode
Use simulated data during the development and testing phase to experience the full functionality without connecting to a real EMR system.
Claude integration
Seamlessly integrate into Claude Desktop and complete all operations through natural language interaction.
Advantages
Significantly reduce the nurses' paperwork time and improve work efficiency.
Simple and intuitive to use through natural language interaction.
The simulation mode is convenient for testing and training without a real system.
Support offline development and testing, reducing the implementation threshold.
Seamlessly integrate with the existing workflow.
Limitations
Currently in simulation mode, waiting for integration with a real EMR system.
Requires the Claude Desktop environment support.
Depends on network connection (in the production environment).
Requires API key configuration (in the production environment).
Currently, the supported patient data fields are limited.

How to use

Install Ratchet
Quickly install the Ratchet MCP server via npm.
Configure Claude Desktop
Add Ratchet server settings to the Claude Desktop configuration file.
Restart Claude Desktop
Restart the Claude Desktop application to load the Ratchet server.
Start using
Directly use Ratchet's functions in the Claude conversation.

Usage examples

Quickly find patient information
After a home visit, a nurse needs to record information but can't remember the patient's full ID.
Record visit vital signs
A nurse has measured the patient's vital signs and needs to enter them into the system.
View nursing progress
A nurse needs to understand the recent changes in a patient's nursing situation.

Frequently Asked Questions

Does Ratchet need to connect to a real electronic medical record system?
How to switch from simulation mode to production mode?
Which electronic medical record systems does Ratchet support?
How is data security ensured?
Do I need programming knowledge to use it?
Which languages are supported?

Related resources

GitHub repository
Ratchet's source code and the latest version
GRIMLOCK project
The MCP server factory for creating Ratchet
Demonstration EMR application
A demonstration electronic medical record application for testing
Claude Desktop
The desktop application required to run Ratchet

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "ratchet": {
      "command": "npx",
      "args": ["-y", "mcp-ratchet-clinical-charting"]
    }
  }
}

{
  "mcpServers": {
    "ratchet": {
      "command": "npx",
      "args": ["-y", "mcp-ratchet-clinical-charting"],
      "env": {
        "POINTCARE_API_URL": "https://api.pointcare.com",
        "POINTCARE_API_KEY": "your-api-key"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.6K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
10.9K
5 points
P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
10.4K
5 points
B
Blueprint MCP
Blueprint MCP is a chart generation tool based on the Arcade ecosystem. It uses technologies such as Nano Banana Pro to automatically generate visual charts such as architecture diagrams and flowcharts by analyzing codebases and system architectures, helping developers understand complex systems.
Python
10.7K
4 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
21.0K
5 points
D
Devtools Debugger MCP
The Node.js Debugger MCP server provides complete debugging capabilities based on the Chrome DevTools protocol, including breakpoint setting, stepping execution, variable inspection, and expression evaluation.
TypeScript
9.2K
4 points
M
Mcpjungle
MCPJungle is a self-hosted MCP gateway used to centrally manage and proxy multiple MCP servers, providing a unified tool access interface for AI agents.
Go
0
4.5 points
N
Nexus
Nexus is an AI tool aggregation gateway that supports connecting multiple MCP servers and LLM providers, providing tool search, execution, and model routing functions through a unified endpoint, and supporting security authentication and rate limiting.
Rust
0
4 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.6K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.6K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.5K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.7K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
63.8K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.5K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase