Patient Search & Create Tasks MCP Server
About
MCP server for searching patients and creating tasks in Flight Health Atlas system.
Details
- Author
- Flight-Health
- Downloads
- 196
- Categories
- Search
Jump to
- Uses Puppeteer for advanced web automation and reliable login handling
- Provides search_patient_v2 tool with optional detailed results
- Provides create_new_task tool with task type, name, and description
- Includes hello_world tool to test MCP connection
- Logs debug information to stderr for troubleshooting
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Patient Search & Create Tasks MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Node.js 18+, clone the repository, run npm install, update credentials in auth.ts, build the V2 server with npm run build:v2, and start it with npm start. Then configure the server in your MCP client (e.g., Cursor's mcp.json) pointing to dist/server-v2.js. Invoke tools like search_patient_v2 and create_new_task via MCP calls.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"patient search & create tasks mcp server": {
"patient-search-v2": {
"command": "node",
"args": [
"/path/to/mcp-search-and-create-task/dist/server-v2.js"
]
}
}
}
}
McpServers
{
"patient-search-v2": {
"command": "node",
"args": [
"/path/to/mcp-search-and-create-task/dist/server-v2.js"
]
}
}
Patient Search & Create Tasks MCP Server
This project provides a Model Context Protocol (MCP) server for searching patients in the Flight Health Atlas system and creating a new task.
Features
- V2 Server (server-v2.ts): Uses Puppeteer for advanced web automation and more reliable login handling
Prerequisites
- Node.js 18 or higher
- npm or yarn package manager
Installation
1. Clone the repository:
git clone <repository-url>
cd patient-search-mcp
2. Install dependencies:
npm install
3. Update Credentials
Go to auth.ts and replace the email and password in LOGIN_CREDENTIALS with your credentials.
For demo purposes these are hardcoded since by default Cursor AI cannot access a .env file (possible to work around this by creating a .cursorignore file and adding !.env to it).
4. Build the servers:
npm build:v2 # only build the V2 server
npm run start # Build and start V2 server
Configuration
For Cursor MCP
Add the following to your Cursor mcp.json file (found through Cursor Settings):
V2 Server (Recommended):
{
"mcpServers": {
"patient-search-v2": {
"command": "node",
"args": ["/path/to/mcp-search-and-create-task/dist/server-v2.js"]
}
}
}
Usage
Available Tools
Both servers provide the following tools:
hello_world
- Description: Test MCP connection
- Parameters:
- name (optional): Name to greet
search_patient_v2 (V2 Server)
- Description: Search for patients using Puppeteer web automation
- Parameters:
- patient_name (required): Name of the patient to search for
- detailed (optional): Whether to return detailed information
create_new_task (V2 Server)
- Description: Create a new task
- Parameters:
- task_type (required): Type of the task to create
- task_name (required): Name of the task to create
- description (optional): Any description you want to add to the task
Example Usage
// Test connection
await callTool("hello_world", { name: "Aakarsh" });
// Search for a patient (V2 server)
await callTool("search_patient_v2", {
patient_name: "John Smith",
detailed: true
});
Development
Running in Development Mode
npm run dev
Starting the Server
bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.

