mcp-progress
MCP server providing notifications and progress tracking for long-running operations.
README
MCP Progress Server
An MCP (Model Context Protocol) server that provides notifications and progress tracking for long-running operations.
Features
- Notifications: Display system notifications using node-notifier
- Progress Tracking: Track progress of long-running operations with MCP-compatible progress notifications
Installation
For use with npx (recommended)
npx mcp-progress
For global installation
npm install -g mcp-progress
For local development
git clone git@github.com:jaume-ferrarons/mcp-progress.git
cd mcp-progress
npm install
Usage
Run the server:
npm start
Or use it as an MCP server in your MCP client configuration.
Tools
notify
Display a notification to the user.
Parameters:
title(string, required): Notification titlemessage(string, required): Notification messagesound(boolean, optional): Play notification sound (default: false)
Note: Notifications stay visible until dismissed by the user.
Example:
{
"title": "Task Complete",
"message": "Your operation finished successfully",
"sound": true
}
start_progress
Start tracking progress for a long-running operation. Creates a sticky notification that updates as progress changes.
Parameters:
progressToken(string, required): Unique identifier for this progress operationtitle(string, required): Title of the operationtotal(number, optional): Total number of steps
Example:
{
"progressToken": "file-processing-1",
"title": "Processing files",
"total": 100
}
update_progress
Update progress for an ongoing operation. Updates the sticky notification with current progress.
Parameters:
progressToken(string, required): Progress operation identifiercurrent(number, required): Current progress valuetotal(number, optional): Total progress value (updates total if provided)message(string, optional): Progress message
Example:
{
"progressToken": "file-processing-1",
"current": 45,
"message": "Processing file 45 of 100"
}
complete_progress
Mark a progress operation as complete. Updates the notification with completion status and plays a sound.
Parameters:
progressToken(string, required): Progress operation identifiermessage(string, optional): Completion message
Example:
{
"progressToken": "file-processing-1",
"message": "All files processed successfully"
}
Example Workflow
// Start progress tracking
await callTool('start_progress', {
progressToken: 'data-sync-1',
title: 'Syncing data',
total: 50
});
// Update progress periodically
for (let i = 1; i <= 50; i++) {
await callTool('update_progress', {
progressToken: 'data-sync-1',
current: i,
message: `Processing item ${i}`
});
}
// Complete the operation
await callTool('complete_progress', {
progressToken: 'data-sync-1',
message: 'Sync completed'
});
// Send a notification
await callTool('notify', {
title: 'Sync Complete',
message: 'Data synchronization finished successfully',
sound: true
});
MCP Configuration
Add to your MCP client configuration:
{
"mcpServers": {
"progress": {
"command": "npx",
"args": ["-y", "mcp-progress"]
}
}
}
Or if installed globally:
{
"mcpServers": {
"progress": {
"command": "mcp-progress"
}
}
}
License
ISC
VS Code Setup
This project is configured to work with GitHub Copilot in VS Code. The MCP server configuration is in .vscode/mcp.json.
To use with Copilot:
- Open this project in VS Code
- Make sure GitHub Copilot Chat is enabled
- The MCP server will be automatically available in Copilot Chat
- Use the tools:
@workspace /toolsto see available tools
You can also configure it globally by adding to your VS Code settings:
{
"github.copilot.chat.mcp.enabled": true
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.