Quire MCP Server
Interact with Quire.io projects and tasks using the Quire API, enabling AI assistants to manage your workflow.
⚠️ Disclaimer: Vibe Coding Project ⚠️
This is a "vibe-based" coding project. While functional, it is developed with a focus on rapid implementation and experimentation. Use it at your own risk. The author is not responsible for any consequences, data loss, or unexpected behavior that may arise from its use.
Quire MCP Server
This project provides a Model Context Protocol (MCP) server for Quire. It exposes tools that allow AI assistants to interact with your projects and tasks right from your AI chat interface.
This server uses OAuth2 for authentication and is designed to be run easily via npx.
1. Getting Your Quire Credentials
This server uses an OAuth2 refresh token for authentication. You only need to perform this setup process once.
Step 1: Create a Quire Application
- Go to the Quire Applications page.
- Click Create a new application.
- Fill in the details:
- Name: Give your application a name (e.g., "My-MCP-Client").
- Website: You can use a placeholder, like
https://localhost. - Redirect URI: Set this to
https://localhost. This is crucial for the next step.
- After creating the app, note down the Client ID and Client Secret.
Step 2: Get an Authorization Code
- Construct the following URL in your browser, replacing
YOUR_CLIENT_IDwith the ID you got in the previous step.https://quire.io/oauth?client_id=YOUR_CLIENT_ID&redirect_uri=https://localhost - Visit the URL. You will be asked to log in to Quire and authorize the application.
- After authorizing, your browser will be redirected to a blank page with a URL like:
https://localhost/?code=SOME_LONG_CODE - Copy the
codevalue from the URL. This code is temporary and will be used in the next step.
Step 3: Exchange the Code for a Refresh Token
-
Open your terminal and use
curlto make a POST request to Quire's token endpoint. -
Replace the placeholders with your actual credentials.
curl -X POST https://quire.io/oauth/token \ -d grant_type=authorization_code \ -d code=PASTE_THE_CODE_FROM_STEP_2_HERE \ -d client_id=YOUR_CLIENT_ID \ -d client_secret=YOUR_CLIENT_SECRET -
The response will be a JSON object containing your
access_tokenandrefresh_token. -
Save the
refresh_tokenvalue. This is the token you will use to run the server. It is long-lived and will be used to automatically fetch new access tokens.
2. Quick Start & Usage
Set Environment Variables
Set the following three environment variables in your terminal.
# Replace with the credentials you obtained above
export QUIRE_CLIENT_ID="your_client_id"
export QUIRE_CLIENT_SECRET="your_client_secret"
export QUIRE_REFRESH_TOKEN="your_refresh_token"
Run with npx
Once the environment variables are set, you can run the server with a single command:
npx quire-mcp
3. Cursor Setup Guide
-
Find your
mcp.jsonfile:~/.cursor-settings/mcp.json -
Add the server configuration:
{ "mcpServers": { "quire": { "command": "npx", "args": [ "-y", "quire-mcp" ], "env": { "QUIRE_CLIENT_ID": "${env:QUIRE_CLIENT_ID}", "QUIRE_CLIENT_SECRET": "${env:QUIRE_CLIENT_SECRET}", "QUIRE_REFRESH_TOKEN": "${env:QUIRE_REFRESH_TOKEN}" } } } } -
Ensure Environment Variables are Set: Before launching Cursor, make sure the variables are set in your shell environment (
.zshrc,.bash_profile, etc.). -
Restart Cursor to load the new MCP server.
4. For Developers
Running from Source
- Clone, install dependencies:
git clone <repository_url> cd quire-mcp && npm install - Create a
.envfile:QUIRE_CLIENT_ID=your_client_id QUIRE_CLIENT_SECRET=your_client_secret QUIRE_REFRESH_TOKEN=your_refresh_token - Run the server:
npm run build npm start
Running Tests
npm test
Features
- List projects
- List tasks within a project
- (More features to be added)
Related Servers
OmniTaskAgent
A multi-model agent for managing tasks across various platforms, requiring API keys for different AI models.
PAF-IAST LMS Automation
Automates interactions with the PAF-IAST Learning Management System (LMS) for AI assistants like Claude and VS Code Copilot.
MCP Sound Tool
A sound tool for MCP-compatible IDEs like Cursor. Plays sounds for events like completion, error, and notification.
MoLing MCP Server
A local office automation assistant for file system operations, system command execution, and browser control.
Taskade
Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.
Linear MCP Server
Interact with the Linear project management system using its GraphQL API.
AI Collaboration MCP Server
An MCP server for AI-to-AI collaboration, enabling autonomous workflows and role-based task management between different AI models.
JIRA
Integrate with JIRA to allow AI assistants to directly interact with JIRA issues.
HubSpot MCP
Access and manage HubSpot CRM data through a standardized interface using the HubSpot API.
Google Workspace
Integrates Google Workspace services like Calendar, Drive, and Gmail with AI assistants.