google-task-ifttt-webhook-mcp
MCP server running on Cloudflare Workers that exposes a create_google_task tool to send tasks to Google Tasks via IFTTT Maker webhook.
README
google-task-ifttt-webhook-mcp
MCP server running on Cloudflare Workers that exposes a create_google_task tool.
Sends tasks to Google Tasks via the IFTTT Maker webhook.
Authentication is handled by Cloudflare Access (OAuth).
How it works
MCP Client Cloudflare Access Cloudflare Worker IFTTT
| | | |
|-- OAuth login ------------>| | |
|<-- JWT token --------------| | |
| | | |
|-- POST (tools/call) ------>|-- Cf-Access-Jwt-Assertion->| |
| | |-- POST webhook ---->|
| | |<-- "Congratulations"|
|<-- result -----------------|<-------------------------| |
Prerequisites
- Node.js 18+
- Cloudflare account with Workers enabled
- Cloudflare Access (requires Cloudflare Zero Trust)
- IFTTT account with the Maker Webhooks service connected
- A Google Tasks applet on IFTTT triggered by the
taskevent from Maker Webhooks
Setup
1. Install dependencies
npm install
2. Get your IFTTT Maker key
- Go to IFTTT Maker Webhooks
- Click Documentation
- Your key is the last path segment of the URL shown:
https://maker.ifttt.com/use/{YOUR_KEY} - Set it as a Worker secret:
npx wrangler secret put IFTTT_MAKER_TASK_KEY
3. Set up the IFTTT applet
Create an applet on IFTTT:
- If: Maker Webhooks → Receive a web request with event name
task - Then: Google Tasks → Create a task
- Title:
{{Value1}} - Notes:
{{Value2}} - Due date:
{{Value3}}
- Title:
4. Configure Cloudflare Access
- Go to Cloudflare Zero Trust dashboard
- Navigate to Access → Applications → Add an application → Self-hosted
- Configure:
- Application name:
google-task-mcp - Application domain:
google-task-mcp.yourdomain.com(or a*.workers.devsubdomain) - Identity providers: Select your preferred IdP (Google, GitHub, email OTP, etc.)
- Policy: Create an allow policy for the users who should access the MCP server
- Application name:
- Note your team domain (e.g.
myteam.cloudflareaccess.com) and the Application Audience (AUD) tag - Set them in
wrangler.jsoncor via wrangler vars:
npx wrangler secret put CF_ACCESS_TEAM_DOMAIN
npx wrangler secret put CF_ACCESS_AUD
5. Deploy
npm run deploy
6. Test locally (optional)
npm run dev
The worker will be available at http://localhost:8787. For local testing without Cloudflare Access, the JWT check can be bypassed by sending a dummy JWT header.
7. Configure the MCP client
opencode
Add to your opencode configuration:
{
"mcpServers": {
"google-tasks": {
"type": "streamableHttp",
"url": "https://google-task-mcp.yourdomain.com",
"auth": "oauth"
}
}
}
The client will discover the OAuth flow from /.well-known/oauth-authorization-server and redirect to Cloudflare Access for login.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"google-tasks": {
"command": "npx",
"args": [
"@anthropic-ai/mcp-client",
"streamableHttp",
"https://google-task-mcp.yourdomain.com"
],
"env": {
"MCP_AUTH": "oauth"
}
}
}
}
Tool: create_google_task
| Parameter | Required | Description |
|---|---|---|
title |
yes | Single-line task title |
notes |
no | Optional detailed notes. \n for line breaks |
due |
no | Optional due date in ISO 8601 UTC (e.g. 2026-07-25T23:59:59Z) |
Example MCP call
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "create_google_task",
"arguments": {
"title": "Buy groceries",
"notes": "Milk, eggs, bread",
"due": "2026-07-25T23:59:59Z"
}
}
}
Secrets
| Secret | Description |
|---|---|
IFTTT_MAKER_TASK_KEY |
IFTTT Maker Webhooks key (required) |
CF_ACCESS_TEAM_DOMAIN |
Cloudflare Zero Trust team domain (required for OAuth) |
CF_ACCESS_AUD |
Cloudflare Access application audience tag (optional, enables audience validation) |
Set via:
npx wrangler secret put <NAME>
Endpoints
| Method | Path | Description |
|---|---|---|
GET |
/.well-known/oauth-authorization-server |
OAuth metadata for MCP client discovery |
POST |
/ |
MCP JSON-RPC endpoint (requires Cf-Access-Jwt-Assertion header) |
OPTIONS |
/ |
CORS preflight |
Troubleshooting
"Unauthorized: Cloudflare Access authentication required"
The request is missing the Cf-Access-Jwt-Assertion header. Ensure Cloudflare Access is properly configured and the client is authenticated through Access.
"IFTTT webhook failed (HTTP 404)"
The Maker key is invalid or the task event name doesn't match any applet. Verify the key and check your IFTTT applet configuration.
"IFTTT_MAKER_TASK_KEY is not configured"
Set the secret via npx wrangler secret put IFTTT_MAKER_TASK_KEY and redeploy.
OAuth flow not working
Check that CF_ACCESS_TEAM_DOMAIN matches your Cloudflare Zero Trust team domain exactly (without https://).
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.