Canvas Poke MCP
Connects Canvas LMS to Poke for proactive text reminders about upcoming assignments and deadlines.
README
Canvas Poke MCP
A Poke recipe integration that connects your Canvas LMS account to Poke, so you get proactive text reminders about upcoming assignments and deadlines.
What it does
- get_upcoming_assignments — Lists all unsubmitted assignments due in the next 14 days across all your courses
- get_urgent_assignments — Flags anything due in the next 48 hours
- get_courses — Lists your active courses
Deploy to Render (free, takes ~5 minutes)
Step 1: Put this code on GitHub
- Go to github.com and sign in
- Click the + icon in the top right, then New repository
- Name it
canvas-poke-mcp - Set it to Public
- Click Create repository
- On the next page, click uploading an existing file
- Upload all the files from this folder (keep the folder structure:
src/index.jsandpackage.jsonin the root) - Click Commit changes
Step 2: Deploy on Render
- Go to render.com and sign up for a free account
- Click New then Web Service
- Connect your GitHub account and select your
canvas-poke-mcprepository - Fill in these settings:
- Name: canvas-poke-mcp
- Runtime: Node
- Build Command:
npm install - Start Command:
npm start - Instance Type: Free
- Click Create Web Service
- Wait about 2 minutes for it to deploy
- Copy your Render URL — it will look like
https://canvas-poke-mcp.onrender.com
Step 3: Get your Canvas API token
- Log in to your school's Canvas (e.g.
https://yourschool.instructure.com) - Click your profile picture in the top right
- Click Settings
- Scroll down to Approved Integrations
- Click + New Access Token
- Give it a name like "Poke" and click Generate Token
- Copy the token — you will only see it once
Step 4: Connect to Poke
- Go to poke.com/settings/connections/integrations/new
- Fill in:
- Name: Canvas
- MCP Server URL: your Render URL +
/mcp(e.g.https://canvas-poke-mcp.onrender.com/mcp) - API Key: your Canvas URL and token joined with a pipe character, like this:
https://yourschool.instructure.com|your_canvas_token_here
- Click Create Integration
Step 5: Test it
Text Poke:
"What assignments do I have due this week?"
or
"Do I have anything urgent due soon?"
Create the Recipe (to earn payouts)
- Go to poke.com/kitchen
- Click Create recipe
- Fill in:
- Name: Canvas Assignment Tracker
- Description: Never miss a deadline. Poke monitors your Canvas courses and texts you about upcoming assignments and anything due in the next 48 hours.
- Onboarding context: Ask the user for their Canvas school URL (e.g. https://school.instructure.com) and their Canvas personal access token, which they can generate in Canvas Settings > Approved Integrations. Combine them as "url|token" and add the integration at poke.com/settings/connections/integrations/new using the MCP server URL provided.
- Prefilled first message: "What assignments do I have due this week?"
- Click Publish
- Share your recipe link everywhere
Notes
- The free Render tier spins down after 15 minutes of inactivity. The first request after spin-down takes ~30 seconds. Upgrading to Render's $7/month tier keeps it always-on.
- Canvas API tokens do not expire unless manually deleted.
- This server never stores your token — it passes through per-request only.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.